Remove mx.evals

## Motivation

No automated integration tests exist for exo. Manual testing against
real hardware clusters is slow and error-prone. We need a pytest
framework that deploys clusters via `eco`, runs inference scenarios, and
tears down cleanly.

## Changes

- **`tools/src/exo_tools/`** — New workspace member shared by bench,
eval, and tests:
- `client.py` — `ExoClient` HTTP client (extracted from
`bench/harness.py`)
- `harness.py` — instance lifecycle helpers (placement, wait-for-ready,
etc.)
- `cluster.py` — `EcoSession` for eco cluster lifecycle
(deploy/stop/start/release/logs/exec) with unique `USER=<prefix>-<uuid>`
per session and atexit/signal cleanup
- **`tests/integration/`** — 17 pytest tests across 5 files:
- `test_1node.py` — place, chat, multi-turn, delete, state/models
endpoints, cluster snapshot, download-from-scratch
- `test_2node.py` — parametrized tensor/jaccl + pipeline/ring inference
and multi-turn
- `test_4node.py` — parametrized 4-node pipeline/ring inference, cluster
state
- `test_resilience.py` — full disconnect/reconnect cycle (2-node →
disconnect → 1-node → reconnect → 2-node)
- `test_dashboard.py` — Playwright: dashboard loads, shows node info,
chat flow
- `helpers.py` — placement/inference helpers, re-exports from
`exo_tools`
- `conftest.py` — session-scoped cluster fixtures with constraint-based
eco reservations; `--hosts` override; `EXO_REF` env var for CI
deployments from a GitHub branch
- **`bench/`** — Updated imports from `exo_tools.client` /
`exo_tools.harness`
- **`pyproject.toml`** — Added `tools` workspace member, `playwright`
dev dep, `--ignore=tests/integration`

## Why It Works

Tests use `eco` for cluster lifecycle and `ExoClient` for API
interactions — same tools humans use. Session-scoped fixtures deploy
once per file. Unique eco users prevent test runs from interfering with
each other or manual usage.

## Test Plan

### Automated Testing

- `uv run pytest tests/integration/ -v -s` — full suite (~4-5 min, 17/17
passing)
- `uv run pytest tests/integration/ -v -s --hosts s4,s9,s10,s22` — pin
specific hosts
- `EXO_REF=main uv run pytest tests/integration/ -v` — deploy from a
GitHub branch (CI)
- `uv run pytest` — confirms integration tests are excluded from default
runs

.gitignore

@@ -40,3 +40,4 @@ bench/**/*.json
 tmp/models
 /build/exo
 /.claude/skills
+/.claude

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"

bench/eval_tool_calls.py

@@ -15,9 +15,8 @@ from pathlib import Path
 from typing import Any, Literal
 
 import httpx
-from harness import (
-    ExoClient,
-    ExoHttpError,
+from exo_tools.client import ExoClient, ExoHttpError
+from exo_tools.harness import (
     add_common_instance_args,
     capture_cluster_snapshot,
     instance_id_from_instance,

bench/exo_bench.py

@@ -30,9 +30,8 @@ from pathlib import Path
 from statistics import mean
 from typing import Any
 
-from harness import (
-    ExoClient,
-    ExoHttpError,
+from exo_tools.client import ExoClient, ExoHttpError
+from exo_tools.harness import (
     add_common_instance_args,
     capture_cluster_snapshot,
     find_existing_instance,

bench/exo_eval.py

@@ -42,9 +42,8 @@ from pathlib import Path
 from typing import Any
 
 import httpx
-from harness import (
-    ExoClient,
-    ExoHttpError,
+from exo_tools.client import ExoClient, ExoHttpError
+from exo_tools.harness import (
     add_common_instance_args,
     capture_cluster_snapshot,
     find_existing_instance,

bench/prefill_decode_bench.py

@@ -35,9 +35,8 @@ from exo_bench import (
     load_tokenizer_for_bench,
     parse_int_list,
 )
-from harness import (
-    ExoClient,
-    ExoHttpError,
+from exo_tools.client import ExoClient, ExoHttpError
+from exo_tools.harness import (
     add_common_instance_args,
     instance_id_from_instance,
     node_ids_from_instance,

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

pyproject.toml

@@ -40,6 +40,7 @@ exo = "exo.main:main"
 dev = [
   "basedpyright>=1.29.0",
   "pyinstaller>=6.17.0",
+  "playwright>=1.52.0",
   "pytest>=8.4.0",
   "pytest-asyncio>=1.0.0",
   "pytest-env",
@@ -75,11 +76,11 @@ cuda13 = [
 ###
 
 [tool.uv.workspace]
-members = ["rust/exo_pyo3_bindings", "bench"]
+members = ["rust/exo_pyo3_bindings", "bench", "tools"]
 
 [tool.uv.sources]
 exo-pyo3-bindings = { workspace = true }
-mlx = { git = "https://github.com/rltakashige/mlx-jaccl-fix-small-recv.git", branch = "address-rdma-gpu-locks", marker = "sys_platform == 'darwin'" }
+mlx = { git = "https://github.com/rltakashige/mlx-jaccl-fix-small-recv.git", branch = "leo/order-distributed-ops", marker = "sys_platform == 'darwin'" }
 mlx-lm = { git = "https://github.com/rltakashige/mlx-lm", branch = "leo/deepseek-v4" }
 torch = [
   { index = "pytorch-cu130", marker = "sys_platform == 'linux' and extra == 'cuda13' and extra != 'cpu' and extra != 'cuda12'" },
@@ -112,7 +113,7 @@ build-backend = "uv_build"
 ###
 
 [tool.basedpyright]
-include = ["src", "bench"]
+include = ["src", "bench", "tools"]
 typeCheckingMode = "strict"
 failOnWarnings = true
 
@@ -146,6 +147,13 @@ reportMissingModuleSource = false
 [[tool.basedpyright.executionEnvironments]]
 root = "src"
 
+[[tool.basedpyright.executionEnvironments]]
+root = "bench"
+extraPaths = ["tools/src"]
+
+[[tool.basedpyright.executionEnvironments]]
+root = "tools/src"
+
 
