json state proxy

## Why

Workers currently update their custom model-card cache by reacting to
`CustomModelCardAdded` / `CustomModelCardDeleted` events directly. That
is another snapshot footgun: a worker restored from State may never see
the historical add/delete event, so the durable State must include the
desired custom-card set.

## How

- Add `State.custom_model_cards`, keyed by `ModelId`.
- Reduce `CustomModelCardAdded` into State.
- Reduce `CustomModelCardDeleted` into State.
- Add focused reducer tests for add and delete.

This PR only makes custom cards durable in State. A follow-up PR will
make workers reconcile their on-disk custom-card cache from this state
instead of relying on those events directly.

## Tests

- `uv run pytest
src/exo/shared/tests/test_apply/test_apply_custom_model_cards.py
src/exo/shared/tests/test_state_serialization.py`
- `uv run pytest`
- `uv run ruff check src/exo/shared/types/state.py
src/exo/shared/apply.py
src/exo/shared/tests/test_apply/test_apply_custom_model_cards.py`
- `uv run basedpyright`
- `nix fmt`

Cargo.toml

@@ -1,6 +1,6 @@
 [workspace]
 resolver = "3"
-members = ["rust/networking", "rust/exo_pyo3_bindings", "rust/util"]
+members = ["rust/exo_pyo3_bindings", "rust/networking"]
 
 [workspace.package]
 version = "0.0.1"
@@ -20,30 +20,19 @@ opt-level = 3
 [workspace.dependencies]
 ## Crate members as common dependencies
 networking = { path = "rust/networking" }
-util = { path = "rust/util" }
 
 # Macro dependecies
 extend = "1.2"
-delegate = "0.13"
-
-# Utility dependencies
-keccak-const = "0.2"
-
-# Async dependencies
-async-stream = "0.3"
 tokio = "1.46"
 futures-lite = "2.6.1"
-futures-timer = "3.0"
-
-# Data structures
-either = "1.15"
 
 # Tracing/logging
 log = "0.4"
+env_logger = "0.11.10"
 
 # networking
-libp2p = "0.56"
-libp2p-tcp = "0.44"
+zenoh = "=1.9.0"
+zerompk = "0.4.2"
 
 [workspace.lints.rust]
 static_mut_refs = "warn"      # Or use "warn" instead of deny

app/EXO/EXO/ContentView.swift

@@ -16,22 +16,13 @@ struct ContentView: View {
     @EnvironmentObject private var updater: SparkleUpdater
     @EnvironmentObject private var thunderboltBridgeService: ThunderboltBridgeService
     @EnvironmentObject private var settingsWindowController: SettingsWindowController
+    @EnvironmentObject private var bugReportWindowController: BugReportWindowController
     @State private var focusedNode: NodeViewModel?
     @State private var deletingInstanceIDs: Set<String> = []
     @State private var showAllNodes = false
     @State private var showAllInstances = false
     @State private var baseURLCopied = false
     @State private var showAdvanced = false
-    @State private var showDebugInfo = false
-    private enum BugReportPhase: Equatable {
-        case idle
-        case prompting
-        case sending(String)
-        case success(String)
-        case failure(String)
-    }
-    @State private var bugReportPhase: BugReportPhase = .idle
-    @State private var bugReportUserDescription: String = ""
     @State private var uninstallInProgress = false
     @State private var pendingNamespace: String = ""
     @State private var pendingHFToken: String = ""
@@ -294,6 +285,13 @@ struct ContentView: View {
             ) {
                 updater.checkForUpdates()
             }
+            HoverButton(
+                title: "Share Bug Report…",
+                tint: .primary,
+                trailingSystemImage: "ladybug"
+            ) {
+                bugReportWindowController.open()
+            }
             .padding(.bottom, 8)
             HoverButton(title: "Quit", tint: .secondary) {
                 controller.stop()
@@ -477,40 +475,6 @@ struct ContentView: View {
         }
     }
 
-    private var debugSection: some View {
-        VStack(alignment: .leading, spacing: 4) {
-            HoverButton(
-                title: "Debug Info",
-                tint: .primary,
-                trailingSystemImage: showDebugInfo ? "chevron.up" : "chevron.down",
-                small: true
-            ) {
-                showDebugInfo.toggle()
-            }
-            if showDebugInfo {
-                VStack(alignment: .leading, spacing: 4) {
-                    Text("Version: \(buildTag)")
-                        .font(.caption2)
-                        .foregroundColor(.secondary)
-                    Text("Commit: \(buildCommit)")
-                        .font(.caption2)
-                        .foregroundColor(.secondary)
-                    Text(thunderboltStatusText)
-                        .font(.caption2)
-                        .foregroundColor(thunderboltStatusColor)
-                    clusterThunderboltBridgeView
-                    interfaceIpList
-                    rdmaStatusView
-                    sendBugReportButton
-                        .padding(.top, 6)
-                }
-                .padding(.leading, 8)
-                .transition(.opacity)
-            }
-        }
-        .animation(.easeInOut(duration: 0.25), value: showDebugInfo)
-    }
-
     private var rdmaStatusView: some View {
         let rdmaStatuses = stateService.latestSnapshot?.nodeRdmaCtl ?? [:]
         let localNodeId = stateService.localNodeId
@@ -559,127 +523,6 @@ struct ContentView: View {
         }
     }
 
-    private var sendBugReportButton: some View {
-        VStack(alignment: .leading, spacing: 6) {
-            switch bugReportPhase {
-            case .idle:
-                Button {
-                    bugReportPhase = .prompting
-                    bugReportUserDescription = ""
-                } label: {
-                    HStack {
-                        Text("Send Bug Report")
-                            .font(.caption)
-                            .fontWeight(.semibold)
-                        Spacer()
-                    }
-                    .padding(.vertical, 6)
-                    .padding(.horizontal, 8)
-                    .background(
-                        RoundedRectangle(cornerRadius: 6)
-                            .fill(Color.accentColor.opacity(0.12))
-                    )
-                }
-                .buttonStyle(.plain)
-
-            case .prompting:
-                VStack(alignment: .leading, spacing: 6) {
-                    VStack(alignment: .leading, spacing: 2) {
-                        Text("Tell us what went wrong (optional)")
-                            .font(.caption2)
-                            .foregroundColor(.secondary)
-                        Text(
-                            "A quick description of what you were doing and what happened helps us track down the bug for you."
-                        )
-                        .font(.caption2)
-                        .foregroundColor(.secondary)
-                        .opacity(0.8)
-                        .fixedSize(horizontal: false, vertical: true)
-                    }
-                    TextEditor(text: $bugReportUserDescription)
-                        .font(.caption2)
-                        .frame(height: 60)
-                        .overlay(
-                            RoundedRectangle(cornerRadius: 4)
-                                .stroke(Color.secondary.opacity(0.3), lineWidth: 1)
-                        )
-                    HStack(spacing: 8) {
-                        Button("Send") {
-                            Task {
-                                await sendBugReport()
-                            }
-                        }
-                        .font(.caption2)
-                        .buttonStyle(.borderedProminent)
-                        .controlSize(.small)
-                        Button("Cancel") {
-                            bugReportPhase = .idle
-                        }
-                        .font(.caption2)
-                        .buttonStyle(.bordered)
-                        .controlSize(.small)
-                    }
-                }
-                .padding(8)
-                .background(
-                    RoundedRectangle(cornerRadius: 6)
-                        .fill(Color.accentColor.opacity(0.06))
-                )
-
-            case .sending(let message):
-                HStack(spacing: 6) {
-                    ProgressView()
-                        .scaleEffect(0.6)
-                    Text(message)
-                        .font(.caption2)
-                        .foregroundColor(.secondary)
-                }
-
-            case .success(let message):
-                VStack(alignment: .leading, spacing: 6) {
-                    Text(message)
-                        .font(.caption2)
-                        .foregroundColor(.secondary)
-                        .fixedSize(horizontal: false, vertical: true)
-                    Button {
-                        openGitHubIssue()
-                    } label: {
-                        HStack(spacing: 4) {
-                            Image(systemName: "arrow.up.right.square")
-                                .imageScale(.small)
-                            Text("Create GitHub Issue")
-                                .font(.caption2)
-                        }
-                    }
-                    .buttonStyle(.bordered)
-                    .controlSize(.small)
-                    Button("Done") {
-                        bugReportPhase = .idle
-                        bugReportUserDescription = ""
-                    }
-                    .font(.caption2)
-                    .buttonStyle(.plain)
-                    .foregroundColor(.secondary)
-                }
-
-            case .failure(let message):
-                VStack(alignment: .leading, spacing: 4) {
-                    Text(message)
-                        .font(.caption2)
-                        .foregroundColor(.red)
-                        .fixedSize(horizontal: false, vertical: true)
-                    Button("Dismiss") {
-                        bugReportPhase = .idle
-                    }
-                    .font(.caption2)
-                    .buttonStyle(.plain)
-                    .foregroundColor(.secondary)
-                }
-            }
-        }
-        .animation(.easeInOut(duration: 0.2), value: bugReportPhase)
-    }
-
     private var processToggleBinding: Binding<Bool> {
         Binding(
             get: {
@@ -720,61 +563,6 @@ struct ContentView: View {
         )
     }
 
-    private func sendBugReport() async {
-        bugReportPhase = .sending("Collecting logs...")
-        let service = BugReportService()
-        let description = bugReportUserDescription.trimmingCharacters(in: .whitespacesAndNewlines)
-        do {
-            let outcome = try await service.sendReport(
-                isManual: true,
-                userDescription: description.isEmpty ? nil : description
-            )
-            if outcome.success {
-                bugReportPhase = .success(outcome.message)
-            } else {
-                bugReportPhase = .failure(outcome.message)
-            }
-        } catch {
-            bugReportPhase = .failure(error.localizedDescription)
-        }
-    }
-
-    private func openGitHubIssue() {
-        let description = bugReportUserDescription.trimmingCharacters(in: .whitespacesAndNewlines)
-
-        var bodyParts: [String] = []
-        bodyParts.append("## Describe the bug")
-        bodyParts.append("")
-        if !description.isEmpty {
-            bodyParts.append(description)
-        } else {
-            bodyParts.append("A clear and concise description of what the bug is.")
-        }
-        bodyParts.append("")
-        bodyParts.append("## Environment")
-        bodyParts.append("")
-        bodyParts.append("- macOS Version: \(ProcessInfo.processInfo.operatingSystemVersionString)")
-        bodyParts.append("- EXO Version: \(buildTag) (\(buildCommit))")
-        bodyParts.append("")
-        bodyParts.append("## Additional context")
-        bodyParts.append("")
-        bodyParts.append("A bug report with diagnostic logs was submitted via the app.")
-
-        let body = bodyParts.joined(separator: "\n")
-
-        var components = URLComponents(string: "https://github.com/exo-explore/exo/issues/new")!
-        components.queryItems = [
-            URLQueryItem(name: "template", value: "bug_report.md"),
-            URLQueryItem(name: "title", value: "[BUG] "),
-            URLQueryItem(name: "body", value: body),
-            URLQueryItem(name: "labels", value: "bug"),
-        ]
-
-        if let url = components.url {
-            NSWorkspace.shared.open(url)
-        }
-    }
-
     private func showUninstallConfirmationAlert() {
         let alert = NSAlert()
         alert.messageText = "Uninstall EXO"
@@ -857,13 +645,6 @@ struct ContentView: View {
         }
     }
 
-    private var buildTag: String {
-        Bundle.main.infoDictionary?["EXOBuildTag"] as? String ?? "unknown"
-    }
-
-    private var buildCommit: String {
-        Bundle.main.infoDictionary?["EXOBuildCommit"] as? String ?? "unknown"
-    }
 }
 
 private struct HoverButton: View {

app/EXO/EXO/EXOApp.swift

@@ -22,6 +22,7 @@ struct EXOApp: App {
     @StateObject private var updater: SparkleUpdater
     @StateObject private var thunderboltBridgeService: ThunderboltBridgeService
     @StateObject private var settingsWindowController: SettingsWindowController
+    @StateObject private var bugReportWindowController: BugReportWindowController
     private let terminationObserver: TerminationObserver
     private let firstLaunchPopout = FirstLaunchPopout()
     private let ciContext = CIContext(options: nil)
@@ -46,6 +47,7 @@ struct EXOApp: App {
         let thunderboltBridge = ThunderboltBridgeService(clusterStateService: service)
         _thunderboltBridgeService = StateObject(wrappedValue: thunderboltBridge)
         _settingsWindowController = StateObject(wrappedValue: SettingsWindowController())
+        _bugReportWindowController = StateObject(wrappedValue: BugReportWindowController())
         enableLaunchAtLoginIfNeeded()
         // Install LaunchDaemon to disable Thunderbolt Bridge on startup (prevents network loops)
         NetworkSetupHelper.promptAndInstallIfNeeded()
@@ -66,6 +68,7 @@ struct EXOApp: App {
                 .environmentObject(updater)
                 .environmentObject(thunderboltBridgeService)
                 .environmentObject(settingsWindowController)
+                .environmentObject(bugReportWindowController)
         } label: {
             menuBarIcon
                 .onReceive(controller.$isFirstLaunchReady) { ready in

app/EXO/EXO/Services/ClusterStateService.swift

@@ -17,7 +17,7 @@ final class ClusterStateService: ObservableObject {
 
     init(
         baseURL: URL = URL(string: "http://127.0.0.1:52415")!,
-        session: URLSession = .shared
+        session: URLSession = ClusterStateService.makeNonCachingSession()
     ) {
         self.baseURL = baseURL
         self.endpoint = baseURL.appendingPathComponent("state")
@@ -27,6 +27,23 @@ final class ClusterStateService: ObservableObject {
         self.decoder = decoder
     }
 
+    /// `URLSession.shared` carries an on-disk `URLCache` that persists every
+    /// response body under `~/Library/Caches/exolabs.EXO/`. We poll `/state`
+    /// at 2 Hz from `startPolling`, so leaving the shared cache attached
+    /// dirties ~500–620 KB/sec of file-backed memory and trips macOS's
+    /// per-process `disk writes` resource limit (microstackshot reports
+    /// observed on M3 Ultra producing GBs of cached responses per hour).
+    /// Cluster-state polling responses are time-sensitive and small; they
+    /// gain nothing from being cached on disk. Use an ephemeral session
+    /// with `urlCache = nil` so neither response bodies nor metadata
+    /// touch disk.
+    private static func makeNonCachingSession() -> URLSession {
+        let config = URLSessionConfiguration.ephemeral
+        config.urlCache = nil
+        config.requestCachePolicy = .reloadIgnoringLocalCacheData
+        return URLSession(configuration: config)
+    }
+
     func startPolling(interval: TimeInterval = 0.5) {
         stopPolling()
         Task {

app/EXO/EXO/Views/BugReportWindowController.swift

@@ -0,0 +1,242 @@
+import AppKit
+import SwiftUI
+
+/// Manages a standalone window for the bug-report flow.
+/// Ensures only one instance exists and brings it to front on repeated opens.
+@MainActor
+final class BugReportWindowController: ObservableObject {
+    private var window: NSWindow?
+
+    func open() {
+        if let existing = window, existing.isVisible {
+            existing.makeKeyAndOrderFront(nil)
+            NSApp.activate()
+            return
+        }
+
+        let view = BugReportView(onDismiss: { [weak self] in
+            self?.window?.close()
+        })
+
+        let hostingController = NSHostingController(rootView: view)
+        hostingController.sizingOptions = [.preferredContentSize, .minSize]
+
+        let newWindow = NSWindow(contentViewController: hostingController)
+        newWindow.styleMask = [.titled, .closable, .resizable]
+        newWindow.title = "Send a Bug Report"
+        newWindow.center()
+        newWindow.setFrameAutosaveName("ExoBugReportWindow")
+        newWindow.isReleasedWhenClosed = false
+        newWindow.makeKeyAndOrderFront(nil)
+        NSApp.activate()
+
+        window = newWindow
+    }
+}
+
+private struct BugReportView: View {
+    fileprivate enum Phase: Equatable {
+        case prompting
+        case sending(String)
+        case success(String)
+        case failure(String)
+    }
+
+    let onDismiss: () -> Void
+
+    @State private var phase: Phase = .prompting
+    @State private var userDescription: String = ""
+    @FocusState private var descriptionFocused: Bool
+
+    var body: some View {
+        VStack(alignment: .leading, spacing: 12) {
+            switch phase {
+            case .prompting:
+                promptingView
+            case .sending(let message):
+                sendingView(message: message)
+            case .success(let message):
+                successView(message: message)
+            case .failure(let message):
+                failureView(message: message)
+            }
+        }
+        .padding(16)
+        .frame(minWidth: 380)
+        .animation(.easeInOut(duration: 0.2), value: phase)
+        .onAppear { descriptionFocused = true }
+    }
+
+    private var promptingView: some View {
+        VStack(alignment: .leading, spacing: 8) {
+            Text("Description (optional)")
+                .font(.subheadline)
+                .foregroundColor(.secondary)
+            ZStack(alignment: .topLeading) {
+                if userDescription.isEmpty {
+                    Text("What were you doing when it broke?")
+                        .font(.body)
+                        .foregroundColor(Color(nsColor: .placeholderTextColor))
+                        .padding(.horizontal, 10)
+                        .padding(.vertical, 8)
+                        .allowsHitTesting(false)
+                }
+                TextEditor(text: $userDescription)
+                    .font(.body)
+                    .scrollContentBackground(.hidden)
+                    .padding(4)
+                    .frame(height: 72)
+                    .focused($descriptionFocused)
+            }
+            .background(
+                RoundedRectangle(cornerRadius: 6)
+                    .fill(Color(nsColor: .textBackgroundColor))
+            )
+            .overlay(
+                RoundedRectangle(cornerRadius: 6)
+                    .strokeBorder(Color(nsColor: .separatorColor), lineWidth: 1)
+            )
+
+            Text("Diagnostic logs will be uploaded with your report.")
+                .font(.caption)
+                .foregroundColor(.secondary)
+
+            HStack {
+                Spacer()
+                Button("Cancel") { onDismiss() }
+                    .keyboardShortcut(.cancelAction)
+                Button("Send") {
+                    Task { await send() }
+                }
+                .keyboardShortcut(.defaultAction)
+            }
+            .padding(.top, 4)
+        }
+    }
+
+    private func sendingView(message: String) -> some View {
+        VStack(alignment: .leading, spacing: 12) {
+            HStack(spacing: 10) {
+                ProgressView().controlSize(.small)
+                Text(message)
+                    .foregroundColor(.secondary)
+            }
+            HStack {
+                Spacer()
+                Button("Cancel") { onDismiss() }
+                    .keyboardShortcut(.cancelAction)
+                    .disabled(true)
+                Button("Send") {}
+                    .disabled(true)
+            }
+        }
+    }
+
+    private func successView(message: String) -> some View {
+        VStack(alignment: .leading, spacing: 12) {
+            HStack(alignment: .top, spacing: 10) {
+                Image(systemName: "checkmark.circle.fill")
+                    .foregroundColor(.green)
+                    .font(.title2)
+                Text(message)
+                    .fixedSize(horizontal: false, vertical: true)
+            }
+            HStack {
+                Button {
+                    openGitHubIssue()
+                } label: {
+                    HStack(spacing: 4) {
+                        Image(systemName: "arrow.up.right.square")
+                        Text("Open GitHub Issue")
+                    }
+                }
+                Spacer()
+                Button("Done") { onDismiss() }
+                    .keyboardShortcut(.defaultAction)
+            }
+        }
+    }
+
+    private func failureView(message: String) -> some View {
+        VStack(alignment: .leading, spacing: 12) {
+            HStack(alignment: .top, spacing: 10) {
+                Image(systemName: "exclamationmark.triangle.fill")
+                    .foregroundColor(.orange)
+                    .font(.title2)
+                Text(message)
+                    .fixedSize(horizontal: false, vertical: true)
+            }
+            HStack {
+                Spacer()
+                Button("Try Again") {
+                    phase = .prompting
+                }
+                Button("Close") { onDismiss() }
+                    .keyboardShortcut(.defaultAction)
+            }
+        }
+    }
+
+    private func send() async {
+        phase = .sending("Collecting logs and uploading…")
+        let service = BugReportService()
+        let description = userDescription.trimmingCharacters(in: .whitespacesAndNewlines)
+        do {
+            let outcome = try await service.sendReport(
+                isManual: true,
+                userDescription: description.isEmpty ? nil : description
+            )
+            if outcome.success {
+                phase = .success(outcome.message)
+            } else {
+                phase = .failure(outcome.message)
+            }
+        } catch {
+            phase = .failure(error.localizedDescription)
+        }
+    }
+
+    private func openGitHubIssue() {
+        let description = userDescription.trimmingCharacters(in: .whitespacesAndNewlines)
+
+        var bodyParts: [String] = []
+        bodyParts.append("## Describe the bug")
+        bodyParts.append("")
+        if !description.isEmpty {
+            bodyParts.append(description)
+        } else {
+            bodyParts.append("A clear and concise description of what the bug is.")
+        }
+        bodyParts.append("")
+        bodyParts.append("## Environment")
+        bodyParts.append("")
+        bodyParts.append("- macOS Version: \(ProcessInfo.processInfo.operatingSystemVersionString)")
+        bodyParts.append("- EXO Version: \(buildTag) (\(buildCommit))")
+        bodyParts.append("")
+        bodyParts.append("## Additional context")
+        bodyParts.append("")
+        bodyParts.append("A bug report with diagnostic logs was submitted via the app.")
+
+        let body = bodyParts.joined(separator: "\n")
+
+        var components = URLComponents(string: "https://github.com/exo-explore/exo/issues/new")!
+        components.queryItems = [
+            URLQueryItem(name: "template", value: "bug_report.md"),
+            URLQueryItem(name: "title", value: "[BUG] "),
+            URLQueryItem(name: "body", value: body),
+            URLQueryItem(name: "labels", value: "bug"),
+        ]
+
+        if let url = components.url {
+            NSWorkspace.shared.open(url)
+        }
+    }
+
+    private var buildTag: String {
+        Bundle.main.infoDictionary?["EXOBuildTag"] as? String ?? "unknown"
+    }
+
+    private var buildCommit: String {
+        Bundle.main.infoDictionary?["EXOBuildCommit"] as? String ?? "unknown"
+    }
+}

app/EXO/EXO/Views/SettingsView.swift

@@ -21,8 +21,6 @@ struct SettingsView: View {
     @State private var pendingReadOnlyModelsDirs: String = ""
     @State private var pendingCustomEnvironmentVariables: [CustomEnvironmentVariable] = []
     @State private var needsRestart = false
-    @State private var bugReportInFlight = false
-    @State private var bugReportMessage: String?
     @State private var uninstallInProgress = false
 
     var body: some View {
@@ -202,8 +200,6 @@ struct SettingsView: View {
                 VStack(alignment: .leading, spacing: 2) {
                     rdmaStatusView
                 }
-
-                sendBugReportButton
             }
 