 ###
 # uv configuration
@@ -220,5 +228,5 @@ pythonpath = "."
 asyncio_mode = "auto"
 markers = ["slow: marks tests as slow (deselected by default)"]
 env = ["EXO_TESTS=1"]
-addopts = "-m 'not slow' --ignore=tests/start_distributed_test.py"
+addopts = "-m 'not slow' --ignore=tests"
 filterwarnings = ["ignore:builtin type Swig:DeprecationWarning"]

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

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/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/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/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/power_sampler.py

@@ -19,19 +19,21 @@ class PowerSampler:
     ):
         self._get_node_system = get_node_system
         self._interval = interval
-        self._samples: defaultdict[NodeId, list[SystemPerformanceProfile]] = (
-            defaultdict(list)
-        )
+        self._samples: defaultdict[
+            NodeId, list[tuple[float, SystemPerformanceProfile]]
+        ] = defaultdict(list)
         self._start_time: float | None = None
         self._stopped = False
 
-    def _take_sample(self) -> None:
+    def _take_sample(self, t_rel: float | None = None) -> None:
+        assert self._start_time is not None
+        ts = t_rel if t_rel is not None else time.perf_counter() - self._start_time
         for node_id, profile in self._get_node_system().items():
-            self._samples[node_id].append(profile)
+            self._samples[node_id].append((ts, profile))
 
     async def run(self) -> None:
         self._start_time = time.perf_counter()
-        self._take_sample()
+        self._take_sample(t_rel=0.0)
         while not self._stopped:
             await anyio.sleep(self._interval)
             self._take_sample()
@@ -39,26 +41,51 @@ class PowerSampler:
     def result(self) -> PowerUsage:
         self._stopped = True
         assert self._start_time is not None, "result() called before run()"
-        self._take_sample()
         elapsed = time.perf_counter() - self._start_time
+        self._take_sample(t_rel=elapsed)
 
         node_stats: list[NodePowerStats] = []
-        for node_id, profiles in self._samples.items():
-            n = len(profiles)
+        total_energy_j = 0.0
+        for node_id, ts_profiles in self._samples.items():
+            n = len(ts_profiles)
             if n == 0:
                 continue
+            node_energy_j = trapezoidal_energy(ts_profiles, elapsed)
+            avg_power_w = node_energy_j / elapsed if elapsed > 0 else 0.0
+            total_energy_j += node_energy_j
             node_stats.append(
                 NodePowerStats(
                     node_id=node_id,
                     samples=n,
-                    avg_sys_power=sum(p.sys_power for p in profiles) / n,
+                    avg_sys_power=avg_power_w,
                 )
             )
 
-        total_avg_sys = sum(ns.avg_sys_power for ns in node_stats)
+        total_avg_sys_w = total_energy_j / elapsed if elapsed > 0 else 0.0
         return PowerUsage(
             elapsed_seconds=elapsed,
             nodes=node_stats,
-            total_avg_sys_power_watts=total_avg_sys,
-            total_energy_joules=total_avg_sys * elapsed,
+            total_avg_sys_power_watts=total_avg_sys_w,
+            total_energy_joules=total_energy_j,
         )
+
+
+def trapezoidal_energy(
+    ts_profiles: list[tuple[float, SystemPerformanceProfile]],
+    elapsed: float,
+) -> float:
+    """Integrate sys_power(t) over the sample window using the trapezoidal rule.
+    First sample is anchored at t=0 and last at t=elapsed (set by `run` /
+    `result`), so the integral spans the full request interval. Falls back to
+    power * elapsed when only one sample exists (constant-power assumption)."""
+    if len(ts_profiles) == 1:
+        return ts_profiles[0][1].sys_power * elapsed
+    energy_j = 0.0
+    for i in range(1, len(ts_profiles)):
+        t_prev, p_prev = ts_profiles[i - 1]
+        t_cur, p_cur = ts_profiles[i]
+        dt = t_cur - t_prev
+        if dt <= 0:
+            continue
+        energy_j += (p_prev.sys_power + p_cur.sys_power) / 2.0 * dt
+    return energy_j

src/exo/utils/tests/test_power_sampler.py

@@ -111,6 +111,36 @@ async def test_empty_state() -> None:
     assert result.total_energy_joules == 0.0
 
 
+def test_trapezoidal_unit_dt_weighting() -> None:
+    """Pure unit test on the integration helper. Crafted samples where the
+    arithmetic mean is wildly wrong vs the time-weighted result."""
+    from exo.utils.power_sampler import trapezoidal_energy
+
+    # 5 s window. Power = 10 W for the first 4.9 s, then 100 W for the last 0.1 s.
+    # Three samples: t=0 W=10, t=4.9 W=10, t=5.0 W=100.
+    samples = [
+        (0.0, _make_profile(10.0)),
+        (4.9, _make_profile(10.0)),
+        (5.0, _make_profile(100.0)),
+    ]
+    energy = trapezoidal_energy(samples, elapsed=5.0)
+    # (10+10)/2 * 4.9 + (10+100)/2 * 0.1 = 49 + 5.5 = 54.5 J
+    assert abs(energy - 54.5) < 1e-9
+    avg = energy / 5.0  # 10.9 W
+    # Arithmetic mean of the three samples would be (10+10+100)/3 ≈ 40 W.
+    # Trapezoidal correctly weights each segment by its dt.
+    assert abs(avg - 10.9) < 1e-9
+
+
+def test_trapezoidal_unit_single_sample() -> None:
+    """One sample: no window to integrate over, so fall back to constant power
+    over the elapsed duration."""
+    from exo.utils.power_sampler import trapezoidal_energy
+
+    samples = [(0.0, _make_profile(42.0))]
+    assert trapezoidal_energy(samples, elapsed=3.0) == 42.0 * 3.0
+
+
 async def test_result_stops_sampling() -> None:
     """Calling result() should stop the sampler's run loop."""
     state: dict[NodeId, SystemPerformanceProfile] = {

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/engines/mlx/auto_parallel.py

@@ -133,9 +133,7 @@ class PipelineFirstLayer(CustomMlxLayer):
         if self.r != 0:
             # We want to avoid GPU timeout errors by evalling the distributed operation
             # so that it stays on CPU, which does not have a timeout.
-            mx.eval(x)
             x = mx.distributed.recv_like(x, (self.r - 1), group=self.group)
-            mx.eval(x)
         return self.original_layer(x, *args, **kwargs)
 