             Section("Danger Zone") {
@@ -504,50 +500,8 @@ struct SettingsView: View {
         }
     }
 
-    private var sendBugReportButton: some View {
-        VStack(alignment: .leading, spacing: 4) {
-            Button {
-                Task {
-                    await sendBugReport()
-                }
-            } label: {
-                HStack {
-                    if bugReportInFlight {
-                        ProgressView()
-                            .scaleEffect(0.6)
-                    }
-                    Text("Send Bug Report")
-                        .font(.caption)
-                        .fontWeight(.semibold)
-                    Spacer()
-                }
-            }
-            .disabled(bugReportInFlight)
-
-            if let message = bugReportMessage {
-                Text(message)
-                    .font(.caption2)
-                    .foregroundColor(.secondary)
-                    .fixedSize(horizontal: false, vertical: true)
-            }
-        }
-    }
-
     // MARK: - Actions
 
-    private func sendBugReport() async {
-        bugReportInFlight = true
-        bugReportMessage = "Collecting logs..."
-        let service = BugReportService()
-        do {
-            let outcome = try await service.sendReport(isManual: true)
-            bugReportMessage = outcome.message
-        } catch {
-            bugReportMessage = error.localizedDescription
-        }
-        bugReportInFlight = false
-    }
-
     private func showUninstallConfirmationAlert() {
         let alert = NSAlert()
         alert.messageText = "Uninstall EXO"

dashboard/src/routes/+page.svelte

@@ -3435,6 +3435,7 @@
             >
               <li>Connect nodes with TB5 cables</li>
               <li>Boot to Recovery (hold power 10s → Options)</li>
+              <li>Open Terminal from the Utilities menu</li>
               <li>
                 Run
                 <code class="text-yellow-300 bg-yellow-400/10 px-1 rounded"
@@ -4822,6 +4823,7 @@
                 >
                   <li>Connect nodes with TB5 cables</li>
                   <li>Boot to Recovery (hold power 10s → Options)</li>
+                  <li>Open Terminal from the Utilities menu</li>
                   <li>
                     Run
                     <code class="text-yellow-300 bg-yellow-400/10 px-1 rounded"
@@ -4968,6 +4970,7 @@
                   >
                     <li>Connect nodes with TB5 cables</li>
                     <li>Boot to Recovery (hold power 10s → Options)</li>
+                    <li>Open Terminal from the Utilities menu</li>
                     <li>
                       Run
                       <code

flake.lock

@@ -47,11 +47,11 @@
         "rust-analyzer-src": "rust-analyzer-src"
       },
       "locked": {
-        "lastModified": 1775807984,
-        "narHash": "sha256-Redoe3D9zGN5I9QPHWL9vfMVQBehY1fKsMiRXQ83X3w=",
+        "lastModified": 1777708550,
+        "narHash": "sha256-Qif3UXT0l5OQq8H9pRWt4/ia4gF48MWK2oHKL8uVx8U=",
         "owner": "nix-community",
         "repo": "fenix",
-        "rev": "fcf90c0c4d368b2ca917a7afa6d08e98a397e5fd",
+        "rev": "74c1591efaff494756b8d35ebe357c6c2bbdca96",
         "type": "github"
       },
       "original": {
@@ -218,11 +218,11 @@
     "rust-analyzer-src": {
       "flake": false,
       "locked": {
-        "lastModified": 1775745684,
-        "narHash": "sha256-8MbfLwd60FNa8dRFkjE+G3TT/x21G3Rsplm1bMBQUtU=",
+        "lastModified": 1777639980,
+        "narHash": "sha256-6d7Hdurvbjc5uwJuc0YiK7rZBGj6Gs3uzfBFcTs+xCc=",
         "owner": "rust-lang",
         "repo": "rust-analyzer",
-        "rev": "64ddb549bc9a70d011328746fa46a8883f937b6b",
+        "rev": "64cdaeb06f69b6b769a492edd88b022ae88e8ca2",
         "type": "github"
       },
       "original": {

flake.nix

@@ -146,7 +146,7 @@
                 config.treefmt.build.wrapper
 
                 # PYTHON
-                self'.packages.editableVenv
+                #self'.packages.editableVenv
                 uv
 
                 # RUST

rust/exo_pyo3_bindings/Cargo.toml

@@ -22,7 +22,8 @@ doc = false
 workspace = true
 
 [dependencies]
-networking = { workspace = true }
+networking.workspace = true
+extend.workspace = true
 
 # interop
 pyo3 = { version = "0.27.2", features = [
@@ -46,21 +47,17 @@ pyo3-async-runtimes = { version = "0.27.0", features = [
 ] }
 pyo3-log = "0.13.2"
 
-# macro dependencies
-extend = { workspace = true }
-delegate = { workspace = true }
-
 # async runtime
 tokio = { workspace = true, features = ["full", "tracing"] }
 futures-lite = { workspace = true }
-
-# utility dependencies
-util = { workspace = true }
+pin-project = "1.1.10"
 
 # Tracing
-log = { workspace = true }
-env_logger = "0.11"
+log.workspace = true
+env_logger.workspace = true
 
 # Networking
-libp2p = { workspace = true, features = ["full"] }
-pin-project = "1.1.10"
+zenoh.workspace = true
+zerompk.workspace = true
+rand = "0.10.1"
+serde_json = "1.0.149"

rust/exo_pyo3_bindings/exo_pyo3_bindings.pyi

@@ -1,94 +1,11 @@
 # This file is automatically generated by pyo3_stub_gen
 # ruff: noqa: E501, F401
 
-import builtins
 import typing
 
 @typing.final
-class AllQueuesFullError(builtins.Exception):
-    def __new__(cls, *args: typing.Any) -> AllQueuesFullError: ...
-    def __repr__(self) -> builtins.str: ...
-    def __str__(self) -> builtins.str: ...
-
-@typing.final
-class Keypair:
-    r"""
-    Identity keypair of a node.
-    """
+class StateProxy:
     @staticmethod
-    def generate() -> Keypair:
-        r"""
-        Generate a new Ed25519 keypair.
-        """
-    @staticmethod
-    def from_bytes(bytes: bytes) -> Keypair:
-        r"""
-        Construct an Ed25519 keypair from secret key bytes
-        """
-    def to_bytes(self) -> bytes:
-        r"""
-        Get the secret key bytes underlying the keypair
-        """
-    def to_node_id(self) -> builtins.str:
-        r"""
-        Convert the `Keypair` into the corresponding `PeerId` string, which we use as our `NodeId`.
-        """
-
-@typing.final
-class MessageTooLargeError(builtins.Exception):
-    def __new__(cls, *args: typing.Any) -> MessageTooLargeError: ...
-    def __repr__(self) -> builtins.str: ...
-    def __str__(self) -> builtins.str: ...
-
-@typing.final
-class NetworkingHandle:
-    def __new__(cls, identity: Keypair, bootstrap_peers: typing.Sequence[builtins.str], listen_port: builtins.int) -> NetworkingHandle: ...
-    async def gossipsub_subscribe(self, topic: builtins.str) -> builtins.bool:
-        r"""
-        Subscribe to a `GossipSub` topic.
-        
-        Returns `True` if the subscription worked. Returns `False` if we were already subscribed.
-        """
-    async def gossipsub_unsubscribe(self, topic: builtins.str) -> builtins.bool:
-        r"""
-        Unsubscribes from a `GossipSub` topic.
-        
-        Returns `True` if we were subscribed to this topic. Returns `False` if we were not subscribed.
-        """
-    async def gossipsub_publish(self, topic: builtins.str, data: bytes) -> None:
-        r"""
-        Publishes a message with multiple topics to the `GossipSub` network.
-        
-        If no peers are found that subscribe to this topic, throws `NoPeersSubscribedToTopicError` exception.
-        """
-    async def recv(self) -> PyFromSwarm: ...
-
-@typing.final
-class NoPeersSubscribedToTopicError(builtins.Exception):
-    def __new__(cls, *args: typing.Any) -> NoPeersSubscribedToTopicError: ...
-    def __repr__(self) -> builtins.str: ...
-    def __str__(self) -> builtins.str: ...
-
-class PyFromSwarm:
-    @typing.final
-    class Connection(PyFromSwarm):
-        __match_args__ = ("peer_id", "connected",)
-        @property
-        def peer_id(self) -> builtins.str: ...
-        @property
-        def connected(self) -> builtins.bool: ...
-        def __new__(cls, peer_id: builtins.str, connected: builtins.bool) -> PyFromSwarm.Connection: ...
-    
-    @typing.final
-    class Message(PyFromSwarm):
-        __match_args__ = ("origin", "topic", "data",)
-        @property
-        def origin(self) -> builtins.str: ...
-        @property
-        def topic(self) -> builtins.str: ...
-        @property
-        def data(self) -> bytes: ...
-        def __new__(cls, origin: builtins.str, topic: builtins.str, data: bytes) -> PyFromSwarm.Message: ...
-    
-    ...
+    async def init() -> StateProxy: ...
+    async def snapshot(self) -> str: ...
 

rust/exo_pyo3_bindings/src/ident.rs

@@ -1,5 +1,4 @@
 use crate::ext::ResultExt as _;
-use libp2p::identity::Keypair;
 use pyo3::types::{PyBytes, PyBytesMethods as _};
 use pyo3::{Bound, PyResult, Python, pyclass, pymethods};
 use pyo3_stub_gen::derive::{gen_stub_pyclass, gen_stub_pymethods};
@@ -8,7 +7,7 @@ use pyo3_stub_gen::derive::{gen_stub_pyclass, gen_stub_pymethods};
 #[gen_stub_pyclass]
 #[pyclass(name = "Keypair", frozen)]
 #[repr(transparent)]
-pub struct PyKeypair(pub Keypair);
+pub struct PyKeypair(pub u128);
 
 #[gen_stub_pymethods]
 #[pymethods]
@@ -17,31 +16,29 @@ impl PyKeypair {
     /// Generate a new Ed25519 keypair.
     #[staticmethod]
     fn generate() -> Self {
-        Self(Keypair::generate_ed25519())
+        Self(rand::random())
     }
 
     /// Construct an Ed25519 keypair from secret key bytes
     #[staticmethod]
     fn from_bytes(bytes: Bound<'_, PyBytes>) -> PyResult<Self> {
-        let mut bytes = Vec::from(bytes.as_bytes());
-        Ok(Self(Keypair::ed25519_from_bytes(&mut bytes).pyerr()?))
+        let bytes = Vec::from(bytes.as_bytes());
+        Ok(Self(u128::from_le_bytes(
+            bytes
+                .try_into()
+                .map_err(|_| "passed too many bytes to from_bytes")
+                .pyerr()?,
+        )))
     }
 
     /// Get the secret key bytes underlying the keypair
     fn to_bytes<'py>(&self, py: Python<'py>) -> PyResult<Bound<'py, PyBytes>> {
-        let bytes = self
-            .0
-            .clone()
-            .try_into_ed25519()
-            .pyerr()?
-            .secret()
-            .as_ref()
-            .to_vec();
+        let bytes = self.0.to_le_bytes();
         Ok(PyBytes::new(py, &bytes))
     }
 
     /// Convert the `Keypair` into the corresponding `PeerId` string, which we use as our `NodeId`.
     fn to_node_id(&self) -> String {
-        self.0.public().to_peer_id().to_base58()
+        format!("{:x}", self.0)
     }
 }

rust/exo_pyo3_bindings/src/lib.rs

@@ -5,21 +5,15 @@
 //!
 
 mod allow_threading;
-mod ident;
-mod networking;
+// mod ident;
+// mod networking;
+mod state;
 
-use crate::ident::PyKeypair;
-use crate::networking::networking_submodule;
+use crate::state::snapshot_module;
 use pyo3::prelude::PyModule;
-use pyo3::types::PyModuleMethods;
-use pyo3::{Bound, PyResult, pyclass, pymodule};
+use pyo3::{Bound, PyResult, pymodule};
 use pyo3_stub_gen::define_stub_info_gatherer;
 
-/// Namespace for all the constants used by this crate.
-pub(crate) mod r#const {
-    pub const MPSC_CHANNEL_SIZE: usize = 1024;
-}
-
 /// Namespace for crate-wide extension traits/methods
 pub(crate) mod ext {
     use crate::allow_threading::AllowThreads;
@@ -162,8 +156,9 @@ fn main_module(m: &Bound<'_, PyModule>) -> PyResult<()> {
     // TODO: for now this is all NOT a submodule, but figure out how to make the submodule system
     //       work with maturin, where the types generate correctly, in the right folder, without
     //       too many importing issues...
-    m.add_class::<PyKeypair>()?;
-    networking_submodule(m)?;
+    // m.add_class::<PyKeypair>()?;
+    // networking_submodule(m)?;
+    snapshot_module(m)?;
 
     // top-level constructs
     // TODO: ...

rust/exo_pyo3_bindings/src/networking.rs

@@ -5,12 +5,8 @@ use crate::r#const::MPSC_CHANNEL_SIZE;
 use crate::ext::{ByteArrayExt as _, FutureExt, PyErrExt as _};
 use crate::ext::{ResultExt as _, TokioMpscSenderExt as _};
 use crate::ident::PyKeypair;
-use crate::networking::exception::{
-    PyAllQueuesFullError, PyMessageTooLargeError, PyNoPeersSubscribedToTopicError,
-};
 use crate::pyclass;
 use futures_lite::{Stream, StreamExt as _};
-use libp2p::gossipsub::PublishError;
 use networking::swarm::{FromSwarm, ToSwarm, create_swarm};
 use pyo3::exceptions::PyRuntimeError;
 use pyo3::prelude::{PyModule, PyModuleMethods as _};
@@ -21,114 +17,6 @@ use pyo3_stub_gen::derive::{
 };
 use tokio::sync::{Mutex, mpsc, oneshot};
 
-mod exception {
-    use pyo3::types::PyTuple;
-    use pyo3::{exceptions::PyException, prelude::*};
-    use pyo3_stub_gen::derive::*;
-
-    #[gen_stub_pyclass]
-    #[pyclass(frozen, extends=PyException, name="NoPeersSubscribedToTopicError")]
-    pub struct PyNoPeersSubscribedToTopicError {}
-
-    impl PyNoPeersSubscribedToTopicError {
-        const MSG: &'static str = "\
-        No peers are currently subscribed to receive messages on this topic. \
-        Wait for peers to subscribe or check your network connectivity.";
-
-        ///   Creates a new  [ `PyErr` ]  of this type.
-        ///
-        ///   [`PyErr`] :  https://docs.rs/pyo3/latest/pyo3/struct.PyErr.html   "PyErr in pyo3"
-        pub(crate) fn new_err() -> PyErr {
-            PyErr::new::<Self, _>(()) // TODO: check if this needs to be replaced???
-        }
-    }
-
-    #[gen_stub_pymethods]
-    #[pymethods]
-    impl PyNoPeersSubscribedToTopicError {
-        #[new]
-        #[pyo3(signature = (*args))]
-        #[allow(unused_variables)]
-        pub(crate) fn new(args: &Bound<'_, PyTuple>) -> Self {
-            Self {}
-        }
-
-        fn __repr__(&self) -> String {
-            format!("PeerId(\"{}\")", Self::MSG)
-        }
-
-        fn __str__(&self) -> String {
-            Self::MSG.to_string()
-        }
-    }
-
-    #[gen_stub_pyclass]
-    #[pyclass(frozen, extends=PyException, name="AllQueuesFullError")]
-    pub struct PyAllQueuesFullError {}
-
-    impl PyAllQueuesFullError {
-        const MSG: &'static str =
-            "All libp2p peers are unresponsive, resend the message or reconnect.";
-
-        ///   Creates a new  [ `PyErr` ]  of this type.
-        ///
-        ///   [`PyErr`] :  https://docs.rs/pyo3/latest/pyo3/struct.PyErr.html   "PyErr in pyo3"
-        pub(crate) fn new_err() -> PyErr {
-            PyErr::new::<Self, _>(()) // TODO: check if this needs to be replaced???
-        }
-    }
-
-    #[gen_stub_pymethods]
-    #[pymethods]
-    impl PyAllQueuesFullError {
-        #[new]
-        #[pyo3(signature = (*args))]
-        #[allow(unused_variables)]
-        pub(crate) fn new(args: &Bound<'_, PyTuple>) -> Self {
-            Self {}
-        }
-
-        fn __repr__(&self) -> String {
-            format!("PeerId(\"{}\")", Self::MSG)
-        }
-
-        fn __str__(&self) -> String {
-            Self::MSG.to_string()
-        }
-    }
-
-    #[gen_stub_pyclass]
-    #[pyclass(frozen, extends=PyException, name="MessageTooLargeError")]
-    pub struct PyMessageTooLargeError {}
-
-    impl PyMessageTooLargeError {
-        const MSG: &'static str = "Gossipsub message exceeds max_transmit_size. Reduce prompt length or increase the limit.";
-
-        pub(crate) fn new_err() -> PyErr {
-            PyErr::new::<Self, _>(())
-        }
-    }
-
-    #[gen_stub_pymethods]
-    #[pymethods]
-    impl PyMessageTooLargeError {
-        #[new]
-        #[pyo3(signature = (*args))]
-        #[allow(unused_variables)]
-        pub(crate) fn new(args: &Bound<'_, PyTuple>) -> Self {
-            Self {}
-        }
-
-        fn __repr__(&self) -> String {
-            format!("MessageTooLargeError(\"{}\")", Self::MSG)
-        }
-
-        fn __str__(&self) -> String {
-            Self::MSG.to_string()
-        }
-    }
-}
-
 #[gen_stub_pyclass]
 #[pyclass(name = "NetworkingHandle")]
 struct PyNetworkingHandle {
@@ -140,29 +28,15 @@ struct PyNetworkingHandle {
 #[gen_stub_pyclass_complex_enum]
 #[pyclass]
 enum PyFromSwarm {
-    Connection {
-        peer_id: String,
-        connected: bool,
-    },
-    Message {
-        origin: String,
-        topic: String,
-        data: Py<PyBytes>,
-    },
+    Connection { connected: bool },
+    Message { topic: String, data: Py<PyBytes> },
 }
 impl From<FromSwarm> for PyFromSwarm {
     fn from(value: FromSwarm) -> Self {
         match value {
-            FromSwarm::Discovered { peer_id } => Self::Connection {
-                peer_id: peer_id.to_base58(),
-                connected: true,
-            },
-            FromSwarm::Expired { peer_id } => Self::Connection {
-                peer_id: peer_id.to_base58(),
-                connected: false,
-            },
-            FromSwarm::Message { from, topic, data } => Self::Message {
-                origin: from.to_base58(),
+            FromSwarm::Discovered {} => Self::Connection { connected: true },
+            FromSwarm::Expired {} => Self::Connection { connected: false },
+            FromSwarm::Message { topic, data } => Self::Message {
                 topic: topic,
                 data: data.pybytes(),
             },
@@ -195,8 +69,8 @@ impl PyNetworkingHandle {
         // create networking swarm (within tokio context!! or it crashes)
         let _guard = pyo3_async_runtimes::tokio::get_runtime().enter();
         let swarm = create_swarm(identity, from_client, bootstrap_peers, listen_port)
-            .pyerr()?
-            .into_stream();
+            .map(|it| it.into_stream())
+            .pyerr()?;
 
         Ok(Self {
             swarm: Arc::new(Mutex::new(swarm)),
@@ -285,14 +159,7 @@ impl PyNetworkingHandle {
             .allow_threads_py() // allow-threads-aware async call
             .await
             .map_err(|_| PyErr::receiver_channel_closed())?
-            .map_err(|e| match e {
-                PublishError::AllQueuesFull(_) => PyAllQueuesFullError::new_err(),
-                PublishError::MessageTooLarge => PyMessageTooLargeError::new_err(),
-                PublishError::NoPeersSubscribedToTopic => {
-                    PyNoPeersSubscribedToTopicError::new_err()
-                }
-                e => PyRuntimeError::new_err(e.to_string()),
-            })?;
+            .map_err(|e| PyRuntimeError::new_err(e.to_string()))?;
         Ok(())
     }
 }
@@ -307,10 +174,6 @@ pyo3_stub_gen::inventory::submit! {
 }
 
 pub fn networking_submodule(m: &Bound<'_, PyModule>) -> PyResult<()> {
-    m.add_class::<exception::PyNoPeersSubscribedToTopicError>()?;
-    m.add_class::<exception::PyAllQueuesFullError>()?;
-    m.add_class::<exception::PyMessageTooLargeError>()?;
-
     m.add_class::<PyNetworkingHandle>()?;
     m.add_class::<PyFromSwarm>()?;
 

rust/exo_pyo3_bindings/src/state.rs

@@ -0,0 +1,110 @@
+use networking::Session;
+use pyo3::{
+    exceptions::{PyRuntimeError, PyValueError},
+    prelude::*,
+};
+use pyo3_stub_gen::derive::{gen_methods_from_python, gen_stub_pyclass, gen_stub_pymethods};
+use serde_json::{Map, Value};
+use zenoh::{Result, Session as ZSession, query::QueryTarget, sample::SampleFields};
+
+pyo3_stub_gen::inventory::submit! {
+    gen_methods_from_python! {
+        r#"
+            class StateProxy:
+                @staticmethod
+                async def init() -> StateProxy: ...
+                async def snapshot(self) -> str: ...
+        "#
+    }
+}
+
+pub fn snapshot_module(m: &Bound<'_, PyModule>) -> PyResult<()> {
+    m.add_class::<StateProxy>()?;
+
+    Ok(())
+}
+
+#[gen_stub_pyclass]
+#[pyclass]
+pub struct StateProxy {
+    session: Session,
+}
+#[gen_stub_pymethods]
+#[pymethods]
+impl StateProxy {
+    #[staticmethod]
+    #[gen_stub(skip)]
+    pub fn init<'py>(py: Python<'py>) -> PyResult<Bound<'py, PyAny>> {
+        pyo3_async_runtimes::tokio::future_into_py(py, async move {
+            Ok(Self {
+                session: networking::open(
+                    networking::cfg(rand::random(), 0).expect("default cfg is valid"),
+                )
+                .await
+                .map_err(|e| PyRuntimeError::new_err(e.to_string()))?,
+            })
+        })
+    }
+
+    #[gen_stub(skip)]
+    pub fn snapshot<'py>(&self, py: Python<'py>) -> PyResult<Bound<'py, PyAny>> {
+        pyo3_async_runtimes::tokio::future_into_py(py, {
+            let session = self.session.clone();
+            async move {
+                Self::_snapshot(session)
+                    .await
+                    .map_err(|e| PyValueError::new_err(e.to_string()))
+                    .map(|v| v.to_string())
+            }
+        })
+    }
+}
+
+impl StateProxy {
+    async fn _snapshot(session: ZSession) -> Result<Value> {
+        let q = session.get("storage/mem1/**").await?;
+
+        let mut v = Value::Object(Map::default());
+
+        while let Ok(sample) = q.recv_async().await {
+            let mut cur_v = &mut v;
+            let Ok(sample) = sample.into_result() else {
+                continue;
+            };
+            // skip storage/mem1
+            let SampleFields {
+                payload, key_expr, ..
+            } = sample.into();
+            let mut iter = key_expr.split('/').skip(2).peekable();
+            loop {
+                let Some(p) = iter.next() else {
+                    break;
+                };
+                if iter.peek().is_none() {
+                    // terminal; write value into json
+                    let existing = cur_v
+                        .as_object_mut()
+                        .expect("path terminated unexpectedly - value stored at some/path and some/path/two")
+                        .insert(p.to_owned(), Value::String(payload.try_to_string()?.to_string()));
+
+                    if let Some(value) = existing {
+                        assert!(value.is_string())
+                        // could log, but string overwrites are fine
+                    }
+                } else {
+                    // non-terminal; ensure key exists in v, then replace cur with that object
+                    cur_v = cur_v
+                        .as_object_mut()
+                        .expect("path terminated unexpectedly - value stored at some/path and some/path/two")
+                        .entry(p)
+                        .or_insert(Value::Object(Map::default()));
+                    assert!(
+                        cur_v.is_object(),
+                        "path terminated unexpectedly - value stored at some/path and some/path/two"
+                    )
+                }
+            }
+        }
+        Ok(v)
+    }
+}

rust/exo_pyo3_bindings/tests/dummy.rs

@@ -1,54 +0,0 @@
-#[cfg(test)]
-mod tests {
-    use core::mem::drop;
-    use core::option::Option::Some;
-    use core::time::Duration;
-    use tokio;
-    use tokio::sync::mpsc;
-
-    #[tokio::test]
-    async fn test_drop_channel() {
-        struct Ping;
-
-        let (tx, mut rx) = mpsc::channel::<Ping>(10);
-
-        let _ = tokio::spawn(async move {
-            println!("TASK: entered");
-
-            loop {
-                tokio::select! {
-                    result = rx.recv() => {
-                        match result {
-                            Some(_) => {
-                                println!("TASK: pinged");
-                            }
-                            None => {
-                                println!("TASK: closing channel");
-                                break;
-                            }
-                        }
-                    }
-                    _ = tokio::time::sleep(Duration::from_secs_f32(0.1)) => {
-                        println!("TASK: heartbeat");
-                    }
-                }
-            }
-
-            println!("TASK: exited");
-        });
-
-        let tx2 = tx.clone();
-
-        tokio::time::sleep(Duration::from_secs_f32(0.11)).await;
-
-        tx.send(Ping).await.expect("Should not fail");
-        drop(tx);
-
-        tokio::time::sleep(Duration::from_secs_f32(0.11)).await;
-
-        tx2.send(Ping).await.expect("Should not fail");
-        drop(tx2);
-
-        tokio::time::sleep(Duration::from_secs_f32(0.11)).await;
-    }
-}

rust/exo_pyo3_bindings/tests/test_python.py

@@ -4,7 +4,6 @@ import pytest
 from exo_pyo3_bindings import (
     Keypair,
     NetworkingHandle,
-    NoPeersSubscribedToTopicError,
     PyFromSwarm,
 )
 
@@ -13,17 +12,15 @@ from exo_pyo3_bindings import (
 async def test_sleep_on_multiple_items() -> None:
     print("PYTHON: starting handle")
     h = NetworkingHandle(Keypair.generate(), [], 0)
+    print("PYTHON: handle started")
 
     rt = asyncio.create_task(_await_recv(h))
 
     # sleep for 4 ticks
-    for i in range(4):
+    for i in range(10):
         await asyncio.sleep(1)
 
-        try:
-            await h.gossipsub_publish("topic", b"somehting or other")
-        except NoPeersSubscribedToTopicError as e:
-            print("caught it", e)
+        await h.gossipsub_publish("topic", b"somehting or other")
 
 
 async def _await_recv(h: NetworkingHandle):
@@ -34,3 +31,6 @@ async def _await_recv(h: NetworkingHandle):
                 print(f"PYTHON: connection update: {c}")
             case PyFromSwarm.Message() as m:
                 print(f"PYTHON: message: {m}")
+
+if __name__ == "__main__":
+    asyncio.run(test_sleep_on_multiple_items())

rust/networking/Cargo.toml

@@ -1,42 +1,22 @@
 [package]
 name = "networking"
-version = { workspace = true }
-edition = { workspace = true }
-publish = false
+version.workspace = true
+edition.workspace = true
 
-[lib]
-doctest = false
-name = "networking"
-path = "src/lib.rs"
+[dependencies]
+async-stream = "0.3.6"
+futures-lite.workspace = true
+netwatcher = { version = "0.6.0", features = ["tokio"] }
+parking_lot = "0.12.5"
+tokio = { workspace = true, features = ["full"] }
+zenoh = { version = "=1.9.0", features = ["internal", "plugins", "unstable"] }
+zenoh-plugin-storage-manager = { version = "=1.9.0", default-features = false }
+zenoh-plugin-trait = "=1.9.0"
+zerompk = { version = "0.4.2", features = ["derive"] }
+rand = "0.10.1"
+tracing = "0.1.44"
+log.workspace = true
 
 [lints]
 workspace = true
 
-[dependencies]
-# datastructures
-either = { workspace = true }
-
-# macro dependencies
-extend = { workspace = true }
-delegate = { workspace = true }
-
-# async
-async-stream = { workspace = true }
-futures-lite = { workspace = true }
-futures-timer = { workspace = true }
-tokio = { workspace = true, features = ["full"] }
-
-# utility dependencies
-util = { workspace = true }
-tracing-subscriber = { version = "0.3.19", features = [
-  "default",
-  "env-filter",
-] }
-keccak-const = { workspace = true }
-
-# tracing/logging
-log = { workspace = true }
-
-# networking
-libp2p = { workspace = true, features = ["full"] }
-pin-project = "1.1.10"

rust/networking/examples/chatroom.rs

@@ -1,86 +0,0 @@
-use futures_lite::StreamExt;
-use libp2p::identity;
-use networking::swarm;
-use networking::swarm::{FromSwarm, ToSwarm};
-use tokio::sync::{mpsc, oneshot};
-use tokio::{io, io::AsyncBufReadExt as _};
-use tracing_subscriber::EnvFilter;
-use tracing_subscriber::filter::LevelFilter;
-
-#[tokio::main]
-async fn main() {
-    let _ = tracing_subscriber::fmt()
-        .with_env_filter(EnvFilter::from_default_env().add_directive(LevelFilter::INFO.into()))
-        .try_init();
-
-    let (to_swarm, from_client) = mpsc::channel(20);
-
-    // Configure swarm
-    let mut swarm = swarm::create_swarm(
-        identity::Keypair::generate_ed25519(),
-        from_client,
-        vec![],
-        0,
-    )
-    .expect("Swarm creation failed")
-    .into_stream();
-
-    // Create a Gossipsub topic & subscribe
-    let (tx, rx) = oneshot::channel();
-    _ = to_swarm
-        .send(ToSwarm::Subscribe {
-            topic: "test-net".to_string(),
-            result_sender: tx,
-        })
-        .await
-        .expect("should send");
-
-    // Read full lines from stdin
-    let mut stdin = io::BufReader::new(io::stdin()).lines();
-    println!("Enter messages via STDIN and they will be sent to connected peers using Gossipsub");
-
-    tokio::task::spawn(async move {
-        rx.await
-            .expect("tx not dropped")
-            .expect("subscribe shouldn't fail");
-        loop {
-            if let Ok(Some(line)) = stdin.next_line().await {
-                let (tx, rx) = oneshot::channel();
-                if let Err(e) = to_swarm
-                    .send(swarm::ToSwarm::Publish {
-                        topic: "test-net".to_string(),
-                        data: line.as_bytes().to_vec(),
-                        result_sender: tx,
-                    })
-                    .await
-                {
-                    println!("Send error: {e:?}");
-                    return;
-                };
-                match rx.await {
-                    Ok(Err(e)) => println!("Publish error: {e:?}"),
-                    Err(e) => println!("Publish error: {e:?}"),
-                    Ok(_) => {}
-                }
-            }
-        }
-    });
-
-    // Kick it off
-    loop {
-        // on gossipsub outgoing
-        match swarm.next().await {
-            // on gossipsub incoming
-            Some(FromSwarm::Discovered { peer_id }) => {
-                println!("\n\nconnected to {peer_id}\n\n")
-            }
-            Some(FromSwarm::Expired { peer_id }) => {
-                println!("\n\ndisconnected from {peer_id}\n\n")
-            }
-            Some(FromSwarm::Message { from, topic, data }) => {
-                println!("{topic}/{from}:\n{}", String::from_utf8_lossy(&data))
-            }
-            None => {}
-        }
-    }
-}

rust/networking/examples/put_string.rs

@@ -0,0 +1,22 @@
+use networking;
+use tracing::info;
+use zenoh::Result;
+
+#[tokio::main]
+async fn main() -> Result<()> {
+    zenoh::init_log_from_env_or("info");
+    info!("Opening session...");
+    let cfg = networking::cfg(rand::random(), 0)?;
+    let session = networking::open(cfg).await?;
+    let _tok = session
+        .liveliness()
+        .declare_token(format!("nodes/{}/live", session.zid()))
+        .await?;
+    let key_expr = "storage/mem1/name";
+    let payload = "me";
+
+    info!("Putting Data ('{key_expr}': '{payload}')...");
+    session.put(key_expr, payload).await?;
+    tokio::signal::ctrl_c().await?;
+    Ok(())
+}

rust/networking/examples/serve_storage.rs

@@ -0,0 +1,23 @@
+use networking;
+use tracing::info;
+use zenoh::Result;
+
+#[tokio::main]
+async fn main() -> Result<()> {
+    zenoh::init_log_from_env_or("info");
+    info!("Opening session...");
+    let cfg = networking::cfg(rand::random(), 0)?;
+    let session = networking::open(cfg).await?;
+    let _tok = session
+        .liveliness()
+        .declare_token(format!("nodes/{}/live", session.zid()))
+        .await?;
+    let _sub = session
+        .liveliness()
+        .declare_subscriber("nodes/*/live")
+        .history(true)
+        .callback(|tok| println!("{tok:?}"))
+        .await?;
+    tokio::signal::ctrl_c().await?;
+    Ok(())
+}

rust/networking/src/RESEARCH_NOTES.txt

@@ -1,44 +0,0 @@
-https://github.com/ml-explore/mlx/commit/3fe98bacc7640d857acf3539f1d21b47a32e5609
-^raw sockets distributed -> `<net/ndrv.h>` -> https://newosxbook.com/code/xnu-3247.1.106/bsd/net/ndrv.h.auto.html
---> header file for a networking component found in the macOS kernel (XNU) that defines structures for network device driver registration, specifically the ndrv_demux_desc and ndrv_protocol_desc structures used for demultiplexing protocol data at the network interface level. It specifies how to describe protocol data, such as an Ethernet type or a SNAP header, and how to associate these descriptions with a specific protocol family to receive matching packets.
---> Used to bind an NDRV socket so that packets that match given protocol demux descriptions can be received.
---> An NDRV socket is a special kind of socket in the Darwin/macOS operating system's XNU kernel, used for low-level network packet manipulation and binding to specific protocols for packet processing. It allows user-space applications or drivers to directly write Layer 2 (L2) network packets or interact with the network stack at a lower level, often by binding to protocol descriptors like the ndrv_protocol_desc. This type of socket is used for functions such as capturing and injecting packets, especially in network infrastructure software like routers or for kernel-level network monitoring and security tools.
---> also called PF_NDRV sockets --> https://newosxbook.com/bonus/vol1ch16.html
-----> they are conceptually similar to https://scapy.disruptivelabs.in/networking/socket-interface PF_RAW or PF_PACKET
-
-https://stackoverflow.com/questions/17169298/af-packet-on-osx
-^AF_PACKET duplicates the packets as soon as it receives them from the physical layer (for incoming packets) or just before sending them out to the physical layer (for outgoing packets). -> this is on Linux only
-^it doesn't exist on OS X so you can use /dev/bpfX (Berkeley Packet Filter) for sniffing
-
-https://www.unix.com/man_page/mojave/4/ip/
-^OS X manpages for IP
-
-https://developer.apple.com/documentation/kernel/implementing_drivers_system_extensions_and_kexts
-^driver kit, system extensions & kexts for macOS
-
-----
-
-To set up a Linux system to use a Thunderbolt connection as a network device, connect the two computers with a Thunderbolt cable, load the thunderbolt-net kernel module (usually automatic but modprobe is an option for manual loading), and then the operating system will create virtual Ethernet interfaces (e.g., thunderbolt0) for networking. You can then use standard tools like ifconfig or your desktop environment's network manager to configure these new interfaces for a link-local network.
---> https://gist.github.com/geosp/80fbd39e617b7d1d9421683df4ea224a
-----> here is a guide on how to set up thunderbolt-ethernet on linux
-----> I may be able to steal the thunderbolt-net code ideas to implement a kernel module for MacOS
-
-https://chatgpt.com/s/t_68af8e41a8548191993281a014f846a7
-^GPT discussion about making socket interface
-
-https://chatgpt.com/s/t_68afb798a85c8191973c02a0fa7a48a3 --> link-local address,,??
-https://chatgpt.com/s/t_68afb02987e08191b2b0044d3667ece2
-^GPT discussion about accessing TB on MacOS low level interactions
-
---------------------------------
-
-https://www.intel.com/content/www/us/en/support/articles/000098893/software.html
-^Thunderbolt Share & Thunderbolt Networking Mode => intel's equivalent of thunderbolt bridge
-
-
----------------------------------
-
-https://www.zerotier.com/blog/how-zerotier-eliminated-kernel-extensions-on-macos/
--->fake ethernet devices on MacOS -> omg??? we can detect thunderbolt bridge, then bind to it, then re-expose it as fake ethernet??
--->ps: https://chatgpt.com/s/t_68afb2b25fb881919526763fb5d7359c, AF/PF_NDRV are one and the same!!!
--->https://github.com/zerotier/ZeroTierOne/blob/dev/osdep/MacEthernetTapAgent.c