 
@@ -162,10 +160,6 @@ class PipelineLastLayer(CustomMlxLayer):
 
         output: mx.array = self.original_layer(x, *args, **kwargs)
 
-        # Eval layer output to materialize it before send — this splits the graph
-        # so the send is isolated and the receiving rank's recv can complete.
-        mx.eval(output)
-
         if self.r != self.s - 1:
             if self.queue_sends:
                 _pending_prefill_sends.append(
@@ -181,7 +175,6 @@ class PipelineLastLayer(CustomMlxLayer):
                 _cache = cache[0] if hasattr(cache, "caches") else cache  # type: ignore
                 if hasattr(_cache, "keys"):  # pyright: ignore[reportAny]
                     _cache.keys = mx.depends(_cache.keys, output)  # type: ignore
-            mx.eval(output)
             if cache is not None and hasattr(_cache, "keys"):  # type: ignore
                 mx.eval(_cache.keys)  # type: ignore
 
@@ -189,7 +182,6 @@ class PipelineLastLayer(CustomMlxLayer):
             output = mx.distributed.all_gather(output, group=self.group)[
                 -output.shape[0] :
             ]
-            mx.eval(output)
 
         return output
 

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")

tests/conftest.py

@@ -0,0 +1,181 @@
+# type: ignore
+"""Pytest configuration for marker-driven exo integration tests.
+
+Test authors declare requirements via markers:
+
+    @pytest.mark.cluster(count=2, thunderbolt='a2a')
+    @pytest.mark.instance('mlx-community/Llama-3.2-1B-Instruct-4bit',
+                          sharding='tensor', comm='jaccl')
+    def test_jaccl_inference(session):
+        resp = session.chat('What is 2+2?')
+        assert '4' in resp
+
+Clusters are cached by `ClusterSpec`; tests with the same cluster_spec
+share a deployment. Each test places its own instance (matching its
+`@pytest.mark.instance`), and instances are cleaned up after the test.
+
+Run with:
+    uv run pytest tests/ -v
+    uv run pytest tests/ -v --hosts s2,s4,s9,s10
+"""
+
+from __future__ import annotations
+
+import contextlib
+import json
+
+import pytest
+from exo_tools.cluster import ClusterInfo, EcoSession
+from exo_tools.harness import cleanup_all_instances, place_instance
+
+from .framework import (
+    ClusterSpec,
+    Session,
+    parse_cluster_marker,
+    parse_instance_marker,
+)
+
+# Single eco session for the entire test process.
+eco = EcoSession(user_prefix="test")
+
+# Cluster cache keyed by ClusterSpec — tests with the same spec share a deployment.
+# Cleared at session teardown.
+_cluster_cache: dict[ClusterSpec, ClusterInfo] = {}
+
+
+def pytest_addoption(parser):
+    parser.addoption(
+        "--hosts",
+        default=None,
+        help="Comma-separated list of hosts (e.g. s2,s4,s9,s10). "
+        "Overrides constraint-based reservation.",
+    )
+
+
+def pytest_configure(config):
+    """Register custom markers."""
+    config.addinivalue_line(
+        "markers",
+        "cluster(count=N, thunderbolt=Thunderbolt|None, min_memory=GB, chip=PATTERN): "
+        "declare cluster requirements for a test",
+    )
+    config.addinivalue_line(
+        "markers",
+        "instance(model_id, sharding=Sharding, comm=Comm, min_nodes=N): "
+        "declare instance placement for a test",
+    )
+
+
+def pytest_report_header(config):
+    """Show the eco user and hosts for this test session."""
+    hosts = config.getoption("--hosts")
+    lines = [f"eco user: {eco.user}"]
+    if hosts:
+        lines.append(f"hosts override: {hosts}")
+    return lines
+
+
+@pytest.fixture(scope="session")
+def _host_pool(request) -> list[str] | None:
+    raw = request.config.getoption("--hosts")
+    if raw:
+        return [h.strip() for h in raw.split(",") if h.strip()]
+    return None
+
+
+@pytest.fixture
+def session(request, _host_pool) -> Session:
+    """Per-test fixture providing a Session matching the test's markers.
+
+    Reads @pytest.mark.cluster and @pytest.mark.instance from the test, deploys
+    a matching cluster (cached across tests with the same spec), places the
+    model, and yields a Session for the test to interact with. Cleans up the
+    instance after the test, and invalidates the cluster cache if the test
+    left nodes disconnected.
+    """
+    cluster_marker = request.node.get_closest_marker("cluster")
+    instance_marker = request.node.get_closest_marker("instance")
+
+    cluster_spec = parse_cluster_marker(cluster_marker)
+    instance_spec = parse_instance_marker(instance_marker)
+
+    # Deploy or reuse a cluster matching the spec
+    cluster = _cluster_cache.get(cluster_spec)
+    if cluster is None:
+        if _host_pool:
+            cluster = eco.start_deploy(
+                hosts=_host_pool[: cluster_spec.count], wait=True
+            )
+        else:
+            cluster = eco.start_deploy(
+                count=cluster_spec.count,
+                thunderbolt=cluster_spec.thunderbolt,
+                chip=cluster_spec.chip,
+                min_memory_gb=cluster_spec.min_memory_gb,
+                wait=True,
+            )
+        _cluster_cache[cluster_spec] = cluster
+
+    # Place an instance for this test if the test specified one
+    instance_id = None
+    if instance_spec is not None:
+        client = cluster.make_client()
+        instance_id = place_instance(
+            client,
+            instance_spec.model_id,
+            sharding=instance_spec.sharding,
+            comm=instance_spec.comm,
+            min_nodes=instance_spec.min_nodes,
+        )
+
+    sess = Session(
+        cluster=cluster,
+        eco=eco,
+        instance_spec=instance_spec,
+        instance_id=instance_id,
+    )
+
+    yield sess
+
+    # ---- Teardown ----
+
+    # If the test left nodes disconnected, invalidate the cluster cache and
+    # stop the cluster so the next test deploys fresh.
+    if sess._stopped_hosts:
+        _cluster_cache.pop(cluster_spec, None)
+        with contextlib.suppress(Exception):
+            eco.stop(sess.cluster.hosts)
+        return
+
+    # Otherwise, clean up any instances created during the test
+    with contextlib.suppress(Exception):
+        cleanup_all_instances(sess.client)
+
+
+# ---------------------------------------------------------------------------
+# Session-level teardown — stop all cached clusters
+# ---------------------------------------------------------------------------
+
+
+@pytest.fixture(scope="session", autouse=True)
+def _teardown_clusters():
+    yield
+    for cluster in _cluster_cache.values():
+        with contextlib.suppress(Exception):
+            eco.stop(cluster.hosts)
+    _cluster_cache.clear()
+
+
+def pytest_runtest_makereport(item, call):
+    """Attach cluster logs to the test report when a test fails."""
+    if call.when != "call" or call.excinfo is None:
+        return
+
+    sess = item.funcargs.get("session")
+    if sess is None:
+        return
+    try:
+        logs = eco.logs(sess.cluster.hosts, lines=200)
+        item.add_report_section("call", "Cluster Logs", json.dumps(logs, indent=2))
+    except Exception:
+        pass