rust/networking/src/discovery.rs

@@ -1,390 +0,0 @@
-use crate::ext::MultiaddrExt;
-use delegate::delegate;
-use either::Either;
-use futures_lite::FutureExt;
-use futures_timer::Delay;
-use libp2p::core::transport::PortUse;
-use libp2p::core::{ConnectedPoint, Endpoint};
-use libp2p::swarm::behaviour::ConnectionEstablished;
-use libp2p::swarm::dial_opts::DialOpts;
-use libp2p::swarm::{
-    CloseConnection, ConnectionClosed, ConnectionDenied, ConnectionHandler,
-    ConnectionHandlerSelect, ConnectionId, FromSwarm, NetworkBehaviour, THandler, THandlerInEvent,
-    THandlerOutEvent, ToSwarm, dummy,
-};
-use libp2p::{Multiaddr, PeerId, identity, mdns};
-use std::collections::{BTreeSet, HashMap};
-use std::convert::Infallible;
-use std::io;
-use std::net::IpAddr;
-use std::task::{Context, Poll};
-use std::time::Duration;
-use util::wakerdeque::WakerDeque;
-
-const RETRY_CONNECT_INTERVAL: Duration = Duration::from_secs(5);
-
-mod managed {
-    use libp2p::swarm::NetworkBehaviour;
-    use libp2p::{identity, mdns, ping};
-    use std::io;
-    use std::time::Duration;
-
-    const MDNS_RECORD_TTL: Duration = Duration::from_secs(2_500);
-    const MDNS_QUERY_INTERVAL: Duration = Duration::from_secs(1_500);
-    const PING_TIMEOUT: Duration = Duration::from_millis(2_500);
-    const PING_INTERVAL: Duration = Duration::from_millis(2_500);
-
-    #[derive(NetworkBehaviour)]
-    pub struct Behaviour {
-        mdns: mdns::tokio::Behaviour,
-        ping: ping::Behaviour,
-    }
-
-    impl Behaviour {
-        pub fn new(keypair: &identity::Keypair) -> io::Result<Self> {
-            Ok(Self {
-                mdns: mdns_behaviour(keypair)?,
-                ping: ping_behaviour(),
-            })
-        }
-    }
-
-    fn mdns_behaviour(keypair: &identity::Keypair) -> io::Result<mdns::tokio::Behaviour> {
-        use mdns::{Config, tokio};
-
-        // mDNS config => enable IPv6
-        let mdns_config = Config {
-            ttl: MDNS_RECORD_TTL,
-            query_interval: MDNS_QUERY_INTERVAL,
-
-            // enable_ipv6: true, // TODO: for some reason, TCP+mDNS don't work well with ipv6?? figure out how to make work
-            ..Default::default()
-        };
-
-        let mdns_behaviour = tokio::Behaviour::new(mdns_config, keypair.public().to_peer_id());
-        Ok(mdns_behaviour?)
-    }
-
-    fn ping_behaviour() -> ping::Behaviour {
-        ping::Behaviour::new(
-            ping::Config::new()
-                .with_timeout(PING_TIMEOUT)
-                .with_interval(PING_INTERVAL),
-        )
-    }
-}
-
-/// Events for when a listening connection is truly established and truly closed.
-#[derive(Debug, Clone)]
-pub enum Event {
-    ConnectionEstablished {
-        peer_id: PeerId,
-        connection_id: ConnectionId,
-        remote_ip: IpAddr,
-        remote_tcp_port: u16,
-    },
-    ConnectionClosed {
-        peer_id: PeerId,
-        connection_id: ConnectionId,
-        remote_ip: IpAddr,
-        remote_tcp_port: u16,
-    },
-}
-
-/// Discovery behavior that wraps mDNS to produce truly discovered durable peer-connections.
-///
-/// The behaviour operates as such:
-///  1) All true (listening) connections/disconnections are tracked, emitting corresponding events
-///     to the swarm.
-///  1) mDNS discovered/expired peers are tracked; discovered but not connected peers are dialed
-///     immediately, and expired but connected peers are disconnected from immediately.
-///  2) Every fixed interval: discovered but not connected peers are dialed, and expired but
-///     connected peers are disconnected from.
-pub struct Behaviour {
-    // state-tracking for managed behaviors & mDNS-discovered peers
-    managed: managed::Behaviour,
-    mdns_discovered: HashMap<PeerId, BTreeSet<Multiaddr>>,
-    bootstrap_peers: Vec<Multiaddr>,
-
-    retry_delay: Delay, // retry interval
-
-    // pending events to emmit => waker-backed Deque to control polling
-    pending_events: WakerDeque<ToSwarm<Event, Infallible>>,
-}
-
-impl Behaviour {
-    pub fn new(keypair: &identity::Keypair, bootstrap_peers: Vec<Multiaddr>) -> io::Result<Self> {
-        Ok(Self {
-            managed: managed::Behaviour::new(keypair)?,
-            mdns_discovered: HashMap::new(),
-            bootstrap_peers,
-            retry_delay: Delay::new(RETRY_CONNECT_INTERVAL),
-            pending_events: WakerDeque::new(),
-        })
-    }
-
-    fn dial(&mut self, peer_id: PeerId, addr: Multiaddr) {
-        self.pending_events.push_back(ToSwarm::Dial {
-            opts: DialOpts::peer_id(peer_id).addresses(vec![addr]).build(),
-        })
-    }
-
-    fn close_connection(&mut self, peer_id: PeerId, connection: ConnectionId) {
-        // push front to make this IMMEDIATE
-        self.pending_events.push_front(ToSwarm::CloseConnection {
-            peer_id,
-            connection: CloseConnection::One(connection),
-        })
-    }
-
-    fn handle_mdns_discovered(&mut self, peers: Vec<(PeerId, Multiaddr)>) {
-        for (p, ma) in peers {
-            self.dial(p, ma.clone()); // always connect
-
-            // get peer's multi-addresses or insert if missing
-            let Some(mas) = self.mdns_discovered.get_mut(&p) else {
-                self.mdns_discovered.insert(p, BTreeSet::from([ma]));
-                continue;
-            };
-
-            // multiaddress should never already be present - else something has gone wrong
-            let is_new_addr = mas.insert(ma);
-            assert!(is_new_addr, "cannot discover a discovered peer");
-        }
-    }
-
-    fn handle_mdns_expired(&mut self, peers: Vec<(PeerId, Multiaddr)>) {
-        for (p, ma) in peers {
-            // at this point, we *must* have the peer
-            let mas = self
-                .mdns_discovered
-                .get_mut(&p)
-                .expect("nonexistent peer cannot expire");
-
-            // at this point, we *must* have the multiaddress
-            let was_present = mas.remove(&ma);
-            assert!(was_present, "nonexistent multiaddress cannot expire");
-
-            // if empty, remove the peer-id entirely
-            if mas.is_empty() {
-                self.mdns_discovered.remove(&p);
-            }
-        }
-    }
-
-    fn on_connection_established(
-        &mut self,
-        peer_id: PeerId,
-        connection_id: ConnectionId,
-        remote_ip: IpAddr,
-        remote_tcp_port: u16,
-    ) {
-        // send out connected event
-        self.pending_events
-            .push_back(ToSwarm::GenerateEvent(Event::ConnectionEstablished {
-                peer_id,
-                connection_id,
-                remote_ip,
-                remote_tcp_port,
-            }));
-    }
-
-    fn on_connection_closed(
-        &mut self,
-        peer_id: PeerId,
-        connection_id: ConnectionId,
-        remote_ip: IpAddr,
-        remote_tcp_port: u16,
-    ) {
-        // send out disconnected event
-        self.pending_events
-            .push_back(ToSwarm::GenerateEvent(Event::ConnectionClosed {
-                peer_id,
-                connection_id,
-                remote_ip,
-                remote_tcp_port,
-            }));
-    }
-}
-
-impl NetworkBehaviour for Behaviour {
-    type ConnectionHandler =
-        ConnectionHandlerSelect<dummy::ConnectionHandler, THandler<managed::Behaviour>>;
-    type ToSwarm = Event;
-
-    // simply delegate to underlying mDNS behaviour
-
-    delegate! {
-        to self.managed {
-            fn handle_pending_inbound_connection(&mut self, connection_id: ConnectionId, local_addr: &Multiaddr, remote_addr: &Multiaddr) -> Result<(), ConnectionDenied>;
-            fn handle_pending_outbound_connection(&mut self, connection_id: ConnectionId, maybe_peer: Option<PeerId>, addresses: &[Multiaddr], effective_role: Endpoint) -> Result<Vec<Multiaddr>, ConnectionDenied>;
-        }
-    }
-
-    fn handle_established_inbound_connection(
-        &mut self,
-        connection_id: ConnectionId,
-        peer: PeerId,
-        local_addr: &Multiaddr,
-        remote_addr: &Multiaddr,
-    ) -> Result<THandler<Self>, ConnectionDenied> {
-        Ok(ConnectionHandler::select(
-            dummy::ConnectionHandler,
-            self.managed.handle_established_inbound_connection(
-                connection_id,
-                peer,
-                local_addr,
-                remote_addr,
-            )?,
-        ))
-    }
-
-    #[allow(clippy::needless_question_mark)]
-    fn handle_established_outbound_connection(
-        &mut self,
-        connection_id: ConnectionId,
-        peer: PeerId,
-        addr: &Multiaddr,
-        role_override: Endpoint,
-        port_use: PortUse,
-    ) -> Result<THandler<Self>, ConnectionDenied> {
-        Ok(ConnectionHandler::select(
-            dummy::ConnectionHandler,
-            self.managed.handle_established_outbound_connection(
-                connection_id,
-                peer,
-                addr,
-                role_override,
-                port_use,
-            )?,
-        ))
-    }
-
-    fn on_connection_handler_event(
-        &mut self,
-        peer_id: PeerId,
-        connection_id: ConnectionId,
-        event: THandlerOutEvent<Self>,
-    ) {
-        match event {
-            Either::Left(ev) => libp2p::core::util::unreachable(ev),
-            Either::Right(ev) => {
-                self.managed
-                    .on_connection_handler_event(peer_id, connection_id, ev)
-            }
-        }
-    }
-
-    // hook into these methods to drive behavior
-
-    fn on_swarm_event(&mut self, event: FromSwarm) {
-        self.managed.on_swarm_event(event); // let mDNS handle swarm events
-
-        // handle swarm events to update internal state:
-        match event {
-            FromSwarm::ConnectionEstablished(ConnectionEstablished {
-                peer_id,
-                connection_id,
-                endpoint,
-                ..
-            }) => {
-                let remote_address = match endpoint {
-                    ConnectedPoint::Dialer { address, .. } => address,
-                    ConnectedPoint::Listener { send_back_addr, .. } => send_back_addr,
-                };
-
-                if let Some((ip, port)) = remote_address.try_to_tcp_addr() {
-                    // handle connection established event which is filtered correctly
-                    self.on_connection_established(peer_id, connection_id, ip, port)
-                }
-            }
-            FromSwarm::ConnectionClosed(ConnectionClosed {
-                peer_id,
-                connection_id,
-                endpoint,
-                ..
-            }) => {
-                let remote_address = match endpoint {
-                    ConnectedPoint::Dialer { address, .. } => address,
-                    ConnectedPoint::Listener { send_back_addr, .. } => send_back_addr,
-                };
-
-                if let Some((ip, port)) = remote_address.try_to_tcp_addr() {
-                    // handle connection closed event which is filtered correctly
-                    self.on_connection_closed(peer_id, connection_id, ip, port)
-                }
-            }
-
-            // since we are running TCP/IP transport layer, we are assuming that
-            // no address changes can occur, hence encountering one is a fatal error
-            FromSwarm::AddressChange(a) => {
-                unreachable!("unhandlable: address change encountered: {:?}", a)
-            }
-            _ => {}
-        }
-    }
-
-    fn poll(&mut self, cx: &mut Context) -> Poll<ToSwarm<Self::ToSwarm, THandlerInEvent<Self>>> {
-        // delegate to managed behaviors for any behaviors they need to perform
-        match self.managed.poll(cx) {
-            Poll::Ready(ToSwarm::GenerateEvent(e)) => {
-                match e {
-                    // handle discovered and expired events from mDNS
-                    managed::BehaviourEvent::Mdns(e) => match e.clone() {
-                        mdns::Event::Discovered(peers) => {
-                            self.handle_mdns_discovered(peers);
-                        }
-                        mdns::Event::Expired(peers) => {
-                            self.handle_mdns_expired(peers);
-                        }
-                    },
-
-                    // handle ping events => if error then disconnect
-                    managed::BehaviourEvent::Ping(e) => {
-                        if let Err(_) = e.result {
-                            self.close_connection(e.peer, e.connection.clone())
-                        }
-                    }
-                }
-
-                // since we just consumed an event, we should immediately wake just in case
-                // there are more events to come where that came from
-                cx.waker().wake_by_ref();
-            }
-
-            // forward any other mDNS event to the swarm or its connection handler(s)
-            Poll::Ready(e) => {
-                return Poll::Ready(
-                    e.map_out(|_| unreachable!("events returning to swarm already handled"))
-                        .map_in(Either::Right),
-                );
-            }
-
-            Poll::Pending => {}
-        }
-
-        // retry connecting to all mDNS peers periodically (fails safely if already connected)
-        if self.retry_delay.poll(cx).is_ready() {
-            for (p, mas) in self.mdns_discovered.clone() {
-                for ma in mas {
-                    self.dial(p, ma)
-                }
-            }
-            // dial bootstrap peers (for environments where mDNS is unavailable)
-            for addr in &self.bootstrap_peers {
-                self.pending_events.push_back(ToSwarm::Dial {
-                    opts: DialOpts::unknown_peer_id().address(addr.clone()).build(),
-                })
-            }
-            self.retry_delay.reset(RETRY_CONNECT_INTERVAL) // reset timeout
-        }
-
-        // send out any pending events from our own service
-        if let Some(e) = self.pending_events.pop_front(cx) {
-            return Poll::Ready(e.map_in(Either::Left));
-        }
-
-        // wait for pending events
-        Poll::Pending
-    }
-}

rust/networking/src/lib.rs

@@ -1,44 +1,118 @@
-//! TODO: crate documentation
-//!
-//! this is here as a placeholder documentation
-//!
-//!
-pub mod discovery;
+use std::{
+    env,
+    ops::{Deref, DerefMut},
+    panic,
+    sync::Arc,
+};
+
+use netwatcher::WatchHandle;
+use parking_lot::Mutex;
+use tokio::{sync::mpsc, task::JoinHandle};
+use zenoh::{Result, Session as ZSession, config::WhatAmI, internal::runtime::Runtime};
+use zenoh_plugin_storage_manager::StoragesPlugin;
+use zenoh_plugin_trait::PluginsManager;
+
+pub use zenoh::{Config, config::ZenohId};
+
 pub mod swarm;
 
-/// Namespace for all the type/trait aliases used by this crate.
-pub(crate) mod alias {
-    use std::error::Error;
-
-    pub type AnyError = Box<dyn Error + Send + Sync + 'static>;
-    pub type AnyResult<T> = Result<T, AnyError>;
+pub fn cfg(identity: u128, listen_port: u16) -> Result<zenoh::Config> {
+    let namespace = env::var("EXO_ZENOH_NAMESPACE").unwrap_or_else(|_| "exo".to_string());
+    let mut cfg = zenoh::Config::default();
+    // todo: cleanup
+    cfg.insert_json5("id", &format!("\"{identity:x}\""))?;
+    cfg.insert_json5("mode", "\"peer\"")?;
+    cfg.insert_json5("listen/endpoints", &format!("[\"tcp/[::]:{listen_port}\"]"))?;
+    cfg.insert_json5("scouting/multicast/enabled", "true")?;
+    cfg.insert_json5("scouting/multicast/autoconnect", "[]")?;
+    cfg.insert_json5("scouting/gossip/multihop", "true")?;
+    cfg.insert_json5("namespace", &format!("{namespace:?}"))?;
+    cfg.insert_json5("transport/link/tx/batch_size", "9216")?;
+    cfg.insert_json5("timestamping/enabled", "true")?;
+    cfg.insert_json5("plugins/storage_manager/__required__", "true")?;
+    cfg.insert_json5(
+        "plugins/storage_manager/storages/mem1",
+        r#"{
+            key_expr: "storage/mem1/**",
+            strip_prefix: "storage/mem1",
+            volume: "memory",
+            replication: {
+                interval: 2,
+            }
+        }"#,
+    )?;
+    Ok(cfg)
 }
 
-/// Namespace for crate-wide extension traits/methods
-pub(crate) mod ext {
-    use extend::ext;
-    use libp2p::Multiaddr;
-    use libp2p::multiaddr::Protocol;
-    use std::net::IpAddr;
-
-    #[ext(pub, name = MultiaddrExt)]
-    impl Multiaddr {
-        /// If the multiaddress corresponds to a TCP address, extracts it
-        fn try_to_tcp_addr(&self) -> Option<(IpAddr, u16)> {
-            let mut ps = self.into_iter();
-            let ip = if let Some(p) = ps.next() {
-                match p {
-                    Protocol::Ip4(ip) => IpAddr::V4(ip),
-                    Protocol::Ip6(ip) => IpAddr::V6(ip),
-                    _ => return None,
+pub async fn open(cfg: zenoh::Config) -> Result<Session> {
+    let mut plugins = PluginsManager::static_plugins_only();
+    plugins.declare_static_plugin::<StoragesPlugin, _>("storage_manager", true);
+    let mut runtime = zenoh::internal::runtime::RuntimeBuilder::new(cfg)
+        .plugins_manager(plugins)
+        .build()
+        .await?;
+    let session = zenoh::session::init(runtime.clone().into()).await?;
+    runtime.start().await?;
+    let _watch_all_handle = Arc::new(Mutex::new(watch_all(runtime).await?));
+    Ok(Session {
+        session,
+        _watch_all_handle,
+    })
+}
+async fn watch_all(runtime: Runtime) -> Result<WatchAllHandle> {
+    log::info!("spawning scout");
+    let mut cfg = Config::default();
+    cfg.insert_json5("scouting/multicast/ttl", "3")?;
+    cfg.insert_json5("scouting/multicast/interface", "\"auto\"")?;
+    let mut scout = zenoh::scout(WhatAmI::Peer, cfg.clone()).await?;
+    let (send, mut recv) = mpsc::unbounded_channel();
+    let _sync = netwatcher::watch_interfaces_with_callback(move |u| _ = send.send(u))?;
+    let _async = tokio::task::spawn(async move {
+        loop {
+            tokio::select! {
+                u = recv.recv() => {
+                    if u.is_none() {
+                        return Ok(());
+                    }
+                    log::info!("reloading scout");
+                    scout = zenoh::scout(WhatAmI::Peer, cfg.clone()).await?;
                 }
-            } else {
-                return None;
-            };
-            let Some(Protocol::Tcp(port)) = ps.next() else {
-                return None;
-            };
-            Some((ip, port))
+                hello = scout.recv_async() => {
+                    if let Ok(hello) = hello {
+                        // todo: auth
+                        runtime
+                            .connect_peer(&hello.zid().into(), hello.locators())
+                            .await;
+                    }
+                }
+            }
         }
+    });
+    Ok(WatchAllHandle { _sync, _async })
+}
+
+pub struct Session {
+    pub session: ZSession,
+    _watch_all_handle: Arc<Mutex<WatchAllHandle>>,
+}
+impl Deref for Session {
+    type Target = ZSession;
+    fn deref(&self) -> &Self::Target {
+        &self.session
     }
 }
+impl DerefMut for Session {
+    fn deref_mut(&mut self) -> &mut Self::Target {
+        &mut self.session
+    }
+}
+impl Drop for WatchAllHandle {
+    fn drop(&mut self) {
+        self._async.abort();
+    }
+}
+
+pub struct WatchAllHandle {
+    _sync: WatchHandle,
+    _async: JoinHandle<Result<()>>,
+}

rust/networking/src/swarm.rs

@@ -1,24 +1,22 @@
+//! Compat shim for the old libp2p code
+
+use std::collections::HashMap;
 use std::pin::Pin;
 
-use crate::swarm::transport::tcp_transport;
-use crate::{alias, discovery};
-pub use behaviour::{Behaviour, BehaviourEvent};
-use futures_lite::{Stream, StreamExt};
-use libp2p::{PeerId, SwarmBuilder, gossipsub, identity, swarm::SwarmEvent};
-use tokio::sync::{mpsc, oneshot};
+use futures_lite::Stream;
+use tokio::sync::mpsc;
+use tokio::sync::oneshot;
+use tracing::info;
+use zenoh::Result;
+use zenoh::Session;
+use zenoh::handlers::FifoChannelHandler;
+use zenoh::liveliness::LivelinessToken;
+use zenoh::pubsub::Subscriber;
+use zenoh::sample::Sample;
+use zenoh::sample::SampleKind;
+use zerompk::{FromMessagePack, ToMessagePack};
 
-/// The current version of the network: this prevents devices running different versions of the
-/// software from interacting with each other.
-///
-/// TODO: right now this is a hardcoded constant; figure out what the versioning semantics should
-///       even be, and how to inject the right version into this config/initialization. E.g. should
-///       this be passed in as a parameter? What about rapidly changing versions in debug builds?
-///       this is all VERY very hard to figure out and needs to be mulled over as a team.
-pub const NETWORK_VERSION: &[u8] = b"v0.0.1";
-pub const OVERRIDE_VERSION_ENV_VAR: &str = "EXO_LIBP2P_NAMESPACE";
-
-// Uses oneshot senders to emulate function calling apis while avoiding requiring unique ownership
-// of the Swarm.
+#[derive(Debug)]
 pub enum ToSwarm {
     Unsubscribe {
         topic: String,
@@ -26,52 +24,66 @@ pub enum ToSwarm {
     },
     Subscribe {
         topic: String,
-        result_sender: oneshot::Sender<Result<bool, gossipsub::SubscriptionError>>,
+        result_sender: oneshot::Sender<Result<bool>>,
     },
     Publish {
         topic: String,
         data: Vec<u8>,
-        result_sender: oneshot::Sender<Result<gossipsub::MessageId, gossipsub::PublishError>>,
+        result_sender: oneshot::Sender<Result<()>>,
     },
 }
+#[derive(Debug, ToMessagePack, FromMessagePack)]
 pub enum FromSwarm {
-    Message {
-        from: PeerId,
-        topic: String,
-        data: Vec<u8>,
-    },
-    Discovered {
-        peer_id: PeerId,
-    },
-    Expired {
-        peer_id: PeerId,
-    },
+    Message { topic: String, data: Vec<u8> },
+    Discovered {},
+    Expired {},
 }
 
+pub type Topics = HashMap<String, Subscriber<()>>;
 pub struct Swarm {
-    swarm: libp2p::Swarm<Behaviour>,
+    cfg: zenoh::Config,
     from_client: mpsc::Receiver<ToSwarm>,
 }
 
 impl Swarm {
     pub fn into_stream(self) -> Pin<Box<dyn Stream<Item = FromSwarm> + Send>> {
         let Swarm {
-            mut swarm,
+            cfg,
             mut from_client,
         } = self;
         let stream = async_stream::stream! {
+            let (mut to_topics, mut from_topics) = mpsc::channel(1024);
+            let mut topics = Topics::new();
+            let Ok(mut session) = crate::open(cfg).await else { return; };
+            let Ok((_token, discovery)) = register_liveness(&mut session).await else { return; };
             loop {
                 tokio::select! {
                     msg = from_client.recv() => {
                         let Some(msg) = msg else { break };
-                        on_message(&mut swarm, msg);
+                        on_message(&mut session, &mut topics, &mut to_topics, msg).await;
                     }
-                    event = swarm.next() => {
-                        let Some(event) = event else { break };
-                        if let Some(item) = filter_swarm_event(event) {
-                            yield item;
+                    event = from_topics.recv() => {
+                        if let Some(event) = event {
+                            yield event
                         }
                     }
+                    token = discovery.recv_async() => {
+                        if let Ok(token) = token {
+                            let key_expr = token.key_expr().as_str().to_owned();
+                            let nid = key_expr.strip_prefix("nodes/").and_then(|s| s.strip_suffix("/live"));
+                            yield match token.kind() {
+                                SampleKind::Put => {
+                                    info!("discovered: {nid:?}");
+                                    FromSwarm::Discovered {}
+                                }
+                                SampleKind::Delete => {
+                                    info!("expired: {nid:?}");
+                                    FromSwarm::Expired {}
+                                }
+                            }
+                        }
+
+                    }
                 }
             }
         };
@@ -79,208 +91,96 @@ impl Swarm {
     }
 }
 
-fn on_message(swarm: &mut libp2p::Swarm<Behaviour>, message: ToSwarm) {
-    match message {
-        ToSwarm::Subscribe {
-            topic,
-            result_sender,
-        } => {
-            let result = swarm
-                .behaviour_mut()
-                .gossipsub
-                .subscribe(&gossipsub::IdentTopic::new(topic));
-            _ = result_sender.send(result);
-        }
-        ToSwarm::Unsubscribe {
-            topic,
-            result_sender,
-        } => {
-            let result = swarm
-                .behaviour_mut()
-                .gossipsub
-                .unsubscribe(&gossipsub::IdentTopic::new(topic));
-            _ = result_sender.send(result);
-        }
+async fn register_liveness(
+    session: &mut Session,
+) -> Result<(LivelinessToken, Subscriber<FifoChannelHandler<Sample>>)> {
+    let token = session
+        .liveliness()
+        .declare_token(format!("nodes/{}/live", session.zid()))
+        .await?;
+    let sub = session
+        .liveliness()
+        .declare_subscriber("nodes/*/live")
+        .history(true)
+        .await?;
+    Ok((token, sub))
+}
+
+async fn on_message(
+    session: &mut Session,
+    topics: &mut Topics,
+    to_topics: &mut mpsc::Sender<FromSwarm>,
+    msg: ToSwarm,
+) {
+    match msg {
         ToSwarm::Publish {
             topic,
             data,
             result_sender,
         } => {
-            let result = swarm
-                .behaviour_mut()
-                .gossipsub
-                .publish(gossipsub::IdentTopic::new(topic), data);
-            _ = result_sender.send(result);
+            let res = session.put(format!("topics/{topic}"), data).await;
+            _ = result_sender.send(res);
+        }
+        ToSwarm::Unsubscribe {
+            topic,
+            result_sender,
+        } => {
+            let Some((_, subscriber)) = topics.remove_entry(&topic) else {
+                _ = result_sender.send(false);
+                return;
+            };
+            _ = subscriber.undeclare().await;
+            _ = result_sender.send(true);
+        }
+        ToSwarm::Subscribe {
+            topic,
+            result_sender,
+        } => {
+            assert!(topic.is_ascii());
+            if topics.contains_key(&topic) {
+                _ = result_sender.send(Ok(false));
+                return;
+            }
+            let subscriber = match session
+                .declare_subscriber(format!("topics/{topic}"))
+                .allowed_origin(zenoh::sample::Locality::Remote)
+                .callback({
+                    let sender = to_topics.clone();
+                    let topic = topic.clone();
+                    move |sample| {
+                        if sample.kind() != SampleKind::Put {
+                            return;
+                        }
+                        _ = sender.try_send(FromSwarm::Message {
+                            topic: topic.clone(),
+                            data: sample.payload().to_bytes().to_vec(),
+                        });
+                    }
+                })
+                .await
+            {
+                Ok(p) => p,
+                Err(e) => {
+                    _ = result_sender.send(Err(e));
+                    return;
+                }
+            };
+            assert!(topics.insert(topic, subscriber).is_none());
+            _ = result_sender.send(Ok(true));
         }
     }
 }
 