tests/framework.py

@@ -0,0 +1,199 @@
+"""Marker-driven test framework for exo integration tests.
+
+Test authors declare requirements via markers:
+
+    @pytest.mark.cluster(count=2, thunderbolt='a2a')
+    @pytest.mark.instance('mlx-community/Llama-3.2-1B-Instruct-4bit',
+                          sharding='tensor', comm='jaccl')
+    def test_jaccl_inference(session):
+        resp = session.chat('What is 2+2?')
+        assert '4' in resp
+
+The `session` fixture reads the markers, deploys the cluster, places the
+instance, and provides a `Session` object. All cluster/instance orchestration
+lives in `exo_tools.harness`; this module is purely the pytest-facing layer.
+"""
+
+from __future__ import annotations
+
+import time
+from dataclasses import dataclass, field
+from typing import Any
+
+from exo_tools.client import ExoClient
+from exo_tools.cluster import (
+    Chip,
+    ClusterInfo,
+    EcoSession,
+    Thunderbolt,
+    make_client_from_url,
+)
+from exo_tools.harness import Comm, Sharding
+
+from exo.api.types.api import (
+    ChatCompletionChoice,
+    ChatCompletionRequest,
+    ChatCompletionResponse,
+)
+
+DEFAULT_MODEL = "mlx-community/Llama-3.2-1B-Instruct-4bit"
+
+
+def _extract_content(resp: ChatCompletionResponse) -> str:
+    """Extract plain-text content from a non-streaming chat completion."""
+    choice = resp.choices[0]
+    if not isinstance(choice, ChatCompletionChoice):
+        raise RuntimeError(
+            f"Expected non-streaming choice, got {type(choice).__name__}"
+        )
+    content = choice.message.content
+    if not isinstance(content, str):
+        raise RuntimeError(f"Expected string content, got {type(content).__name__}")
+    return content
+
+
+@dataclass(frozen=True)
+class ClusterSpec:
+    count: int = 1
+    thunderbolt: Thunderbolt | None = None
+    min_memory_gb: float | None = None
+    chip: Chip | None = None
+
+
+@dataclass(frozen=True)
+class InstanceSpec:
+    model_id: str
+    sharding: Sharding = Sharding.PIPELINE
+    comm: Comm = Comm.RING
+    min_nodes: int = 1
+
+
+def parse_cluster_marker(marker) -> ClusterSpec:
+    if marker is None:
+        return ClusterSpec()
+    return ClusterSpec(
+        count=marker.kwargs.get("count", 1),
+        thunderbolt=marker.kwargs.get("thunderbolt"),
+        min_memory_gb=marker.kwargs.get("min_memory"),
+        chip=marker.kwargs.get("chip"),
+    )
+
+
+def parse_instance_marker(marker) -> InstanceSpec | None:
+    if marker is None:
+        return None
+    if not marker.args:
+        raise ValueError(
+            "@pytest.mark.instance requires a positional model_id argument"
+        )
+    return InstanceSpec(
+        model_id=marker.args[0],
+        sharding=marker.kwargs.get("sharding", Sharding.PIPELINE),
+        comm=marker.kwargs.get("comm", Comm.RING),
+        min_nodes=marker.kwargs.get("min_nodes", 1),
+    )
+
+
+@dataclass
+class Session:
+    cluster: ClusterInfo
+    eco: EcoSession
+    instance_spec: InstanceSpec | None = None
+    instance_id: str | None = None
+    _stopped_hosts: set[str] = field(default_factory=set)
+
+    @property
+    def client(self) -> ExoClient:
+        for host in self.cluster.hosts:
+            if host not in self._stopped_hosts:
+                return make_client_from_url(self.cluster.api_endpoints[host])
+        return self.cluster.make_client()
+
+    @property
+    def state(self) -> dict[str, Any]:
+        return self.client.request_json("GET", "/state") or {}
+
+    @property
+    def instances(self) -> dict[str, Any]:
+        return self.state.get("instances", {})
+
+    # ---- Inference ----
+
+    def chat(self, prompt: str, max_tokens: int = 100) -> str:
+        resp = self.chat_raw(prompt, max_tokens=max_tokens)
+        return _extract_content(resp)
+
+    def chat_raw(self, prompt: str, **kwargs: Any) -> ChatCompletionResponse:
+        if not self.instance_spec:
+            raise RuntimeError(
+                "No instance placed; add @pytest.mark.instance to the test"
+            )
+        max_tokens = kwargs.pop("max_tokens", 100)
+        request = ChatCompletionRequest.model_validate(
+            {
+                "model": self.instance_spec.model_id,
+                "messages": [{"role": "user", "content": prompt}],
+                "max_tokens": max_tokens,
+                **kwargs,
+            }
+        )
+        return self._post_chat(request)
+
+    def multi_turn(self, messages: list[dict[str, str]], max_tokens: int = 100) -> str:
+        if not self.instance_spec:
+            raise RuntimeError(
+                "No instance placed; add @pytest.mark.instance to the test"
+            )
+        request = ChatCompletionRequest.model_validate(
+            {
+                "model": self.instance_spec.model_id,
+                "messages": messages,
+                "max_tokens": max_tokens,
+            }
+        )
+        return _extract_content(self._post_chat(request))
+
+    def _post_chat(self, request: ChatCompletionRequest) -> ChatCompletionResponse:
+        raw = self.client.request_json(
+            "POST",
+            "/v1/chat/completions",
+            body=request.model_dump(exclude_none=True),
+        )
+        return ChatCompletionResponse.model_validate(raw)
+
+    def disconnect_node(self, index: int) -> None:
+        """Stop exo on a node and wait for the cluster to observe the disconnect."""
+        host = self.cluster.hosts[index]
+        self.eco.stop([host], keep=True)
+        self._stopped_hosts.add(host)
+
+    def reconnect_node(self, index: int) -> None:
+        """Restart a previously disconnected node into the existing namespace."""
+        host = self.cluster.hosts[index]
+        self.eco.start_hosts([host], namespace=self.cluster.namespace)
+        self._stopped_hosts.discard(host)
+
+    def wait_ready(
+        self, expected_nodes: int | None = None, timeout: float = 60
+    ) -> None:
+        """Wait until the cluster has exactly `expected_nodes` visible and reporting memory.
+
+        Defaults to the count of non-stopped hosts. Use this after
+        `disconnect_node` / `reconnect_node` to wait for the cluster to settle.
+        """
+        if expected_nodes is None:
+            expected_nodes = len(self.cluster.hosts) - len(self._stopped_hosts)
+        start = time.time()
+        while time.time() - start < timeout:
+            try:
+                state = self.state
+                identities = len(state.get("nodeIdentities", {}))
+                memory = len(state.get("nodeMemory", {}))
+                if identities == expected_nodes and memory == expected_nodes:
+                    return
+            except Exception:
+                pass
+            time.sleep(2.0)
+        raise TimeoutError(
+            f"Cluster did not reach exactly {expected_nodes} ready nodes within {timeout}s"
+        )