-fn filter_swarm_event(event: SwarmEvent<BehaviourEvent>) -> Option<FromSwarm> {
-    match event {
-        SwarmEvent::Behaviour(BehaviourEvent::Gossipsub(gossipsub::Event::Message {
-            message:
-                gossipsub::Message {
-                    source: Some(peer_id),
-                    topic,
-                    data,
-                    ..
-                },
-            ..
-        })) => Some(FromSwarm::Message {
-            from: peer_id,
-            topic: topic.into_string(),
-            data,
-        }),
-        SwarmEvent::Behaviour(BehaviourEvent::Discovery(
-            discovery::Event::ConnectionEstablished { peer_id, .. },
-        )) => Some(FromSwarm::Discovered { peer_id }),
-        SwarmEvent::Behaviour(BehaviourEvent::Discovery(discovery::Event::ConnectionClosed {
-            peer_id,
-            ..
-        })) => Some(FromSwarm::Expired { peer_id }),
-        _ => None,
-    }
-}
-
-/// Create and configure a swarm.
-///
-/// - `listen_port`: TCP port to listen on. `0` lets the OS assign one.
-/// - `bootstrap_peers`: multiaddrs to dial for environments without mDNS.
 pub fn create_swarm(
-    keypair: identity::Keypair,
+    identity: u128,
     from_client: mpsc::Receiver<ToSwarm>,
     bootstrap_peers: Vec<String>,
     listen_port: u16,
-) -> alias::AnyResult<Swarm> {
-    let parsed_bootstrap_peers: Vec<libp2p::Multiaddr> = bootstrap_peers
-        .iter()
-        .filter(|s| !s.is_empty())
-        .filter_map(|s| s.parse().ok())
-        .collect();
-
-    let mut swarm = SwarmBuilder::with_existing_identity(keypair)
-        .with_tokio()
-        .with_other_transport(tcp_transport)?
-        .with_behaviour(|keypair| Behaviour::new(keypair, parsed_bootstrap_peers))?
-        .build();
-
-    swarm.listen_on(format!("/ip4/0.0.0.0/tcp/{listen_port}").parse()?)?;
-    Ok(Swarm { swarm, from_client })
-}
-
-mod transport {
-    use crate::alias;
-    use crate::swarm::{NETWORK_VERSION, OVERRIDE_VERSION_ENV_VAR};
-    use futures_lite::{AsyncRead, AsyncWrite};
-    use keccak_const::Sha3_256;
-    use libp2p::core::muxing;
-    use libp2p::core::transport::Boxed;
-    use libp2p::pnet::{PnetError, PnetOutput};
-    use libp2p::{PeerId, Transport, identity, noise, pnet, yamux};
-    use std::{env, sync::LazyLock};
-
-    /// Key used for networking's private network; parametrized on the [`NETWORK_VERSION`].
-    /// See [`pnet_upgrade`] for more.
-    static PNET_PRESHARED_KEY: LazyLock<[u8; 32]> = LazyLock::new(|| {
-        let builder = Sha3_256::new().update(b"exo_discovery_network");
-
-        if let Ok(var) = env::var(OVERRIDE_VERSION_ENV_VAR) {
-            let bytes = var.into_bytes();
-            builder.update(&bytes)
-        } else {
-            builder.update(NETWORK_VERSION)
-        }
-        .finalize()
-    });
-
-    /// Make the Swarm run on a private network, as to not clash with public libp2p nodes and
-    /// also different-versioned instances of this same network.
-    /// This is implemented as an additional "upgrade" ontop of existing [`libp2p::Transport`] layers.
-    async fn pnet_upgrade<TSocket>(
-        socket: TSocket,
-        _: impl Sized,
-    ) -> Result<PnetOutput<TSocket>, PnetError>
-    where
-        TSocket: AsyncRead + AsyncWrite + Send + Unpin + 'static,
-    {
-        use pnet::{PnetConfig, PreSharedKey};
-        PnetConfig::new(PreSharedKey::new(*PNET_PRESHARED_KEY))
-            .handshake(socket)
-            .await
-    }
-
-    /// TCP/IP transport layer configuration.
-    pub fn tcp_transport(
-        keypair: &identity::Keypair,
-    ) -> alias::AnyResult<Boxed<(PeerId, muxing::StreamMuxerBox)>> {
-        use libp2p::{
-            core::upgrade::Version,
-            tcp::{Config, tokio},
-        };
-
-        // `TCP_NODELAY` enabled => avoid latency
-        let tcp_config = Config::default().nodelay(true);
-
-        // V1 + lazy flushing => 0-RTT negotiation
-        let upgrade_version = Version::V1Lazy;
-
-        // Noise is faster than TLS + we don't care much for security
-        let noise_config = noise::Config::new(keypair)?;
-
-        // Use default Yamux config for multiplexing
-        let yamux_config = yamux::Config::default();
-
-        // Create new Tokio-driven TCP/IP transport layer
-        let base_transport = tokio::Transport::new(tcp_config)
-            .and_then(pnet_upgrade)
-            .upgrade(upgrade_version)
-            .authenticate(noise_config)
-            .multiplex(yamux_config);
-
-        // Return boxed transport (to flatten complex type)
-        Ok(base_transport.boxed())
-    }
-}
-
-mod behaviour {
-    use crate::{alias, discovery};
-    use libp2p::swarm::NetworkBehaviour;
-    use libp2p::{gossipsub, identity};
-
-    /// Behavior of the Swarm which composes all desired behaviors:
-    /// Right now its just [`discovery::Behaviour`] and [`gossipsub::Behaviour`].
-    #[derive(NetworkBehaviour)]
-    pub struct Behaviour {
-        pub discovery: discovery::Behaviour,
-        pub gossipsub: gossipsub::Behaviour,
-    }
-
-    impl Behaviour {
-        pub fn new(
-            keypair: &identity::Keypair,
-            bootstrap_peers: Vec<libp2p::Multiaddr>,
-        ) -> alias::AnyResult<Self> {
-            Ok(Self {
-                discovery: discovery::Behaviour::new(keypair, bootstrap_peers)?,
-                gossipsub: gossipsub_behaviour(keypair),
-            })
-        }
-    }
-
-    fn gossipsub_behaviour(keypair: &identity::Keypair) -> gossipsub::Behaviour {
-        use gossipsub::{ConfigBuilder, MessageAuthenticity, ValidationMode};
-
-        // build a gossipsub network behaviour
-        //  => signed message authenticity + strict validation mode means the message-ID is
-        //     automatically provided by gossipsub w/out needing to provide custom message-ID function
-        gossipsub::Behaviour::new(
-            MessageAuthenticity::Signed(keypair.clone()),
-            ConfigBuilder::default()
-                .max_transmit_size(8 * 1024 * 1024)
-                .validation_mode(ValidationMode::Strict)
-                .build()
-                .expect("the configuration should always be valid"),
-        )
-        .expect("creating gossipsub behavior should always work")
-    }
+) -> Result<Swarm> {
+    // todo: bootstrap
+    if !bootstrap_peers.is_empty() || listen_port != 0 {
+        todo!();
+    }
+    let cfg = crate::cfg(identity, listen_port)?;
+    Ok(Swarm { cfg, from_client })
 }

rust/networking/tests/bootstrap_peers.rs

@@ -1,107 +0,0 @@
-use futures_lite::StreamExt;
-use networking::swarm::{FromSwarm, create_swarm};
-use std::time::Duration;
-use tokio::sync::mpsc;
-use tokio::time::timeout;
-
-/// Helper: find a free TCP port.
-fn free_port() -> u16 {
-    let listener = std::net::TcpListener::bind("127.0.0.1:0").unwrap();
-    listener.local_addr().unwrap().port()
-}
-
-/// Two nodes connect via bootstrap peers — no mDNS needed.
-///
-/// Node A listens on a fixed port. Node B bootstraps to A's address.
-/// We verify that B emits `FromSwarm::Discovered` for A's peer ID.
-#[tokio::test]
-async fn two_nodes_connect_via_bootstrap_peers() {
-    let port_a = free_port();
-
-    // Node A: listens on a known port, no bootstrap peers
-    let keypair_a = libp2p::identity::Keypair::generate_ed25519();
-    let peer_id_a = keypair_a.public().to_peer_id();
-    let (_tx_a, rx_a) = mpsc::channel(16);
-    let swarm_a = create_swarm(keypair_a, rx_a, vec![], port_a).expect("create swarm A");
-    let mut stream_a = swarm_a.into_stream();
-
-    // Node B: bootstraps to A's address
-    let keypair_b = libp2p::identity::Keypair::generate_ed25519();
-    let (_tx_b, rx_b) = mpsc::channel(16);
-    let swarm_b = create_swarm(
-        keypair_b,
-        rx_b,
-        vec![format!("/ip4/127.0.0.1/tcp/{port_a}")],
-        0,
-    )
-    .expect("create swarm B");
-    let mut stream_b = swarm_b.into_stream();
-
-    // Wait for B to discover A (connection established)
-    let connected = timeout(Duration::from_secs(10), async {
-        loop {
-            tokio::select! {
-                Some(event) = stream_a.next() => {
-                    // A will also see B connect, but we check from B's perspective
-                    let _ = event;
-                }
-                Some(event) = stream_b.next() => {
-                    if let FromSwarm::Discovered { peer_id } = event {
-                        if peer_id == peer_id_a {
-                            return true;
-                        }
-                    }
-                }
-            }
-        }
-    })
-    .await;
-
-    assert!(
-        connected.is_ok() && connected.unwrap(),
-        "Node B should discover Node A via bootstrap peer"
-    );
-}
-
-/// Empty bootstrap peers should work (backward compatible).
-#[tokio::test]
-async fn create_swarm_with_empty_bootstrap_peers() {
-    let keypair = libp2p::identity::Keypair::generate_ed25519();
-    let (_tx, rx) = mpsc::channel(16);
-    let swarm = create_swarm(keypair, rx, vec![], 0);
-    assert!(
-        swarm.is_ok(),
-        "create_swarm with no bootstrap peers should succeed"
-    );
-}
-
-/// Invalid multiaddr strings are silently filtered out.
-#[tokio::test]
-async fn create_swarm_ignores_invalid_bootstrap_addrs() {
-    let keypair = libp2p::identity::Keypair::generate_ed25519();
-    let (_tx, rx) = mpsc::channel(16);
-    let swarm = create_swarm(
-        keypair,
-        rx,
-        vec![
-            "not-a-valid-multiaddr".to_string(),
-            "".to_string(),
-            "/ip4/10.0.0.1/tcp/30000".to_string(), // valid
-        ],
-        0,
-    );
-    assert!(
-        swarm.is_ok(),
-        "create_swarm should succeed even with invalid bootstrap addrs"
-    );
-}
-
-/// Fixed listen port works correctly.
-#[tokio::test]
-async fn create_swarm_with_fixed_port() {
-    let port = free_port();
-    let keypair = libp2p::identity::Keypair::generate_ed25519();
-    let (_tx, rx) = mpsc::channel(16);
-    let swarm = create_swarm(keypair, rx, vec![], port);
-    assert!(swarm.is_ok(), "create_swarm with fixed port should succeed");
-}

rust/networking/tests/dummy.rs

@@ -1,7 +0,0 @@
-// maybe this will hold test in the future...??
-
-#[cfg(test)]
-mod tests {
-    #[test]
-    fn does_nothing() {}
-}

rust/util/Cargo.toml

@@ -1,15 +0,0 @@
-[package]
-name = "util"
-version = { workspace = true }
-edition = { workspace = true }
-publish = false
-
-[lib]
-doctest = false
-name = "util"
-path = "src/lib.rs"
-
-[lints]
-workspace = true
-
-[dependencies]

rust/util/src/lib.rs

@@ -1 +0,0 @@
-pub mod wakerdeque;

rust/util/src/wakerdeque.rs

@@ -1,55 +0,0 @@
-use std::collections::VecDeque;
-use std::fmt::{Debug, Formatter};
-use std::task::{Context, Waker};
-
-/// A wrapper around [`VecDeque`] which wakes (if it can) on any `push_*` methods,
-/// and updates the internally stored waker by consuming [`Context`] on any `pop_*` methods.
-pub struct WakerDeque<T> {
-    waker: Option<Waker>,
-    deque: VecDeque<T>,
-}
-
-impl<T: Debug> Debug for WakerDeque<T> {
-    fn fmt(&self, f: &mut Formatter<'_>) -> std::fmt::Result {
-        self.deque.fmt(f)
-    }
-}
-
-impl<T> WakerDeque<T> {
-    pub fn new() -> Self {
-        Self {
-            waker: None,
-            deque: VecDeque::new(),
-        }
-    }
-
-    fn update(&mut self, cx: &mut Context<'_>) {
-        self.waker = Some(cx.waker().clone());
-    }
-
-    fn wake(&mut self) {
-        let Some(ref mut w) = self.waker else { return };
-        w.wake_by_ref();
-        self.waker = None;
-    }
-
-    pub fn pop_front(&mut self, cx: &mut Context<'_>) -> Option<T> {
-        self.update(cx);
-        self.deque.pop_front()
-    }
-
-    pub fn pop_back(&mut self, cx: &mut Context<'_>) -> Option<T> {
-        self.update(cx);
-        self.deque.pop_back()
-    }
-
-    pub fn push_front(&mut self, value: T) {
-        self.wake();
-        self.deque.push_front(value);
-    }
-
-    pub fn push_back(&mut self, value: T) {
-        self.wake();
-        self.deque.push_back(value);
-    }
-}

src/exo/api/main.py

@@ -133,12 +133,10 @@ from exo.shared.constants import (
 )
 from exo.shared.election import ElectionMessage
 from exo.shared.logging import InterceptLogger
+from exo.shared.models import model_cards
 from exo.shared.models.model_cards import (
     ModelCard,
     ModelId,
-    add_to_card_cache,
-    get_card,
-    get_model_cards,
 )
 from exo.shared.tracing import TraceEvent, compute_stats, export_trace, load_trace_file
 from exo.shared.types.chunks import (
@@ -481,6 +479,7 @@ class API:
                 topology=self.state.topology,
                 current_instances=self.state.instances,
                 download_status=self.state.downloads,
+                node_rdma_ctl=self.state.node_rdma_ctl,
             )
         except ValueError as exc:
             raise HTTPException(status_code=400, detail=str(exc)) from exc
@@ -544,6 +543,7 @@ class API:
                     current_instances=self.state.instances,
                     required_nodes=required_nodes,
                     download_status=self.state.downloads,
+                    node_rdma_ctl=self.state.node_rdma_ctl,
                 )
             except ValueError as exc:
                 if (model_card.model_id, sharding, instance_meta, 0) not in seen:
@@ -1633,17 +1633,16 @@ class API:
     async def ollama_tags(self) -> OllamaTagsResponse:
         """Returns list of models in Ollama tags format. We return the downloaded ones only."""
 
-        def none_if_empty(value: str) -> str | None:
-            return value or None
-
-        downloaded_model_ids: set[str] = set()
+        downloaded_model_ids: set[ModelId] = set()
         for node_downloads in self.state.downloads.values():
             for dl in node_downloads:
                 if isinstance(dl, DownloadCompleted):
                     downloaded_model_ids.add(dl.shard_metadata.model_card.model_id)
 
         cards = [
-            c for c in await get_model_cards() if c.model_id in downloaded_model_ids
+            c
+            for c in await model_cards.card_cache.list_all()
+            if c.model_id in downloaded_model_ids
         ]
 
         now = time.strftime("%Y-%m-%dT%H:%M:%SZ", time.gmtime())
@@ -1656,8 +1655,8 @@ class API:
                     size=card.storage_size.in_bytes,
                     digest="sha256:000000000000",
                     details=OllamaModelDetails(
-                        family=none_if_empty(card.family),
-                        quantization_level=none_if_empty(card.quantization),
+                        family=card.family or None,
+                        quantization_level=card.quantization or None,
                     ),
                 )
                 for card in cards
@@ -1720,7 +1719,7 @@ class API:
 
     async def get_models(self, status: str | None = Query(default=None)) -> ModelList:
         """Returns list of available models, optionally filtered by being downloaded."""
-        cards = await get_model_cards()
+        cards = await model_cards.card_cache.list_all()
 
         if status == "downloaded":
             downloaded_model_ids: set[str] = set()
@@ -1771,7 +1770,7 @@ class API:
 
         # Immediately update the local cache so the subsequent GET /models
         # returns the new model without waiting for the event round-trip.
-        add_to_card_cache(card)
+        model_cards.card_cache.cc[card.model_id] = card
 
         return ModelListModel(
             id=card.model_id,
@@ -1787,7 +1786,7 @@ class API:
 
     async def delete_custom_model(self, model_id: ModelId) -> JSONResponse:
         """Delete a user-added custom model card and sync deletion across the cluster."""
-        card = get_card(model_id)
+        card = model_cards.card_cache.get(model_id)
         if card is None or not card.is_custom:
             raise HTTPException(status_code=404, detail="Custom model card not found")
 

src/exo/download/coordinator.py

@@ -16,7 +16,8 @@ from exo.download.download_utils import (
 )
 from exo.download.shard_downloader import ShardDownloader
 from exo.shared.constants import EXO_DEFAULT_MODELS_DIR, EXO_MODELS_READ_ONLY_DIRS
-from exo.shared.models.model_cards import ModelId, get_model_cards
+from exo.shared.models import model_cards
+from exo.shared.models.model_cards import ModelId
 from exo.shared.types.commands import (
     CancelDownload,
     DeleteDownload,
@@ -422,7 +423,7 @@ class DownloadCoordinator:
                     )
                 # Scan read-only directories for pre-downloaded models
                 if EXO_MODELS_READ_ONLY_DIRS:
-                    for card in await get_model_cards():
+                    for card in await model_cards.card_cache.list_all():
                         mid = card.model_id
                         if mid in self.active_downloads:
                             continue

src/exo/download/download_utils.py

@@ -1,11 +1,12 @@
 import asyncio
 import hashlib
 import os
+import random
 import shutil
 import ssl
 import time
 import traceback
-from collections.abc import Awaitable
+from collections.abc import Awaitable, Mapping
 from datetime import timedelta
 from pathlib import Path
 from typing import Callable, Literal
@@ -55,6 +56,36 @@ class HuggingFaceAuthenticationError(Exception):
 class HuggingFaceRateLimitError(Exception):
     """429 Huggingface code"""
 
+    def __init__(self, msg: str, retry_after: float | None = None) -> None:
+        super().__init__(msg)
+        self.retry_after = retry_after
+
+
+def _parse_retry_after(headers: Mapping[str, str]) -> float | None:
+    """Parse seconds-to-reset from HF's RateLimit header.
+
+    HF sends e.g. ``ratelimit: "api";r=0;t=52`` on 429s; ``t`` is the wait.
+    Returns ``None`` if the header is missing or has no ``t`` field.
+    """
+    raw = headers.get("RateLimit") or headers.get("ratelimit")
+    if raw is None:
+        return None
+    for part in raw.split(";"):
+        key, _, val = part.strip().partition("=")
+        if key == "t":
+            try:
+                return float(val)
+            except ValueError:
+                return None
+    return None
+
+
+# reset window is 5 min
+_RATE_LIMIT_MAX_SLEEP_SECS = 300.0
+
+# 24h. Manually clear the cache (or `delete_model`) to force a refresh.
+_FILE_LIST_CACHE_TTL_SECS = 24 * 60 * 60
+
 
 async def _build_auth_error_message(status_code: int, model_id: ModelId) -> str:
     token = await get_hf_token()
@@ -348,9 +379,6 @@ async def _build_file_list_from_local_directory(
     return None
 
 
-_fetched_file_lists_this_session: set[str] = set()
-
-
 async def fetch_file_list_with_cache(
     model_id: ModelId,
     revision: str = "main",
@@ -360,13 +388,16 @@ async def fetch_file_list_with_cache(
 ) -> list[FileListEntry]:
     target_dir = await ensure_cache_dir(model_id)
     cache_file = target_dir / f"{model_id.normalize()}--{revision}--file_list.json"
-    cache_key = f"{model_id.normalize()}--{revision}"
 