tests/test_1node.py

@@ -0,0 +1,75 @@
+# type: ignore
+"""Single-node integration tests.
+
+Run with:
+    uv run pytest tests/test_1node.py -v
+"""
+
+from __future__ import annotations
+
+import time
+
+import pytest
+from exo_tools.harness import is_model_downloaded, place_instance
+
+from .framework import DEFAULT_MODEL, InstanceSpec
+
+
+@pytest.mark.cluster(count=1)
+@pytest.mark.instance(DEFAULT_MODEL)
+def test_place_instance_and_chat(session):
+    resp = session.chat("Say hello in one sentence.")
+    assert len(resp) > 0
+
+
+@pytest.mark.cluster(count=1)
+@pytest.mark.instance(DEFAULT_MODEL)
+def test_chat_multiple_turns(session):
+    first_reply = session.chat("What is 2 + 2?")
+    assert len(first_reply) > 0
+
+    second_reply = session.multi_turn(
+        [
+            {"role": "user", "content": "What is 2 + 2?"},
+            {"role": "assistant", "content": first_reply},
+            {"role": "user", "content": "Now multiply that by 3."},
+        ]
+    )
+    assert len(second_reply) > 0
+
+
+@pytest.mark.cluster(count=1)
+@pytest.mark.instance(DEFAULT_MODEL)
+def test_delete_instance(session):
+    from exo_tools.harness import wait_for_instance_gone
+
+    session.client.request_json("DELETE", f"/instance/{session.instance_id}")
+    wait_for_instance_gone(session.client, session.instance_id, timeout=30.0)
+    assert len(session.instances) == 0, (
+        f"Expected no instances, found {len(session.instances)}"
+    )
+
+
+@pytest.mark.cluster(count=1)
+def test_download_from_scratch(session):
+    """Ensure the model is not on the cluster, then place an instance to
+    trigger a fresh download and verify inference.
+    """
+    node_id = next(iter(session.state.get("nodeIdentities", {})))
+
+    # Delete any existing download — the API call is idempotent
+    session.client.request_json("DELETE", f"/download/{node_id}/{DEFAULT_MODEL}")
+
+    # Poll until the model is gone (it may already be gone)
+    deadline = time.time() + 60.0
+    while time.time() < deadline:
+        if not is_model_downloaded(session.client, DEFAULT_MODEL):
+            break
+        time.sleep(2.0)
+    else:
+        raise AssertionError(f"Expected {DEFAULT_MODEL} to be deleted from cluster")
+
+    place_instance(session.client, DEFAULT_MODEL, timeout=900.0)
+    session.instance_spec = InstanceSpec(model_id=DEFAULT_MODEL)
+    resp = session.chat("Say hello in one sentence.")
+    assert len(resp) > 0

tests/test_2node.py

@@ -0,0 +1,49 @@
+# type: ignore
+"""Two-node integration tests (ring + jaccl parallelism).
+
+Run with:
+    uv run pytest tests/test_2node.py -v
+"""
+
+from __future__ import annotations
+
+import pytest
+from exo_tools.cluster import Thunderbolt
+from exo_tools.harness import Comm, Sharding
+
+from .framework import DEFAULT_MODEL
+
+
+@pytest.mark.cluster(count=2, thunderbolt=Thunderbolt.A2A)
+@pytest.mark.instance(
+    DEFAULT_MODEL, sharding=Sharding.TENSOR, comm=Comm.JACCL, min_nodes=2
+)
+def test_2node_jaccl(session):
+    resp = session.chat("Say hello in one sentence.")
+    assert len(resp) > 0
+
+
+@pytest.mark.cluster(count=2, thunderbolt=Thunderbolt.A2A)
+@pytest.mark.instance(
+    DEFAULT_MODEL, sharding=Sharding.PIPELINE, comm=Comm.RING, min_nodes=2
+)
+def test_2node_ring(session):
+    resp = session.chat("Say hello in one sentence.")
+    assert len(resp) > 0
+
+
+@pytest.mark.cluster(count=2, thunderbolt=Thunderbolt.A2A)
+@pytest.mark.instance(
+    DEFAULT_MODEL, sharding=Sharding.TENSOR, comm=Comm.JACCL, min_nodes=2
+)
+def test_2node_jaccl_multi_turn(session):
+    first = session.chat("What is the capital of France?")
+    assert len(first) > 0
+    second = session.multi_turn(
+        [
+            {"role": "user", "content": "What is the capital of France?"},
+            {"role": "assistant", "content": first},
+            {"role": "user", "content": "What country is it in?"},
+        ]
+    )
+    assert len(second) > 0

tests/test_4node.py

@@ -0,0 +1,32 @@
+# type: ignore
+"""Four-node integration tests.
+
+Run with:
+    uv run pytest tests/test_4node.py -v
+"""
+
+from __future__ import annotations
+
+import pytest
+from exo_tools.cluster import Thunderbolt
+from exo_tools.harness import Comm, Sharding
+
+from .framework import DEFAULT_MODEL
+
+
+@pytest.mark.cluster(count=4, thunderbolt=Thunderbolt.A2A)
+@pytest.mark.instance(
+    DEFAULT_MODEL, sharding=Sharding.PIPELINE, comm=Comm.RING, min_nodes=4
+)
+def test_4node_pipeline_ring(session):
+    resp = session.chat("Say hello in one sentence.")
+    assert len(resp) > 0
+
+
+@pytest.mark.cluster(count=4, thunderbolt=Thunderbolt.A2A)
+@pytest.mark.instance(
+    DEFAULT_MODEL, sharding=Sharding.TENSOR, comm=Comm.JACCL, min_nodes=4
+)
+def test_4node_tensor_jaccl(session):
+    resp = session.chat("Say hello in one sentence.")
+    assert len(resp) > 0

tests/test_dashboard.py

@@ -0,0 +1,102 @@
+# type: ignore
+"""Dashboard end-to-end tests using Playwright (headless Chromium).
+
+Prerequisites:
+    uv run playwright install chromium
+
+Run with:
+    uv run pytest tests/test_dashboard.py -v
+"""
+
+from __future__ import annotations
+
+import contextlib
+
+import pytest
+
+try:
+    from playwright.sync_api import sync_playwright
+
+    _HAS_PLAYWRIGHT = True
+except ImportError:
+    _HAS_PLAYWRIGHT = False
+
+# Check if Chromium is installed by attempting a quick launch
+_HAS_CHROMIUM = False
+if _HAS_PLAYWRIGHT:
+    try:
+        with sync_playwright() as p:
+            browser = p.chromium.launch(headless=True)
+            browser.close()
+        _HAS_CHROMIUM = True
+    except Exception:
+        pass
+
+pytestmark = pytest.mark.skipif(
+    not _HAS_PLAYWRIGHT or not _HAS_CHROMIUM,
+    reason="playwright or chromium not installed (run: uv run playwright install chromium)",
+)
+
+
+def _mark_onboarding_complete(session) -> None:
+    """Mark onboarding complete on the server so the wizard doesn't auto-launch a model."""
+    with contextlib.suppress(Exception):
+        session.client.request_json("POST", "/onboarding")
+
+
+@pytest.mark.cluster(count=1)
+def test_dashboard_chat_inference(session):
+    """Full UI flow: open dashboard, pick a model, send a chat, verify response.
+
+    The instance is created via the dashboard UI (model picker → chat send
+    triggers the dashboard's auto-launch flow), not via @pytest.mark.instance.
+    """
+    _mark_onboarding_complete(session)
+
+    with sync_playwright() as p:
+        browser = p.chromium.launch(headless=True)
+        page = browser.new_page(viewport={"width": 1280, "height": 800})
+        page.goto(session.cluster.api_url, wait_until="networkidle")
+        page.wait_for_timeout(3000)
+        page.screenshot(path="/tmp/dashboard_initial.png")
+
+        # Open the model picker by clicking the "SELECT MODEL" button
+        page.get_by_text("SELECT MODEL", exact=False).first.click()
+        page.wait_for_timeout(1000)
+        page.screenshot(path="/tmp/dashboard_picker_open.png")
+
+        # Search for the model — uses the model id substring; the picker
+        # matches against name/id so "Llama-3.2-1B" filters to the small Llama.
+        search_input = page.locator('input[placeholder*="Search models"]').first
+        search_input.fill("Llama-3.2-1B")
+        page.wait_for_timeout(1500)
+        page.screenshot(path="/tmp/dashboard_picker_search.png")
+
+        # Click the only matching result. The picker shows the model's
+        # display name (e.g. "Llama 3.2 1B") which differs from the model_id.
+        # We click the first visible button-like row in the result list.
+        page.get_by_text("Llama 3.2 1B", exact=False).first.click()
+        page.wait_for_timeout(1500)
+        page.screenshot(path="/tmp/dashboard_model_selected.png")
+
+        # Type a chat message — sending triggers the dashboard's auto-launch
+        # flow: it picks an optimal placement for the selected model and POSTs
+        # to /instance, then sends the chat once the runner is ready.
+        chat_input = page.locator("textarea").first
+        chat_input.fill("Say hello")
+        chat_input.press("Enter")
+        page.screenshot(path="/tmp/dashboard_chat_sent.png")
+
+        # Wait for the instance to launch and respond. Generous timeout
+        # because this includes model placement + load + generation.
+        page.wait_for_timeout(60000)
+        page.screenshot(path="/tmp/dashboard_after_chat.png")
+
+        # Verify an instance was created and the chat got a response
+        instances = session.client.request_json("GET", "/state").get("instances", {})
+        assert len(instances) > 0, "Expected the dashboard to have created an instance"
+
+        body_text = page.text_content("body") or ""
+        assert len(body_text) > 0
+
+        browser.close()

tests/test_resilience.py

@@ -0,0 +1,56 @@
+# type: ignore
+"""Resilience tests: disconnect/reconnect nodes and verify cluster recovery.
+
+Run with:
+    uv run pytest tests/test_resilience.py -v
+"""
+
+from __future__ import annotations
+
+import pytest
+from exo_tools.cluster import Thunderbolt
+from exo_tools.harness import Comm, Sharding, cleanup_all_instances, place_instance
+
+from .framework import DEFAULT_MODEL, InstanceSpec
+
+
+@pytest.mark.cluster(count=2, thunderbolt=Thunderbolt.A2A)
+@pytest.mark.instance(
+    DEFAULT_MODEL, sharding=Sharding.PIPELINE, comm=Comm.RING, min_nodes=2
+)
+def test_node_recovery(session):
+    """Full disconnect/reconnect cycle.
+
+    1. Place a 2-node instance, verify inference
+    2. Disconnect one node
+    3. Place a 1-node instance on remaining node, verify inference
+    4. Reconnect the stopped node, wait for the cluster to reform
+    5. Place a 2-node instance again, verify inference
+    """
+    # --- Phase 1: 2-node inference ---
+    resp = session.chat("Hello")
+    assert len(resp) > 0
+
+    # --- Phase 2: disconnect one node ---
+    session.disconnect_node(1)
+    session.wait_ready(60)
+
+    # Clean up the now-broken 2-node instance
+    cleanup_all_instances(session.client)
+
+    # --- Phase 3: 1-node inference on the remaining node ---
+    place_instance(session.client, DEFAULT_MODEL, min_nodes=1)
+    session.instance_spec = InstanceSpec(model_id=DEFAULT_MODEL, min_nodes=1)
+    resp = session.chat("Hello")
+    assert len(resp) > 0
+
+    # --- Phase 4: reconnect and restore 2-node cluster ---
+    cleanup_all_instances(session.client)
+    session.reconnect_node(1)
+    session.wait_ready(60)
+
+    # --- Phase 5: 2-node inference again ---
+    place_instance(session.client, DEFAULT_MODEL, min_nodes=2)
+    session.instance_spec = InstanceSpec(model_id=DEFAULT_MODEL, min_nodes=2)
+    resp = session.chat("Hello again")
+    assert len(resp) > 0