-    if cache_key in _fetched_file_lists_this_session and await aios.path.exists(
-        cache_file
-    ):
-        async with aiofiles.open(cache_file, "r") as f:
-            return TypeAdapter(list[FileListEntry]).validate_json(await f.read())
+    # cache survives process restarts so cold starts don't re-burst HF
+    if await aios.path.exists(cache_file):
+        try:
+            cache_age = time.time() - (await aios.stat(cache_file)).st_mtime
+        except OSError:
+            cache_age = float("inf")
+        if cache_age < _FILE_LIST_CACHE_TTL_SECS:
+            async with aiofiles.open(cache_file, "r") as f:
+                return TypeAdapter(list[FileListEntry]).validate_json(await f.read())
 
     if skip_internet:
         if await aios.path.exists(cache_file):
@@ -395,7 +426,6 @@ async def fetch_file_list_with_cache(
             await f.write(
                 TypeAdapter(list[FileListEntry]).dump_json(file_list).decode()
             )
-        _fetched_file_lists_this_session.add(cache_key)
         return file_list
     except Exception as e:
         logger.opt(exception=e).warning(
@@ -426,17 +456,29 @@ async def fetch_file_list_with_retry(
     recursive: bool = False,
     on_connection_lost: Callable[[], None] = lambda: None,
 ) -> list[FileListEntry]:
-    n_attempts = 3
+    n_attempts = 5
     for attempt in range(n_attempts):
         try:
             return await _fetch_file_list(model_id, revision, path, recursive)
         except HuggingFaceAuthenticationError:
             raise
+        except HuggingFaceRateLimitError as e:
+            if attempt == n_attempts - 1:
+                raise
+            sleep_for = e.retry_after if e.retry_after is not None else 2.0**attempt
+            sleep_for = min(sleep_for, _RATE_LIMIT_MAX_SLEEP_SECS) + random.uniform(
+                0, 1
+            )
+            logger.warning(
+                f"Rate limited by HuggingFace fetching file list for {model_id}; "
+                f"sleeping {sleep_for:.1f}s before retry {attempt + 2}/{n_attempts}"
+            )
+            await asyncio.sleep(sleep_for)
         except Exception as e:
             on_connection_lost()
             if attempt == n_attempts - 1:
                 raise e
-            await asyncio.sleep(2.0**attempt)
+            await asyncio.sleep(2.0**attempt + random.uniform(0, 1))
     raise Exception(
         f"Failed to fetch file list for {model_id=} {revision=} {path=} {recursive=}"
     )
@@ -447,6 +489,9 @@ async def _fetch_file_list(
 ) -> list[FileListEntry]:
     api_url = f"{get_hf_endpoint()}/api/models/{model_id}/tree/{revision}"
     url = f"{api_url}/{path}" if path else api_url
+    # ?recursive=true returns the whole subtree in one request
+    if recursive:
+        url = f"{url}?recursive=true"
 
     headers = await get_download_headers()
     async with (
@@ -458,7 +503,8 @@ async def _fetch_file_list(
             raise HuggingFaceAuthenticationError(msg)
         elif response.status == 429:
             raise HuggingFaceRateLimitError(
-                f"Couldn't download {model_id} because of HuggingFace rate limit."
+                f"HuggingFace rate limit hit fetching file list for {model_id}",
+                retry_after=_parse_retry_after(response.headers),
             )
         elif response.status == 200:
             data_json = await response.text()
@@ -468,10 +514,14 @@ async def _fetch_file_list(
                 if item.type == "file":
                     files.append(FileListEntry.model_validate(item))
                 elif item.type == "directory" and recursive:
-                    subfiles = await _fetch_file_list(
-                        model_id, revision, item.path, recursive
-                    )
-                    files.extend(subfiles)
+                    # already inlined by ?recursive=true
+                    continue
+            if recursive and len(data) >= 1000:
+                # HF tree endpoint paginates at 1000; we don't follow cursors
+                logger.warning(
+                    f"File list for {model_id} hit the 1000-entry page cap "
+                    "and may be truncated; cursor pagination is not implemented"
+                )
             return files
         else:
             raise Exception(f"Failed to fetch file list: {response.status}")
@@ -552,6 +602,11 @@ async def file_meta(
         if r.status in [401, 403]:
             msg = await _build_auth_error_message(r.status, model_id)
             raise HuggingFaceAuthenticationError(msg)
+        if r.status == 429:
+            raise HuggingFaceRateLimitError(
+                f"HuggingFace rate limit hit fetching metadata for {model_id}/{path}",
+                retry_after=_parse_retry_after(r.headers),
+            )
         content_length = int(
             r.headers.get("x-linked-size") or r.headers.get("content-length") or 0
         )
@@ -571,7 +626,7 @@ async def download_file_with_retry(
     on_connection_lost: Callable[[], None] = lambda: None,
     skip_internet: bool = False,
 ) -> Path:
-    n_attempts = 3
+    n_attempts = 5
     for attempt in range(n_attempts):
         try:
             return await _download_file(
@@ -583,12 +638,16 @@ async def download_file_with_retry(
             raise
         except HuggingFaceRateLimitError as e:
             if attempt == n_attempts - 1:
-                raise e
-            logger.error(
-                f"Download error on attempt {attempt}/{n_attempts} for {model_id=} {revision=} {path=} {target_dir=}"
+                raise
+            sleep_for = e.retry_after if e.retry_after is not None else 2.0**attempt
+            sleep_for = min(sleep_for, _RATE_LIMIT_MAX_SLEEP_SECS) + random.uniform(
+                0, 1
             )
-            logger.error(traceback.format_exc())
-            await asyncio.sleep(2.0**attempt)
+            logger.warning(
+                f"Rate limited by HuggingFace downloading {model_id}/{path}; "
+                f"sleeping {sleep_for:.1f}s before retry {attempt + 2}/{n_attempts}"
+            )
+            await asyncio.sleep(sleep_for)
         except Exception as e:
             if attempt == n_attempts - 1:
                 on_connection_lost()
@@ -597,7 +656,7 @@ async def download_file_with_retry(
                 f"Download error on attempt {attempt + 1}/{n_attempts} for {model_id=} {revision=} {path=} {target_dir=}"
             )
             logger.error(traceback.format_exc())
-            await asyncio.sleep(2.0**attempt)
+            await asyncio.sleep(2.0**attempt + random.uniform(0, 1))
     raise Exception(
         f"Failed to download file {model_id=} {revision=} {path=} {target_dir=}"
     )
@@ -665,6 +724,11 @@ async def _download_file(
             if r.status in [401, 403]:
                 msg = await _build_auth_error_message(r.status, model_id)
                 raise HuggingFaceAuthenticationError(msg)
+            if r.status == 429:
+                raise HuggingFaceRateLimitError(
+                    f"HuggingFace rate limit hit downloading {model_id}/{path}",
+                    retry_after=_parse_retry_after(r.headers),
+                )
             assert r.status in [200, 206], (
                 f"Failed to download {path} from {url}: {r.status}"
             )

src/exo/download/impl_shard_downloader.py

@@ -11,11 +11,11 @@ from exo.download.download_utils import (
     download_shard,
 )
 from exo.download.shard_downloader import ShardDownloader
+from exo.shared.models import model_cards
 from exo.shared.models.model_cards import (
     ModelCard,
     ModelId,
     ModelTask,
-    get_model_cards,
 )
 from exo.shared.types.memory import Memory
 from exo.shared.types.worker.shards import (
@@ -258,7 +258,7 @@ class ResumableShardDownloader(ShardDownloader):
 
         tasks = [
             create_task(download_with_semaphore(model_card))
-            for model_card in await get_model_cards()
+            for model_card in await model_cards.card_cache.list_all()
         ]
 
         for task in asyncio.as_completed(tasks):

src/exo/download/tests/test_offline_mode.py

@@ -1,5 +1,7 @@
 """Tests for offline/air-gapped mode."""
 
+import os
+import time
 from collections.abc import AsyncIterator
 from pathlib import Path
 from unittest.mock import AsyncMock, patch
@@ -231,3 +233,64 @@ class TestFetchFileListOffline:
         raise FileNotFoundError."""
         with pytest.raises(FileNotFoundError, match="No internet"):
             await fetch_file_list_with_cache(model_id, "main", skip_internet=True)
+
+
+class TestFileListCacheTTL:
+    async def test_uses_fresh_cache_without_fetching(
+        self, model_id: ModelId, temp_models_dir: Path
+    ) -> None:
+        from pydantic import TypeAdapter
+
+        cache_dir = temp_models_dir / "caches" / model_id.normalize()
+        await aios.makedirs(cache_dir, exist_ok=True)
+
+        cached_list = [
+            FileListEntry(type="file", path="model.safetensors", size=1000),
+        ]
+        cache_file = cache_dir / f"{model_id.normalize()}--main--file_list.json"
+        async with aiofiles.open(cache_file, "w") as f:
+            await f.write(
+                TypeAdapter(list[FileListEntry]).dump_json(cached_list).decode()
+            )
+
+        with patch(
+            "exo.download.download_utils.fetch_file_list_with_retry",
+            new_callable=AsyncMock,
+        ) as mock_fetch:
+            result = await fetch_file_list_with_cache(model_id, "main")
+
+        assert result == cached_list
+        mock_fetch.assert_not_called()
+
+    async def test_refetches_when_cache_older_than_ttl(
+        self, model_id: ModelId, temp_models_dir: Path
+    ) -> None:
+        from pydantic import TypeAdapter
+
+        from exo.download.download_utils import (
+            _FILE_LIST_CACHE_TTL_SECS,  # pyright: ignore[reportPrivateUsage]
+        )
+
+        cache_dir = temp_models_dir / "caches" / model_id.normalize()
+        await aios.makedirs(cache_dir, exist_ok=True)
+
+        stale_list = [FileListEntry(type="file", path="stale.bin", size=1)]
+        cache_file = cache_dir / f"{model_id.normalize()}--main--file_list.json"
+        async with aiofiles.open(cache_file, "w") as f:
+            await f.write(
+                TypeAdapter(list[FileListEntry]).dump_json(stale_list).decode()
+            )
+
+        old_mtime = time.time() - _FILE_LIST_CACHE_TTL_SECS - 60
+        os.utime(cache_file, (old_mtime, old_mtime))
+
+        fresh_list = [FileListEntry(type="file", path="fresh.bin", size=2)]
+        with patch(
+            "exo.download.download_utils.fetch_file_list_with_retry",
+            new_callable=AsyncMock,
+            return_value=fresh_list,
+        ) as mock_fetch:
+            result = await fetch_file_list_with_cache(model_id, "main")
+
+        assert result == fresh_list
+        mock_fetch.assert_called_once()

src/exo/download/tests/test_rate_limit_handling.py

@@ -0,0 +1,355 @@
+"""Tests for HuggingFace 429 rate-limit handling in download_utils."""
+
+from collections.abc import AsyncIterator
+from pathlib import Path
+from unittest.mock import AsyncMock, MagicMock, patch
+
+import aiofiles.os as aios
+import pytest
+
+from exo.download.download_utils import (
+    HuggingFaceRateLimitError,
+    _download_file,  # pyright: ignore[reportPrivateUsage]
+    _fetch_file_list,  # pyright: ignore[reportPrivateUsage]
+    _parse_retry_after,  # pyright: ignore[reportPrivateUsage]
+    download_file_with_retry,
+    fetch_file_list_with_retry,
+    file_meta,
+)
+from exo.shared.types.common import ModelId
+
+# captured from a real HF 429 on 2026-04-30 (header is lowercased by Cloudfront)
+REAL_HF_429_HEADERS_2026_04_30 = {
+    "ratelimit": '"api";r=0;t=52',
+    "ratelimit-policy": '"fixed window";"api";q=500;w=300',
+}
+
+
+class TestParseRetryAfter:
+    def test_parses_documented_format(self) -> None:
+        assert _parse_retry_after({"RateLimit": '"api";r=0;t=243'}) == 243.0
+
+    def test_parses_real_hf_response(self) -> None:
+        assert _parse_retry_after(REAL_HF_429_HEADERS_2026_04_30) == 52.0
+
+    def test_parses_resolvers_bucket(self) -> None:
+        assert _parse_retry_after({"ratelimit": '"resolvers";r=0;t=120'}) == 120.0
+
+    def test_parses_pages_bucket(self) -> None:
+        assert _parse_retry_after({"ratelimit": '"pages";r=0;t=10'}) == 10.0
+
+    def test_returns_none_when_header_missing(self) -> None:
+        assert _parse_retry_after({}) is None
+
+    def test_returns_none_when_only_retry_after_present(self) -> None:
+        assert _parse_retry_after({"Retry-After": "60"}) is None
+
+    def test_returns_none_when_format_unrecognised(self) -> None:
+        assert _parse_retry_after({"ratelimit": "garbage"}) is None
+
+    def test_handles_extra_whitespace(self) -> None:
+        assert _parse_retry_after({"ratelimit": '"api"; r=0; t=42'}) == 42.0
+
+
+class TestFetchFileListRetry:
+    async def test_uses_retry_after_from_error(self) -> None:
+        sleeps: list[float] = []
+
+        async def fake_sleep(seconds: float) -> None:
+            sleeps.append(seconds)
+
+        async def fake_fetch(*args: object, **kwargs: object) -> list[object]:
+            if not sleeps:
+                raise HuggingFaceRateLimitError("rate limited", retry_after=2.0)
+            return []
+
+        with (
+            patch(
+                "exo.download.download_utils._fetch_file_list", side_effect=fake_fetch
+            ),
+            patch("exo.download.download_utils.asyncio.sleep", side_effect=fake_sleep),
+        ):
+            result = await fetch_file_list_with_retry(ModelId("test/model"))
+
+        assert result == []
+        assert len(sleeps) == 1
+        assert 2.0 <= sleeps[0] < 3.0  # retry_after + jitter[0,1)
+
+    async def test_falls_back_to_exp_backoff_when_no_retry_after(self) -> None:
+        sleeps: list[float] = []
+
+        async def fake_sleep(seconds: float) -> None:
+            sleeps.append(seconds)
+
+        async def fake_fetch(*args: object, **kwargs: object) -> list[object]:
+            if not sleeps:
+                raise HuggingFaceRateLimitError("rate limited", retry_after=None)
+            return []
+
+        with (
+            patch(
+                "exo.download.download_utils._fetch_file_list", side_effect=fake_fetch
+            ),
+            patch("exo.download.download_utils.asyncio.sleep", side_effect=fake_sleep),
+        ):
+            await fetch_file_list_with_retry(ModelId("test/model"))
+
+        assert len(sleeps) == 1
+        assert 1.0 <= sleeps[0] < 2.0  # 2**0 + jitter[0,1)
+
+    async def test_caps_sleep_at_max_window(self) -> None:
+        sleeps: list[float] = []
+
+        async def fake_sleep(seconds: float) -> None:
+            sleeps.append(seconds)
+
+        async def fake_fetch(*args: object, **kwargs: object) -> list[object]:
+            if not sleeps:
+                raise HuggingFaceRateLimitError("rate limited", retry_after=10_000.0)
+            return []
+
+        with (
+            patch(
+                "exo.download.download_utils._fetch_file_list", side_effect=fake_fetch
+            ),
+            patch("exo.download.download_utils.asyncio.sleep", side_effect=fake_sleep),
+        ):
+            await fetch_file_list_with_retry(ModelId("test/model"))
+
+        assert len(sleeps) == 1
+        assert 300.0 <= sleeps[0] < 301.0  # cap + jitter[0,1)
+
+    async def test_retries_up_to_five_times(self) -> None:
+        sleeps: list[float] = []
+
+        async def fake_sleep(seconds: float) -> None:
+            sleeps.append(seconds)
+
+        async def fake_fetch(*args: object, **kwargs: object) -> list[object]:
+            raise HuggingFaceRateLimitError("rate limited", retry_after=1.0)
+
+        with (
+            patch(
+                "exo.download.download_utils._fetch_file_list", side_effect=fake_fetch
+            ),
+            patch("exo.download.download_utils.asyncio.sleep", side_effect=fake_sleep),
+            pytest.raises(HuggingFaceRateLimitError),
+        ):
+            await fetch_file_list_with_retry(ModelId("test/model"))
+
+        assert len(sleeps) == 4  # 5 attempts -> 4 sleeps before giving up
+
+
+class TestDownloadFileRetry:
+    @pytest.fixture
+    async def target_dir(self, tmp_path: Path) -> AsyncIterator[Path]:
+        target = tmp_path / "downloads"
+        await aios.makedirs(target, exist_ok=True)
+        yield target
+
+    async def test_uses_retry_after_from_error(self, target_dir: Path) -> None:
+        sleeps: list[float] = []
+        results: list[Path] = [target_dir / "file.bin"]
+
+        async def fake_sleep(seconds: float) -> None:
+            sleeps.append(seconds)
+
+        async def fake_download(*args: object, **kwargs: object) -> Path:
+            if not sleeps:
+                raise HuggingFaceRateLimitError("rate limited", retry_after=5.0)
+            return results[0]
+
+        with (
+            patch(
+                "exo.download.download_utils._download_file",
+                side_effect=fake_download,
+            ),
+            patch("exo.download.download_utils.asyncio.sleep", side_effect=fake_sleep),
+        ):
+            result = await download_file_with_retry(
+                ModelId("test/model"), "main", "file.bin", target_dir
+            )
+
+        assert result == results[0]
+        assert len(sleeps) == 1
+        assert 5.0 <= sleeps[0] < 6.0
+
+    async def test_caps_sleep_at_max_window(self, target_dir: Path) -> None:
+        sleeps: list[float] = []
+        results: list[Path] = [target_dir / "file.bin"]
+
+        async def fake_sleep(seconds: float) -> None:
+            sleeps.append(seconds)
+
+        async def fake_download(*args: object, **kwargs: object) -> Path:
+            if not sleeps:
+                raise HuggingFaceRateLimitError("rate limited", retry_after=99_999.0)
+            return results[0]
+
+        with (
+            patch(
+                "exo.download.download_utils._download_file",
+                side_effect=fake_download,
+            ),
+            patch("exo.download.download_utils.asyncio.sleep", side_effect=fake_sleep),
+        ):
+            await download_file_with_retry(
+                ModelId("test/model"), "main", "file.bin", target_dir
+            )
+
+        assert len(sleeps) == 1
+        assert 300.0 <= sleeps[0] < 301.0
+
+    async def test_retries_up_to_five_times(self, target_dir: Path) -> None:
+        sleeps: list[float] = []
+
+        async def fake_sleep(seconds: float) -> None:
+            sleeps.append(seconds)
+
+        with (
+            patch(
+                "exo.download.download_utils._download_file",
+                new_callable=AsyncMock,
+                side_effect=HuggingFaceRateLimitError("rate limited", retry_after=1.0),
+            ),
+            patch("exo.download.download_utils.asyncio.sleep", side_effect=fake_sleep),
+            pytest.raises(HuggingFaceRateLimitError),
+        ):
+            await download_file_with_retry(
+                ModelId("test/model"), "main", "file.bin", target_dir
+            )
+
+        assert len(sleeps) == 4
+
+
+def _make_mock_session_returning(
+    response_attrs: dict[str, object], method: str = "get"
+) -> MagicMock:
+    """Build a MagicMock that mimics ``create_http_session`` returning a
+    response whose ``status`` / ``headers`` are set from ``response_attrs``.
+
+    Mocks the chain ``create_http_session().__aenter__() -> session``, and
+    ``session.<method>().__aenter__() -> response``.
+    """
+    mock_response = MagicMock()
+    for k, v in response_attrs.items():
+        setattr(mock_response, k, v)
+
+    mock_session = MagicMock()
+    method_mock = getattr(mock_session, method)  # pyright: ignore[reportAny]
+    method_mock.return_value.__aenter__ = AsyncMock(  # pyright: ignore[reportAny]
+        return_value=mock_response
+    )
+    method_mock.return_value.__aexit__ = AsyncMock(  # pyright: ignore[reportAny]
+        return_value=None
+    )
+
+    mock_factory = MagicMock()
+    mock_factory.return_value.__aenter__ = AsyncMock(  # pyright: ignore[reportAny]
+        return_value=mock_session
+    )
+    mock_factory.return_value.__aexit__ = AsyncMock(  # pyright: ignore[reportAny]
+        return_value=None
+    )
+    return mock_factory
+
+
+REAL_HF_429_HEADER_DICT = {"ratelimit": '"api";r=0;t=52'}
+
+
+class TestRateLimitAtHttpCallSites:
+    """Verify each HF call site translates an HTTP 429 into a
+    ``HuggingFaceRateLimitError`` carrying the parsed ``retry_after``.
+
+    These tests would catch regressions where (a) the 429 branch is
+    deleted, (b) ``_parse_retry_after`` stops being called, or
+    (c) the wrong header object is passed to it.
+    """
+
+    async def test_fetch_file_list_maps_429_to_rate_limit_error(self) -> None:
+        mock_factory = _make_mock_session_returning(
+            {"status": 429, "headers": REAL_HF_429_HEADER_DICT}
+        )
+        with (
+            patch("exo.download.download_utils.create_http_session", mock_factory),
+            pytest.raises(HuggingFaceRateLimitError) as exc_info,
+        ):
+            await _fetch_file_list(ModelId("test/model"), "main")
+        assert exc_info.value.retry_after == 52.0
+
+    async def test_file_meta_maps_429_to_rate_limit_error(self) -> None:
+        mock_factory = _make_mock_session_returning(
+            {"status": 429, "headers": REAL_HF_429_HEADER_DICT}, method="head"
+        )
+        with (
+            patch("exo.download.download_utils.create_http_session", mock_factory),
+            pytest.raises(HuggingFaceRateLimitError) as exc_info,
+        ):
+            await file_meta(ModelId("test/model"), "main", "weights.safetensors")
+        assert exc_info.value.retry_after == 52.0
+
+    async def test_file_meta_maps_429_after_307_redirect(self) -> None:
+        """When the initial HEAD 307s and the redirected HEAD then 429s,
+        the 429 must still surface as ``HuggingFaceRateLimitError``."""
+        # First HEAD -> 307 with a Location header pointing somewhere new.
+        first_response = MagicMock()
+        first_response.status = 307
+        first_response.headers = {"location": "/redirected/url"}
+
+        # Second HEAD (the recursive call) -> 429 with the real-HF header.
+        second_response = MagicMock()
+        second_response.status = 429
+        second_response.headers = REAL_HF_429_HEADER_DICT
+
+        responses = iter([first_response, second_response])
+
+        mock_session = MagicMock()
+        mock_session.head.return_value.__aenter__ = AsyncMock(  # pyright: ignore[reportAny]
+            side_effect=lambda: next(responses)
+        )
+        mock_session.head.return_value.__aexit__ = AsyncMock(  # pyright: ignore[reportAny]
+            return_value=None
+        )
+
+        mock_factory = MagicMock()
+        mock_factory.return_value.__aenter__ = AsyncMock(  # pyright: ignore[reportAny]
+            return_value=mock_session
+        )
+        mock_factory.return_value.__aexit__ = AsyncMock(  # pyright: ignore[reportAny]
+            return_value=None
+        )
+
+        with (
+            patch("exo.download.download_utils.create_http_session", mock_factory),
+            pytest.raises(HuggingFaceRateLimitError) as exc_info,
+        ):
+            await file_meta(ModelId("test/model"), "main", "weights.safetensors")
+        assert exc_info.value.retry_after == 52.0
+
+    async def test_download_file_maps_429_to_rate_limit_error(
+        self, tmp_path: Path
+    ) -> None:
+        target_dir = tmp_path / "downloads"
+        await aios.makedirs(target_dir, exist_ok=True)
+        # No local file -> _download_file goes straight to file_meta then GET.
+        # We need both calls to succeed enough to reach the GET branch:
+        #   - file_meta returns a non-429 (size, etag) so we proceed.
+        #   - the GET then 429s.
+        with (
+            patch(
+                "exo.download.download_utils.file_meta",
+                new_callable=AsyncMock,
+                return_value=(100, "abc123"),
+            ),
+            patch(
+                "exo.download.download_utils.create_http_session",
+                _make_mock_session_returning(
+                    {"status": 429, "headers": REAL_HF_429_HEADER_DICT}
+                ),
+            ),
+            pytest.raises(HuggingFaceRateLimitError) as exc_info,
+        ):
+            await _download_file(
+                ModelId("test/model"), "main", "weights.safetensors", target_dir
+            )
+        assert exc_info.value.retry_after == 52.0

src/exo/master/main.py

@@ -365,6 +365,7 @@ class Master:
                                 self.state.node_memory,
                                 self.state.node_network,
                                 download_status=self.state.downloads,
+                                node_rdma_ctl=self.state.node_rdma_ctl,
                             )
                             transition_events = get_transition_events(
                                 self.state.instances, placement, self.state.tasks
@@ -439,9 +440,7 @@ class Master:
                                 InstanceLinkDeleted(link_id=command.link_id)
                             )
                         case RequestEventLog():
-                            # We should just be able to send everything, since other buffers will ignore old messages
-                            # rate limit to 1000 at a time
-                            end = min(command.since_idx + 1000, len(self._event_log))
+                            end = len(self._event_log)
                             for i, event in enumerate(
                                 self._event_log.read_range(command.since_idx, end),
                                 start=command.since_idx,

src/exo/master/placement.py

@@ -28,7 +28,7 @@ from exo.shared.types.events import (
     TaskStatusUpdated,
 )
 from exo.shared.types.memory import Memory
-from exo.shared.types.profiling import MemoryUsage, NodeNetworkInfo
+from exo.shared.types.profiling import MemoryUsage, NodeNetworkInfo, NodeRdmaCtlStatus
 from exo.shared.types.tasks import Task, TaskId, TaskStatus
 from exo.shared.types.worker.downloads import (
     DownloadCompleted,
@@ -105,6 +105,7 @@ def place_instance(
     node_network: Mapping[NodeId, NodeNetworkInfo],
     required_nodes: set[NodeId] | None = None,
     download_status: Mapping[NodeId, Sequence[DownloadProgress]] | None = None,
+    node_rdma_ctl: Mapping[NodeId, NodeRdmaCtlStatus] | None = None,
 ) -> dict[InstanceId, Instance]:
     cycles = topology.get_cycles()
     candidate_cycles = list(filter(lambda it: len(it) >= command.min_nodes, cycles))
@@ -166,8 +167,18 @@ def place_instance(
 
     smallest_cycles = get_smallest_cycles(cycles_with_sufficient_memory)
 
+    rdma_ctl_status = node_rdma_ctl or {}
+
+    def _all_rdma_ctl_enabled(cycle: Cycle) -> bool:
+        return all(
+            ((status := rdma_ctl_status.get(node_id)) is not None and status.enabled)
+            for node_id in cycle
+        )
+
     smallest_rdma_cycles = [
-        cycle for cycle in smallest_cycles if topology.is_rdma_cycle(cycle)
+        cycle
+        for cycle in smallest_cycles
+        if topology.is_rdma_cycle(cycle) and _all_rdma_ctl_enabled(cycle)
     ]
 
     if command.instance_meta == InstanceMeta.MlxJaccl:

src/exo/master/tests/test_placement.py

@@ -21,7 +21,11 @@ from exo.shared.types.events import (
 )
 from exo.shared.types.memory import Memory
 from exo.shared.types.multiaddr import Multiaddr
-from exo.shared.types.profiling import NetworkInterfaceInfo, NodeNetworkInfo
+from exo.shared.types.profiling import (
+    NetworkInterfaceInfo,
+    NodeNetworkInfo,
+    NodeRdmaCtlStatus,
+)
 from exo.shared.types.tasks import TaskId, TaskStatus, TextGeneration
 from exo.shared.types.text_generation import (
     InputMessage,
@@ -439,8 +443,21 @@ def test_tensor_rdma_backend_connectivity_matrix(
         min_nodes=1,
     )
 
+    node_rdma_ctl = {
+        node_a: NodeRdmaCtlStatus(enabled=True),
+        node_b: NodeRdmaCtlStatus(enabled=True),
+        node_c: NodeRdmaCtlStatus(enabled=True),
+    }
+
     # act
-    placements = place_instance(cic, topology, {}, node_memory, node_network)
+    placements = place_instance(
+        cic,
+        topology,
+        {},
+        node_memory,
+        node_network,
+        node_rdma_ctl=node_rdma_ctl,
+    )
 
     # assert
     assert len(placements) == 1
@@ -482,6 +499,131 @@ def test_tensor_rdma_backend_connectivity_matrix(
             assert len(ip_part.split(".")) == 4
 
 
+def _build_three_node_rdma_topology() -> tuple[
+    Topology, NodeId, NodeId, NodeId, dict[NodeId, NodeNetworkInfo]
+]:
+    topology = Topology()
+    node_a = NodeId()
+    node_b = NodeId()
+    node_c = NodeId()
+
+    ethernet_interface = NetworkInterfaceInfo(name="en0", ip_address="10.0.0.1")
+    ethernet_conn = SocketConnection(
+        sink_multiaddr=Multiaddr(address="/ip4/10.0.0.1/tcp/8000")
+    )
+    node_network = {
+        node_a: NodeNetworkInfo(interfaces=[ethernet_interface]),
+        node_b: NodeNetworkInfo(interfaces=[ethernet_interface]),
+        node_c: NodeNetworkInfo(interfaces=[ethernet_interface]),
+    }
+
+    for n in (node_a, node_b, node_c):
+        topology.add_node(n)
+
+    rdma_pairs = [
+        (node_a, node_b, 3),
+        (node_b, node_a, 3),
+        (node_b, node_c, 4),
+        (node_c, node_b, 4),
+        (node_a, node_c, 5),
+        (node_c, node_a, 5),
+    ]
+    for src, sink, iface in rdma_pairs:
+        topology.add_connection(
+            Connection(source=src, sink=sink, edge=create_rdma_connection(iface))
+        )
+
+    socket_pairs = [
+        (node_a, node_b),
+        (node_b, node_c),
+        (node_c, node_a),
+        (node_a, node_c),
+        (node_b, node_a),
+        (node_c, node_b),
+    ]
+    for src, sink in socket_pairs:
+        topology.add_connection(Connection(source=src, sink=sink, edge=ethernet_conn))
+
+    return topology, node_a, node_b, node_c, node_network
+
+
+def test_place_mlx_jaccl_rejects_when_a_node_has_rdma_ctl_disabled(
+    model_card: ModelCard,
+):
+    # arrange
+    model_card = model_card.model_copy(
+        update={"n_layers": 12, "storage_size": Memory.from_bytes(1500)}
+    )
+    topology, node_a, node_b, node_c, node_network = _build_three_node_rdma_topology()
+    node_memory = {
+        node_a: create_node_memory(500),
+        node_b: create_node_memory(500),
+        node_c: create_node_memory(500),
+    }
+    node_rdma_ctl = {
+        node_a: NodeRdmaCtlStatus(enabled=True),
+        node_b: NodeRdmaCtlStatus(enabled=True),
+        node_c: NodeRdmaCtlStatus(enabled=False),
+    }
+    cic = PlaceInstance(
+        sharding=Sharding.Tensor,
+        instance_meta=InstanceMeta.MlxJaccl,
+        command_id=CommandId(),
+        model_card=model_card,
+        min_nodes=3,
+    )
+
+    # act / assert
+    with pytest.raises(
+        ValueError, match="Requested RDMA \\(MlxJaccl\\) but no RDMA-connected cycles"
+    ):
+        place_instance(
+            cic,
+            topology,
+            {},
+            node_memory,
+            node_network,
+            node_rdma_ctl=node_rdma_ctl,
+        )
+
+
+def test_place_mlx_jaccl_rejects_when_node_rdma_ctl_missing(model_card: ModelCard):
+    """A node with no observed rdma_ctl status must not participate in RDMA placement."""
+    # arrange
+    model_card = model_card.model_copy(
+        update={"n_layers": 12, "storage_size": Memory.from_bytes(1500)}
+    )
+    topology, node_a, node_b, node_c, node_network = _build_three_node_rdma_topology()
+    node_memory = {
+        node_a: create_node_memory(500),
+        node_b: create_node_memory(500),
+        node_c: create_node_memory(500),
+    }
+    # node_c has no rdma_ctl entry at all
+    node_rdma_ctl = {
+        node_a: NodeRdmaCtlStatus(enabled=True),
+        node_b: NodeRdmaCtlStatus(enabled=True),
+    }
+    cic = PlaceInstance(
+        sharding=Sharding.Tensor,
+        instance_meta=InstanceMeta.MlxJaccl,
+        command_id=CommandId(),
+        model_card=model_card,
+        min_nodes=3,
+    )
+
+    # act / assert
+    with pytest.raises(ValueError):
+        place_instance(
+            cic,
+            topology,
+            {},
+            node_memory,
+            node_network,
+            node_rdma_ctl=node_rdma_ctl,
+        )
+
+
 def _make_task(
     instance_id: InstanceId,
     status: TaskStatus = TaskStatus.Running,

src/exo/routing/connection_message.py

@@ -1,15 +1,13 @@
 from exo_pyo3_bindings import PyFromSwarm
 
-from exo.shared.types.common import NodeId
 from exo.utils.pydantic_ext import FrozenModel
 
 """Serialisable types for Connection Updates/Messages"""
 
 
 class ConnectionMessage(FrozenModel):
-    node_id: NodeId
     connected: bool
 
     @classmethod
     def from_update(cls, update: PyFromSwarm.Connection) -> "ConnectionMessage":
-        return cls(node_id=NodeId(update.peer_id), connected=update.connected)
+        return cls(connected=update.connected)

src/exo/routing/router.py

@@ -13,11 +13,8 @@ from anyio import (
     sleep_forever,
 )
 from exo_pyo3_bindings import (
-    AllQueuesFullError,
     Keypair,
-    MessageTooLargeError,
     NetworkingHandle,
-    NoPeersSubscribedToTopicError,
     PyFromSwarm,
 )
 from filelock import FileLock
@@ -191,9 +188,9 @@ class Router:
                 from_swarm = await self._net.recv()
                 logger.debug(from_swarm)
                 match from_swarm:
-                    case PyFromSwarm.Message(origin, topic, data):
+                    case PyFromSwarm.Message(topic, data):
                         logger.trace(
-                            f"Received message on {topic} from {origin} with payload {data}"
+                            f"Received message on {topic} with payload {data}"
                         )
                         if topic not in self.topic_routers:
                             logger.warning(
@@ -225,21 +222,12 @@ class Router:
     async def _networking_publish(self):
         with self.networking_receiver as networked_items:
             async for topic, data in networked_items:
-                try:
-                    logger.trace(f"Sending message on {topic} with payload {data}")
-                    if len(data) > 1024 * 1024:
-                        logger.warning(
-                            "Sending overlarge payload, network performance may be temporarily degraded"
-                        )
-                    await self._net.gossipsub_publish(topic, data)
-                except NoPeersSubscribedToTopicError:
-                    pass
-                except AllQueuesFullError:
-                    logger.warning(f"All peer queues full, dropping message on {topic}")
-                except MessageTooLargeError:
+                logger.trace(f"Sending message on {topic} with payload {data}")
+                if len(data) > 1024 * 1024:
                     logger.warning(
-                        f"Message too large for gossipsub on {topic} ({len(data)} bytes), dropping"
+                        "Sending overlarge payload, network performance may be temporarily degraded"
                     )
+                await self._net.gossipsub_publish(topic, data)
 
 
 def get_node_id_keypair(

src/exo/shared/apply.py

@@ -4,7 +4,8 @@ from datetime import datetime
 
 from loguru import logger
 
-from exo.shared.types.common import NodeId
+from exo.shared.models.model_cards import ModelCard
+from exo.shared.types.common import ModelId, NodeId
 from exo.shared.types.events import (
     ChunkGenerated,
     CustomModelCardAdded,
@@ -65,6 +66,18 @@ from exo.utils.info_gatherer.info_gatherer import (
 )
 
 
+def _is_rdma_ctl_enabled(
+    node_id: NodeId, node_rdma_ctl: Mapping[NodeId, NodeRdmaCtlStatus]
+) -> bool:
+    """A node is RDMA-capable only if rdma_ctl status has been observed as enabled.
+
+    Missing entries default to ``False`` — if we have not yet observed (or the node
+    cannot run) ``rdma_ctl``, it must not participate in an RDMA-backed instance.
+    """
+    status = node_rdma_ctl.get(node_id)
+    return status is not None and status.enabled
+
+
 def event_apply(event: Event, state: State) -> State:
     """Apply an event to state."""
     match event:
@@ -75,10 +88,12 @@ def event_apply(event: Event, state: State) -> State:
             | InputChunkReceived()
             | TracesCollected()
             | TracesMerged()
-            | CustomModelCardAdded()
-            | CustomModelCardDeleted()
         ):  # Pass-through events that don't modify state
             return state
+        case CustomModelCardAdded():
+            return apply_custom_model_card_added(event, state)
+        case CustomModelCardDeleted():
+            return apply_custom_model_card_deleted(event, state)
         case InstanceCreated():
             return apply_instance_created(event, state)
         case InstanceDeleted():
@@ -397,6 +412,9 @@ def apply_node_gathered_info(event: NodeGatheredInfo, state: State) -> State:
                 for nid in state.node_thunderbolt
                 for tb_ident in state.node_thunderbolt[nid].interfaces
             }
+            source_is_rdma_enabled = _is_rdma_ctl_enabled(
+                event.node_id, state.node_rdma_ctl
+            )
             as_rdma_conns = [
                 Connection(
                     source=event.node_id,
@@ -409,6 +427,10 @@ def apply_node_gathered_info(event: NodeGatheredInfo, state: State) -> State:
                 for tb_conn in info.conns
                 if tb_conn.source_uuid in conn_map
                 if tb_conn.sink_uuid in conn_map
+                if source_is_rdma_enabled
+                and _is_rdma_ctl_enabled(
+                    conn_map[tb_conn.sink_uuid][0], state.node_rdma_ctl
+                )
             ]
             topology.replace_all_out_rdma_connections(event.node_id, as_rdma_conns)
         case ThunderboltBridgeInfo():
@@ -432,6 +454,12 @@ def apply_node_gathered_info(event: NodeGatheredInfo, state: State) -> State:
                 **state.node_rdma_ctl,
                 event.node_id: NodeRdmaCtlStatus(enabled=info.enabled),
             }
+            # If RDMA just got disabled on this node, drop any RDMA edges touching it
+            # so placement / topology consumers cannot pick a disabled node for an
+            # RDMA-backed instance. (Edges will repopulate on the next
+            # MacThunderboltConnections poll once both endpoints are enabled again.)
+            if not info.enabled:
+                topology.remove_all_rdma_connections_touching(event.node_id)
 
     return state.model_copy(update=update)
 
@@ -447,3 +475,22 @@ def apply_topology_edge_deleted(event: TopologyEdgeDeleted, state: State) -> Sta
     topology.remove_connection(event.conn)
     # TODO: Clean up removing the reverse connection
     return state.model_copy(update={"topology": topology})
+
+
+def apply_custom_model_card_added(event: CustomModelCardAdded, state: State) -> State:
+    new_cards: Mapping[ModelId, ModelCard] = {
+        **state.custom_model_cards,
+        event.model_card.model_id: event.model_card,
+    }
+    return state.model_copy(update={"custom_model_cards": new_cards})
+
+
+def apply_custom_model_card_deleted(
+    event: CustomModelCardDeleted, state: State
+) -> State:
+    new_cards: Mapping[ModelId, ModelCard] = {
+        model_id: card
+        for model_id, card in state.custom_model_cards.items()
+        if model_id != event.model_id
+    }
+    return state.model_copy(update={"custom_model_cards": new_cards})

src/exo/shared/logging.py

@@ -46,7 +46,8 @@ class _InterceptHandler(logging.Handler):
 def logger_setup(log_file: Path | None, verbosity: int = 0):
     """Set up logging for this process - formatting, file handles, verbosity and output"""
 
-    logging.getLogger("exo_pyo3_bindings").setLevel(logging.WARNING)
+    logging.getLogger("exo_net").setLevel(logging.INFO)
+    logging.getLogger("networking").setLevel(logging.INFO)
     logging.getLogger("httpx").setLevel(logging.WARNING)
     logging.getLogger("httpcore").setLevel(logging.WARNING)
 

src/exo/shared/models/model_cards.py

@@ -39,7 +39,57 @@ _BUILTIN_CARD_DIRS = [
     Path(RESOURCES_DIR) / "image_model_cards",
 ]
 
-_card_cache: dict[ModelId, "ModelCard"] = {}
+
+class _CardCache:
+    def __init__(self):
+        self.cc: dict[ModelId, "ModelCard"] = {}
+
+    def get(self, model_id: ModelId) -> "ModelCard | None":
+        return self.cc.get(model_id)
+
+    async def save(self, card: "ModelCard"):
+        self.cc[card.model_id] = card
+        try:
+            await card.save_to_custom_dir()
+        except OSError as e:
+            logger.warning(f"failed to save custom model card ({e.strerror})")
+
+    async def pop(self, model_id: ModelId) -> "ModelCard | None":
+        """Delete a user-added custom model card. Returns True if deleted."""
+        card_path = _custom_cards_dir / (ModelId(model_id).normalize() + ".toml")
+        try:
+            if await card_path.exists():
+                await card_path.unlink()
+                return self.cc.pop(model_id, None)
+        except OSError as e:
+            logger.warning(f"failed to delete custom model card ({e.strerror})")
+
+    async def list_all(self) -> list["ModelCard"]:
+        if len(self.cc) == 0:
+            await self.refresh()
+        if EXO_ENABLE_IMAGE_MODELS:
+            return list(self.cc.values())
+        return [c for c in self.cc.values() if not _is_image_card(c)]
+
+    async def _load_cards_from_dir(self, directory: Path, *, is_custom: bool) -> None:
+        """Load all TOML model cards from a directory into the cache."""
+        async for toml_file in directory.rglob("*.toml"):
+            try:
+                card = await ModelCard.load_from_path(toml_file)
+                if is_custom:
+                    card = card.model_copy(update={"is_custom": True})
+                if self.get(card.model_id) is None:
+                    self.cc[card.model_id] = card
+            except (ValidationError, TOMLKitError):
+                pass
+
+    async def refresh(self) -> None:
+        for path in _BUILTIN_CARD_DIRS:
+            await self._load_cards_from_dir(path, is_custom=False)
+        await self._load_cards_from_dir(_custom_cards_dir, is_custom=True)
+
+
+card_cache = _CardCache()
 
 
 def detect_vision_from_config(model_id: ModelId) -> "VisionCardConfig | None":
@@ -59,42 +109,10 @@ def detect_vision_from_config(model_id: ModelId) -> "VisionCardConfig | None":
     return None
 
 
-async def _load_cards_from_dir(directory: Path, *, is_custom: bool) -> None:
-    """Load all TOML model cards from a directory into the cache."""
-    async for toml_file in directory.rglob("*.toml"):
-        try:
-            card = await ModelCard.load_from_path(toml_file)
-            if is_custom:
-                card = card.model_copy(update={"is_custom": True})
-            if card.model_id not in _card_cache:
-                _card_cache[card.model_id] = card
-        except (ValidationError, TOMLKitError):
-            pass
-
-
-async def _refresh_card_cache() -> None:
-    for path in _BUILTIN_CARD_DIRS:
-        await _load_cards_from_dir(path, is_custom=False)
-    await _load_cards_from_dir(_custom_cards_dir, is_custom=True)
-
-
 def _is_image_card(card: "ModelCard") -> bool:
     return any(t in (ModelTask.TextToImage, ModelTask.ImageToImage) for t in card.tasks)
 
 
-def get_card(model_id: ModelId) -> "ModelCard | None":
-    """Look up a single model card from the cache by ID."""
-    return _card_cache.get(model_id)
-
-
-async def get_model_cards() -> list["ModelCard"]:
-    if len(_card_cache) == 0:
-        await _refresh_card_cache()
-    if EXO_ENABLE_IMAGE_MODELS:
-        return list(_card_cache.values())
-    return [c for c in _card_cache.values() if not _is_image_card(c)]
-
-
 class ModelTask(str, Enum):
     TextGeneration = "TextGeneration"
     TextToImage = "TextToImage"
@@ -196,14 +214,13 @@ class ModelCard(FrozenModel):
     # Is it okay that model card.load defaults to network access if the card doesn't exist? do we want to be more explicit here?
     @staticmethod
     async def load(model_id: ModelId) -> "ModelCard":
-        if model_id not in _card_cache:
-            await _refresh_card_cache()
-        if (mc := _card_cache.get(model_id)) is not None:
+        if card_cache.get(model_id) is None:
+            await card_cache.refresh()
+        if (mc := card_cache.get(model_id)) is not None:
             return mc
 
         mc = await ModelCard.fetch_from_hf(model_id)
         await mc.save_to_custom_dir()
-        _card_cache[model_id] = mc
         return mc
 
     @staticmethod
@@ -233,21 +250,6 @@ class ModelCard(FrozenModel):
         )
 