tools/pyproject.toml

@@ -0,0 +1,10 @@
+[project]
+name = "exo-tools"
+version = "0.1.0"
+description = "Shared tooling for interacting with exo clusters"
+requires-python = ">=3.13"
+dependencies = ["loguru>=0.7.3"]
+
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"

tools/src/exo_tools/client.py

@@ -0,0 +1,117 @@
+# type: ignore
+"""HTTP client for the exo API."""
+
+from __future__ import annotations
+
+import http.client
+import json
+from collections.abc import Iterator
+from typing import Any
+from urllib.parse import urlencode
+
+
+class ExoHttpError(RuntimeError):
+    def __init__(self, status: int, reason: str, body_preview: str):
+        super().__init__(f"HTTP {status} {reason}: {body_preview}")
+        self.status = status
+
+
+class ExoClient:
+    def __init__(self, host: str, port: int, timeout_s: float = 7200.0):
+        self.host = host
+        self.port = port
+        self.timeout_s = timeout_s
+
+    def request_json(
+        self,
+        method: str,
+        path: str,
+        params: dict[str, Any] | None = None,
+        body: dict[str, Any] | None = None,
+        headers: dict[str, str] | None = None,
+    ) -> Any:
+        if not path.startswith("/"):
+            path = "/" + path
+        if params:
+            path = path + "?" + urlencode(params)
+
+        conn = http.client.HTTPConnection(self.host, self.port, timeout=self.timeout_s)
+        try:
+            payload: bytes | None = None
+            hdrs: dict[str, str] = {"Accept": "application/json"}
+
+            if body is not None:
+                payload = json.dumps(body).encode("utf-8")
+                hdrs["Content-Type"] = "application/json"
+            if headers:
+                hdrs.update(headers)
+
+            conn.request(method.upper(), path, body=payload, headers=hdrs)
+            resp = conn.getresponse()
+            raw = resp.read()
+            text = raw.decode("utf-8", errors="replace") if raw else ""
+
+            if resp.status >= 400:
+                raise ExoHttpError(resp.status, resp.reason, text[:300])
+
+            if not text:
+                return None
+            return json.loads(text)
+        finally:
+            conn.close()
+
+    def post_bench_chat_completions(self, payload: dict[str, Any]) -> dict[str, Any]:
+        return self.request_json("POST", "/bench/chat/completions", body=payload)
+
+    def stream_bench_chat_completions(self, payload: dict[str, Any]) -> Iterator[str]:
+        """POST /bench/chat/completions with stream=True, yielding raw SSE lines."""
+        payload = {**payload, "stream": True}
+        data = json.dumps(payload).encode("utf-8")
+        conn = http.client.HTTPConnection(self.host, self.port, timeout=self.timeout_s)
+        try:
+            conn.request(
+                "POST",
+                "/bench/chat/completions",
+                body=data,
+                headers={
+                    "Content-Type": "application/json",
+                    "Accept": "text/event-stream",
+                },
+            )
+            resp = conn.getresponse()
+            if resp.status >= 400:
+                raw = resp.read().decode("utf-8", errors="replace")
+                raise ExoHttpError(resp.status, resp.reason, raw[:300])
+            for line in resp:
+                yield line.decode("utf-8", errors="replace")
+        finally:
+            conn.close()
+
+    def get_state_path(self, path: str) -> Any:
+        try:
+            return self.request_json("GET", f"/state/{path}")
+        except ExoHttpError as e:
+            if e.status == 404:
+                return None
+            raise
+
+    def get_instance(self, instance_id: str) -> dict[str, Any] | None:
+        return self.get_state_path(f"instances/{instance_id}")
+
+    def get_runner(self, runner_id: str) -> dict[str, Any] | None:
+        return self.get_state_path(f"runners/{runner_id}")
+
+    def get_node_downloads(self, node_id: str) -> list[dict[str, Any]] | None:
+        return self.get_state_path(f"downloads/{node_id}")
+
+    def get_node_disk(self, node_id: str) -> dict[str, Any] | None:
+        return self.get_state_path(f"nodeDisk/{node_id}")
+
+    def get_node_system(self, node_id: str) -> dict[str, Any] | None:
+        return self.get_state_path(f"nodeSystem/{node_id}")
+
+    def get_node_identities(self) -> dict[str, Any] | None:
+        return self.get_state_path("nodeIdentities")
+
+    def get_topology(self) -> dict[str, Any] | None:
+        return self.get_state_path("topology")