 
-def add_to_card_cache(card: "ModelCard") -> None:
-    """Add or update a model card in the in-memory cache."""
-    _card_cache[card.model_id] = card
-
-
-async def delete_custom_card(model_id: ModelId) -> bool:
-    """Delete a user-added custom model card. Returns True if deleted."""
-    card_path = _custom_cards_dir / (ModelId(model_id).normalize() + ".toml")
-    if await card_path.exists():
-        await card_path.unlink()
-        _card_cache.pop(model_id, None)
-        return True
-    return False
-
-
 class ConfigData(BaseModel):
     model_config = {"extra": "ignore"}  # Allow unknown fields
 

src/exo/shared/tests/test_apply/test_apply_custom_model_cards.py

@@ -0,0 +1,44 @@
+from exo.shared.apply import apply
+from exo.shared.models.model_cards import ModelCard, ModelTask
+from exo.shared.types.common import ModelId
+from exo.shared.types.events import (
+    CustomModelCardAdded,
+    CustomModelCardDeleted,
+    IndexedEvent,
+)
+from exo.shared.types.memory import Memory
+from exo.shared.types.state import State
+
+
+def _model_card(model_id: ModelId) -> ModelCard:
+    return ModelCard(
+        model_id=model_id,
+        n_layers=1,
+        storage_size=Memory.from_bytes(1),
+        hidden_size=1,
+        supports_tensor=True,
+        tasks=[ModelTask.TextGeneration],
+    )
+
+
+def test_custom_model_card_added_is_reduced_into_state() -> None:
+    card = _model_card(ModelId("custom/model"))
+
+    state = apply(
+        State(),
+        IndexedEvent(idx=0, event=CustomModelCardAdded(model_card=card)),
+    )
+
+    assert state.custom_model_cards == {card.model_id: card}
+
+
+def test_custom_model_card_deleted_removes_card_from_state() -> None:
+    card = _model_card(ModelId("custom/model"))
+    state = State(custom_model_cards={card.model_id: card}, last_event_applied_idx=0)
+
+    state = apply(
+        state,
+        IndexedEvent(idx=1, event=CustomModelCardDeleted(model_id=card.model_id)),
+    )
+
+    assert state.custom_model_cards == {}

src/exo/shared/tests/test_apply/test_apply_rdma_gating.py

@@ -0,0 +1,231 @@
+from datetime import datetime, timezone
+
+from exo.shared.apply import apply_node_gathered_info
+from exo.shared.topology import Topology
+from exo.shared.types.common import NodeId
+from exo.shared.types.events import NodeGatheredInfo
+from exo.shared.types.profiling import (
+    NodeRdmaCtlStatus,
+    NodeThunderboltInfo,
+)
+from exo.shared.types.state import State
+from exo.shared.types.thunderbolt import ThunderboltConnection, ThunderboltIdentifier
+from exo.shared.types.topology import RDMAConnection
+from exo.utils.info_gatherer.info_gatherer import (
+    MacThunderboltConnections,
+    RdmaCtlStatus,
+)
+
+
+def _now() -> str:
+    return datetime.now(timezone.utc).isoformat()
+
+
+def _make_state_with_thunderbolt_idents(
+    *node_ids_and_uuids: tuple[NodeId, str, str],
+    rdma_ctl: dict[NodeId, NodeRdmaCtlStatus] | None = None,
+) -> State:
+    """Build a State with Thunderbolt identifiers per node so the apply MacThunderboltConnections
+    case can resolve uuid -> (node, iface)."""
+    node_thunderbolt = {
+        nid: NodeThunderboltInfo(
+            interfaces=[ThunderboltIdentifier(rdma_interface=iface, domain_uuid=uuid)]
+        )
+        for nid, uuid, iface in node_ids_and_uuids
+    }
+    return State(
+        node_thunderbolt=node_thunderbolt,
+        node_rdma_ctl=rdma_ctl or {},
+    )
+
+
+def _has_rdma_edge(topology: Topology, source: NodeId, sink: NodeId) -> bool:
+    return any(
+        isinstance(edge, RDMAConnection)
+        for edge in topology.get_all_connections_between(source, sink)
+    )
+
+
+def test_mac_thunderbolt_connections_emits_rdma_when_both_endpoints_enabled():
+    node_a = NodeId()
+    node_b = NodeId()
+    state = _make_state_with_thunderbolt_idents(
+        (node_a, "uuid-a", "rdma_en1"),
+        (node_b, "uuid-b", "rdma_en1"),
+        rdma_ctl={
+            node_a: NodeRdmaCtlStatus(enabled=True),
+            node_b: NodeRdmaCtlStatus(enabled=True),
+        },
+    )
+
+    event = NodeGatheredInfo(
+        node_id=node_a,
+        when=_now(),
+        info=MacThunderboltConnections(
+            conns=[ThunderboltConnection(source_uuid="uuid-a", sink_uuid="uuid-b")]
+        ),
+    )
+
+    new_state = apply_node_gathered_info(event, state)
+
+    assert _has_rdma_edge(new_state.topology, node_a, node_b)
+
+
+def test_mac_thunderbolt_connections_skips_rdma_when_source_rdma_ctl_disabled():
+    node_a = NodeId()
+    node_b = NodeId()
+    state = _make_state_with_thunderbolt_idents(
+        (node_a, "uuid-a", "rdma_en1"),
+        (node_b, "uuid-b", "rdma_en1"),
+        rdma_ctl={
+            node_a: NodeRdmaCtlStatus(enabled=False),
+            node_b: NodeRdmaCtlStatus(enabled=True),
+        },
+    )
+
+    event = NodeGatheredInfo(
+        node_id=node_a,
+        when=_now(),
+        info=MacThunderboltConnections(
+            conns=[ThunderboltConnection(source_uuid="uuid-a", sink_uuid="uuid-b")]
+        ),
+    )
+
+    new_state = apply_node_gathered_info(event, state)
+
+    assert not _has_rdma_edge(new_state.topology, node_a, node_b)
+
+
+def test_mac_thunderbolt_connections_skips_rdma_when_sink_rdma_ctl_disabled():
+    node_a = NodeId()
+    node_b = NodeId()
+    state = _make_state_with_thunderbolt_idents(
+        (node_a, "uuid-a", "rdma_en1"),
+        (node_b, "uuid-b", "rdma_en1"),
+        rdma_ctl={
+            node_a: NodeRdmaCtlStatus(enabled=True),
+            node_b: NodeRdmaCtlStatus(enabled=False),
+        },
+    )
+
+    event = NodeGatheredInfo(
+        node_id=node_a,
+        when=_now(),
+        info=MacThunderboltConnections(
+            conns=[ThunderboltConnection(source_uuid="uuid-a", sink_uuid="uuid-b")]
+        ),
+    )
+
+    new_state = apply_node_gathered_info(event, state)
+
+    assert not _has_rdma_edge(new_state.topology, node_a, node_b)
+
+
+def test_mac_thunderbolt_connections_skips_rdma_when_rdma_ctl_status_missing():
+    """Missing rdma_ctl status defaults to not-enabled — node is RDMA-incapable."""
+    node_a = NodeId()
+    node_b = NodeId()
+    state = _make_state_with_thunderbolt_idents(
+        (node_a, "uuid-a", "rdma_en1"),
+        (node_b, "uuid-b", "rdma_en1"),
+        rdma_ctl={
+            node_a: NodeRdmaCtlStatus(enabled=True),
+            # node_b intentionally absent
+        },
+    )
+
+    event = NodeGatheredInfo(
+        node_id=node_a,
+        when=_now(),
+        info=MacThunderboltConnections(
+            conns=[ThunderboltConnection(source_uuid="uuid-a", sink_uuid="uuid-b")]
+        ),
+    )
+
+    new_state = apply_node_gathered_info(event, state)
+
+    assert not _has_rdma_edge(new_state.topology, node_a, node_b)
+
+
+def test_rdma_ctl_status_disabled_purges_existing_rdma_edges():
+    """When a node reports rdma_ctl disabled, all RDMA edges touching it must be removed."""
+    node_a = NodeId()
+    node_b = NodeId()
+
+    # Start with both nodes RDMA-enabled and existing RDMA edges in the topology.
+    state = _make_state_with_thunderbolt_idents(
+        (node_a, "uuid-a", "rdma_en1"),
+        (node_b, "uuid-b", "rdma_en1"),
+        rdma_ctl={
+            node_a: NodeRdmaCtlStatus(enabled=True),
+            node_b: NodeRdmaCtlStatus(enabled=True),
+        },
+    )
+    state = apply_node_gathered_info(
+        NodeGatheredInfo(
+            node_id=node_a,
+            when=_now(),
+            info=MacThunderboltConnections(
+                conns=[ThunderboltConnection(source_uuid="uuid-a", sink_uuid="uuid-b")]
+            ),
+        ),
+        state,
+    )
+    state = apply_node_gathered_info(
+        NodeGatheredInfo(
+            node_id=node_b,
+            when=_now(),
+            info=MacThunderboltConnections(
+                conns=[ThunderboltConnection(source_uuid="uuid-b", sink_uuid="uuid-a")]
+            ),
+        ),
+        state,
+    )
+    assert _has_rdma_edge(state.topology, node_a, node_b)
+    assert _has_rdma_edge(state.topology, node_b, node_a)
+
+    # Now node_a flips to rdma_ctl disabled — both directions of RDMA edge must drop.
+    state = apply_node_gathered_info(
+        NodeGatheredInfo(
+            node_id=node_a, when=_now(), info=RdmaCtlStatus(enabled=False)
+        ),
+        state,
+    )
+
+    assert not _has_rdma_edge(state.topology, node_a, node_b)
+    assert not _has_rdma_edge(state.topology, node_b, node_a)
+    assert state.node_rdma_ctl[node_a].enabled is False
+
+
+def test_topology_remove_all_rdma_connections_touching_keeps_socket_edges():
+    """Purging RDMA edges for a disabled node must not affect non-RDMA edges."""
+    from exo.shared.types.multiaddr import Multiaddr
+    from exo.shared.types.topology import Connection, SocketConnection
+
+    topology = Topology()
+    node_a = NodeId()
+    node_b = NodeId()
+    topology.add_node(node_a)
+    topology.add_node(node_b)
+    topology.add_connection(
+        Connection(
+            source=node_a,
+            sink=node_b,
+            edge=RDMAConnection(
+                source_rdma_iface="rdma_en1", sink_rdma_iface="rdma_en1"
+            ),
+        )
+    )
+    socket_edge = SocketConnection(
+        sink_multiaddr=Multiaddr(address="/ip4/10.0.0.1/tcp/8000")
+    )
+    topology.add_connection(Connection(source=node_a, sink=node_b, edge=socket_edge))
+
+    topology.remove_all_rdma_connections_touching(node_a)
+
+    assert not _has_rdma_edge(topology, node_a, node_b)
+    # Socket edge survives.
+    assert any(
+        isinstance(edge, SocketConnection)
+        for edge in topology.get_all_connections_between(node_a, node_b)
+    )

src/exo/shared/tests/test_election.py

@@ -327,7 +327,7 @@ async def test_connection_message_triggers_new_round_broadcast() -> None:
             tg.start_soon(election.run)
 
             # Send any connection message object; we close quickly to cancel before result creation
-            await cm_tx.send(ConnectionMessage(node_id=NodeId(), connected=True))
+            await cm_tx.send(ConnectionMessage(connected=True))
 
             # Expect a broadcast for the new round at clock=1
             while True:

src/exo/shared/topology.py

@@ -169,6 +169,22 @@ class Topology:
         for conn in new_connections:
             self.add_connection(conn)
 
+    def remove_all_rdma_connections_touching(self, node_id: NodeId) -> None:
+        """Remove every RDMA edge incident to ``node_id`` (incoming or outgoing)."""
+        if node_id not in self._vertex_indices:
+            return
+        rx_idx = self._vertex_indices[node_id]
+        rdma_edge_idxs = [
+            edge_idx
+            for edge_idx in (
+                *self._graph.out_edge_indices(rx_idx),
+                *self._graph.in_edge_indices(rx_idx),
+            )
+            if isinstance(self._graph.get_edge_data_by_index(edge_idx), RDMAConnection)
+        ]
+        for edge_idx in rdma_edge_idxs:
+            self._graph.remove_edge_from_index(edge_idx)
+
     def remove_connection(self, conn: Connection) -> None:
         if (
             conn.source not in self._vertex_indices

src/exo/shared/types/state.py

@@ -5,8 +5,9 @@ from typing import Any, cast
 from pydantic import ConfigDict, Field, field_serializer, field_validator
 from pydantic.alias_generators import to_camel
 
+from exo.shared.models.model_cards import ModelCard
 from exo.shared.topology import Topology, TopologySnapshot
-from exo.shared.types.common import NodeId
+from exo.shared.types.common import ModelId, NodeId
 from exo.shared.types.instance_link import InstanceLink, InstanceLinkId
 from exo.shared.types.profiling import (
     DiskUsage,
@@ -65,6 +66,9 @@ class State(FrozenModel):
     instance_links: Mapping[InstanceLinkId, InstanceLink] = {}
     prefill_server_ports: Mapping[RunnerId, int] = {}
 
+    # User-added model cards. Workers can reconcile their on-disk custom card cache
+    custom_model_cards: Mapping[ModelId, ModelCard] = {}
+
     @field_serializer("topology", mode="plain")
     def _encode_topology(self, value: Topology) -> TopologySnapshot:
         return value.to_snapshot()

src/exo/shared/types/text_generation.py

@@ -135,9 +135,9 @@ class TextGenerationTaskParams(BaseModel, frozen=True):
     prefill_endpoint: str | None = None
 
     def with_card_sampling_defaults(self) -> "TextGenerationTaskParams":
-        from exo.shared.models.model_cards import get_card
+        from exo.shared.models import model_cards
 
-        card = get_card(self.model)
+        card = model_cards.card_cache.get(self.model)
         if card is None:
             return self
 

src/exo/utils/banner.py

@@ -38,7 +38,7 @@ def print_startup_banner(port: int) -> None:
 
 ╔═══════════════════════════════════════════════════════════════════════╗
 ║                                                                       ║
-║  🌐 Dashboard & API Ready                                             ║
+║  Dashboard & API Ready                                                ║
 ║                                                                       ║
 ║  {dashboard_url}{" " * (69 - len(dashboard_url))}║
 ║                                                                       ║

src/exo/worker/engines/image/builder.py

@@ -143,6 +143,7 @@ class ImageEngine(Engine):
         Generator[tuple[TaskId, Chunk | FinishedResponse | CancelledResponse]] | None
     ) = field(init=False, default=None)
     queue: deque[ImageTask] = field(init=False, default_factory=deque)
+    _cancelled_tasks: set[TaskId] = field(init=False, default_factory=set)
 
     def warmup(self) -> None:
         image = warmup_image_generator(model=self.image_model)
@@ -168,7 +169,11 @@ class ImageEngine(Engine):
             task = self.queue.popleft()
             self.current_gen = self._run_image_task(task.task_id, task.task_params)
             resp = next(self.current_gen, None)
-        return (resp,) if resp is not None else ()
+        return (
+            (resp,)
+            if resp is not None and _is_primary_output_node(self.shard_metadata)
+            else ()
+        )
 
     def close(self) -> None:
         with contextlib.suppress(NameError, AttributeError):

src/exo/worker/main.py

@@ -10,7 +10,7 @@ from exo.api.types import ImageEditsTaskParams
 from exo.download.download_utils import is_read_only_model_dir, resolve_existing_model
 from exo.shared.apply import apply
 from exo.shared.constants import EXO_MAX_INSTANCE_RETRIES
-from exo.shared.models.model_cards import ModelId, add_to_card_cache, delete_custom_card
+from exo.shared.models.model_cards import ModelId, card_cache
 from exo.shared.types.chunks import InputImageChunk
 from exo.shared.types.commands import (
     DeleteInstance,
@@ -20,8 +20,6 @@ from exo.shared.types.commands import (
 )
 from exo.shared.types.common import CommandId, NodeId, SystemId
 from exo.shared.types.events import (
-    CustomModelCardAdded,
-    CustomModelCardDeleted,
     Event,
     IndexedEvent,
     InputChunkReceived,
@@ -110,6 +108,8 @@ class Worker:
                 tg.start_soon(self.plan_step)
                 tg.start_soon(self._event_applier)
                 tg.start_soon(self._poll_connection_updates)
+                tg.start_soon(self._reconcile_custom_cards)
+
         finally:
             # Actual shutdown code - waits for all tasks to complete before executing.
             logger.info("Stopping Worker")
@@ -151,7 +151,6 @@ class Worker:
                     self.input_chunk_buffer[cmd_id][event.chunk.chunk_index] = (
                         event.chunk
                     )
-
                     if (
                         len(self.input_chunk_buffer[cmd_id])
                         == self.input_chunk_counts[cmd_id]
@@ -172,12 +171,18 @@ class Worker:
                                 )
                             ] = img
 
-                if isinstance(event, CustomModelCardAdded):
-                    await event.model_card.save_to_custom_dir()
-                    add_to_card_cache(event.model_card)
+    async def _reconcile_custom_cards(self) -> None:
+        while True:
+            await anyio.sleep(1)
+            target = dict(self.state.custom_model_cards)
+            for model_id, card in target.items():
+                if card_cache.get(model_id) == card:
+                    continue
+                await card_cache.save(card)
 
-                if isinstance(event, CustomModelCardDeleted):
-                    await delete_custom_card(event.model_id)
+            for card in await card_cache.list_all():
+                if card.model_id not in target:
+                    await card_cache.pop(card.model_id)
 
     async def plan_step(self):
         while True:

src/exo/worker/runner/llm_inference/batch_generator.py

@@ -138,8 +138,10 @@ class SequentialGenerator(Engine):
     def agree_on_tasks(self) -> None:
         """Agree between all ranks about the task ordering (some may have received in different order or not at all)."""
         agreed, different = mx_all_gather_tasks(self._maybe_queue, self.group)
-        self._queue.extend(task for task in self._maybe_queue if task in agreed)
-        self._maybe_queue = [task for task in self._maybe_queue if task in different]
+        # Extend from `agreed` (sorted by task_id on all ranks) to guarantee every
+        # rank enqueues tasks in the same order, preventing TP collective deadlocks.
+        self._queue.extend(agreed)
+        self._maybe_queue = list(different)
 
     def agree_on_cancellations(self) -> None:
         """Agree between all ranks about which tasks to cancel."""
@@ -197,9 +199,14 @@ class SequentialGenerator(Engine):
             self._active = None
             raise
 
-        return itertools.chain(
-            output,
-            map(lambda task: (task, CancelledResponse()), self._cancelled_tasks),
+        return filter(
+            lambda chunk: (
+                not isinstance(chunk[1], GenerationChunk) or self.device_rank == 0
+            ),
+            itertools.chain(
+                output,
+                map(lambda task: (task, CancelledResponse()), self._cancelled_tasks),
+            ),
         )
 
     def _start_next(self) -> None:
@@ -368,8 +375,10 @@ class BatchGenerator(Engine):
     def agree_on_tasks(self) -> None:
         """Agree between all ranks about the task ordering (some may have received in different order or not at all)."""
         agreed, different = mx_all_gather_tasks(self._maybe_queue, self.group)
-        self._queue.extend(task for task in self._maybe_queue if task in agreed)
-        self._maybe_queue = [task for task in self._maybe_queue if task in different]
+        # Extend from `agreed` (sorted by task_id on all ranks) to guarantee every
+        # rank enqueues tasks in the same order, preventing TP collective deadlocks.
+        self._queue.extend(agreed)
+        self._maybe_queue = list(different)
 
     def agree_on_cancellations(self) -> None:
         """Agree between all ranks about which tasks to cancel."""
@@ -449,7 +458,12 @@ class BatchGenerator(Engine):
                 output.append((task.task_id, FinishedResponse()))
                 del self._active_tasks[uid]
 
-        return itertools.chain(output, self._apply_cancellations())
+        return filter(
+            lambda chunk: (
+                not isinstance(chunk[1], GenerationChunk) or self.device_rank == 0
+            ),
+            itertools.chain(output, self._apply_cancellations()),
+        )
 
     def _apply_cancellations(
         self,

src/exo/worker/runner/runner.py

@@ -390,5 +390,5 @@ class Runner:
         chunk: Chunk,
         command_id: CommandId,
     ):
-        if self.device_rank == 0:
-            self.event_sender.send(ChunkGenerated(command_id=command_id, chunk=chunk))
+        assert isinstance(self.generator, Engine)
+        self.event_sender.send(ChunkGenerated(command_id=command_id, chunk=chunk))

src/exo/worker/tests/unittests/test_mlx/test_tokenizers.py

@@ -16,7 +16,7 @@ from exo.download.download_utils import (
     fetch_file_list_with_cache,
     resolve_model_dir,
 )
-from exo.shared.models.model_cards import ModelCard, ModelId, get_model_cards
+from exo.shared.models.model_cards import ModelCard, ModelId, card_cache
 from exo.worker.engines.mlx.utils_mlx import (
     get_eos_token_ids_for_model,
     load_tokenizer_for_model_id,
@@ -76,7 +76,7 @@ def get_test_models() -> list[ModelCard]:
     """Get a representative sample of models to test."""
     # Pick one model from each family to test
     families: dict[str, ModelCard] = {}
-    for card in asyncio.run(get_model_cards()):
+    for card in asyncio.run(card_cache.list_all()):
         # Extract family name (e.g., "llama-3.1" from "llama-3.1-8b")
         parts = card.model_id.short().split("-")
         family = "-".join(parts[:2]) if len(parts) >= 2 else parts[0]
@@ -298,7 +298,7 @@ async def test_tokenizer_special_tokens(model_card: ModelCard) -> None:
 async def test_kimi_tokenizer_specifically():
     """Test Kimi tokenizer with its specific patches and quirks."""
     kimi_models = [
-        card for card in await get_model_cards() if "kimi" in card.model_id.lower()
+        card for card in await card_cache.list_all() if "kimi" in card.model_id.lower()
     ]
 
     if not kimi_models:
@@ -350,7 +350,7 @@ async def test_glm_tokenizer_specifically():
 
     glm_model_cards = [
         card
-        for card in await get_model_cards()
+        for card in await card_cache.list_all()
         if contains(card, "glm")
         and not contains(card, "-5")
         and not contains(card, "4.7")

tmp/state_proxy.py

@@ -0,0 +1,13 @@
+from exo_pyo3_bindings import StateProxy
+import anyio
+
+async def main():
+    sp = await StateProxy.init()
+    while True:
+        data = await sp.snapshot()
+        if data != "{}":
+            print(data)
+        await anyio.sleep(1)
+    
+if __name__ == "__main__":
+    anyio.run(main)