tools/src/exo_tools/cluster.py

@@ -0,0 +1,243 @@
+# type: ignore
+"""Cluster lifecycle management via eco.
+
+Provides subprocess wrappers for eco commands (deploy, stop, start, release,
+logs, exec) and a ClusterInfo dataclass. Reusable by integration tests,
+bench, eval, and CI workflows.
+"""
+
+from __future__ import annotations
+
+import atexit
+import contextlib
+import json
+import logging
+import os
+import signal
+import subprocess
+import uuid
+from dataclasses import dataclass, field
+from enum import Enum
+
+from .client import ExoClient
+
+
+class Thunderbolt(str, Enum):
+    A2A = "a2a"  # all-to-all (eco --tb-a2a)
+    RING = "ring"  # ring topology (eco --tb-ring)
+
+
+class Chip(str, Enum):
+    M1 = "M1"
+    M1_PRO = "M1 Pro"
+    M1_MAX = "M1 Max"
+    M1_ULTRA = "M1 Ultra"
+    M2 = "M2"
+    M2_PRO = "M2 Pro"
+    M2_MAX = "M2 Max"
+    M2_ULTRA = "M2 Ultra"
+    M3 = "M3"
+    M3_PRO = "M3 Pro"
+    M3_MAX = "M3 Max"
+    M3_ULTRA = "M3 Ultra"
+    M4 = "M4"
+    M4_PRO = "M4 Pro"
+    M4_MAX = "M4 Max"
+    M4_ULTRA = "M4 Ultra"
+
+
+logger = logging.getLogger("exo_tools.cluster")
+
+# When set, deploy from a GitHub branch/tag instead of local source (rsync).
+_EXO_REF = os.environ.get("EXO_REF")
+
+
+@dataclass
+class ClusterInfo:
+    """Holds the result of an `eco start --deploy` invocation."""
+
+    hosts: list[str]
+    namespace: str
+    api_endpoints: dict[str, str]  # host -> url
+    api_url: str  # primary endpoint for ExoClient
+
+    primary_host: str = ""
+    _host: str = field(init=False, repr=False, default="")
+    _port: int = field(init=False, repr=False, default=52415)
+
+    def __post_init__(self) -> None:
+        if not self.primary_host:
+            self.primary_host = self.hosts[0]
+        url = self.api_url.replace("http://", "").replace("https://", "")
+        parts = url.split(":")
+        self._host = parts[0]
+        self._port = int(parts[1]) if len(parts) > 1 else 52415
+
+    def make_client(self, timeout_s: float = 7200.0) -> ExoClient:
+        return ExoClient(self._host, self._port, timeout_s=timeout_s)
+
+
+class EcoSession:
+    """Manages an eco session with a unique user and automatic cleanup.
+
+    Usage:
+        session = EcoSession(user_prefix="test")
+        cluster = session.start_deploy(count=2, thunderbolt=True)
+        ...
+        session.stop_all()  # or let atexit handle it
+
+    The session registers atexit and signal handlers to ensure cleanup
+    on normal exit, uncaught exceptions, SIGTERM, and SIGHUP. SIGINT
+    is left unhandled so KeyboardInterrupt propagates normally.
+    """
+
+    def __init__(self, user_prefix: str = "test") -> None:
+        self._session_id = uuid.uuid4().hex[:8]
+        self.user = f"{user_prefix}-{self._session_id}"
+        self._env = {**os.environ, "USER": self.user}
+
+        # Register cleanup handlers
+        atexit.register(self.stop_all)
+        for sig in (signal.SIGTERM, signal.SIGHUP):
+            signal.signal(sig, self._signal_handler)
+
+    def _signal_handler(self, signum: int, _frame: object) -> None:
+        self.stop_all()
+        raise SystemExit(128 + signum)
+
+    def stop_all(self) -> None:
+        """Stop all clusters and release all reservations for this session."""
+        with contextlib.suppress(Exception):
+            subprocess.run(
+                ["eco", "stop"],
+                capture_output=True,
+                text=True,
+                timeout=30,
+                env=self._env,
+            )
+
+    def _run(
+        self, args: list[str], *, check: bool = True, timeout: int = 120
+    ) -> subprocess.CompletedProcess[str]:
+        """Run an eco command as this session's user.
+
+        stdout is captured (JSON output), stderr is passed through to the
+        console so eco's progress messages are visible.
+        """
+        logger.info(f"eco: {' '.join(args)}")
+        return subprocess.run(
+            args,
+            stdout=subprocess.PIPE,
+            stderr=None,
+            text=True,
+            check=check,
+            timeout=timeout,
+            env=self._env,
+        )
+
+    def start_deploy(
+        self,
+        hosts: list[str] | None = None,
+        *,
+        count: int | None = None,
+        thunderbolt: Thunderbolt | None = None,
+        chip: Chip | None = None,
+        min_memory_gb: float | None = None,
+        wait: bool = True,
+        ref: str | None = _EXO_REF,
+        timeout: int = 600,
+    ) -> ClusterInfo:
+        """Start and deploy exo on a set of hosts via eco.
+
+        By default, deploys from local source via rsync. Set EXO_REF
+        or pass ref= to deploy from a GitHub branch/tag instead (for CI).
+        """
+        cmd: list[str] = ["eco", "--json", "start", "--deploy"]
+        if hosts:
+            cmd.extend(hosts)
+        if count is not None:
+            cmd.extend(["--count", str(count)])
+        if thunderbolt is not None:
+            cmd.append(f"--tb-{thunderbolt.value}")
+        if chip is not None:
+            cmd.extend(["--chip", chip.value])
+        if min_memory_gb is not None:
+            cmd.extend(["--min-memory", str(min_memory_gb)])
+        if wait:
+            cmd.append("--wait")
+        if ref:
+            cmd.extend(["--ref", ref])
+
+        result = self._run(cmd, timeout=timeout)
+        data = json.loads(result.stdout)["data"]
+        endpoints: dict[str, str] = data["api_endpoints"]
+        primary_host = data["hosts"][0]
+
+        return ClusterInfo(
+            hosts=data["hosts"],
+            namespace=data["namespace"],
+            api_endpoints=endpoints,
+            api_url=endpoints[primary_host],
+            primary_host=primary_host,
+        )
+
+    def stop(self, hosts: list[str], *, keep: bool = False, timeout: int = 120) -> None:
+        """Stop exo on the given hosts. If keep=True, keep the reservation."""
+        cmd: list[str] = ["eco", "stop"]
+        cmd.extend(hosts)
+        if keep:
+            cmd.append("--keep")
+        self._run(cmd, timeout=timeout)
+
+    def start_hosts(
+        self, hosts: list[str], *, namespace: str, timeout: int = 300
+    ) -> None:
+        """Start (previously stopped) hosts back into an existing namespace."""
+        cmd: list[str] = ["eco", "--json", "start"]
+        cmd.extend(hosts)
+        cmd.extend(["--namespace", namespace])
+        self._run(cmd, timeout=timeout)
+
+    def release(self, hosts: list[str], timeout: int = 120) -> None:
+        """Release hosts from the reservation."""
+        cmd: list[str] = ["eco", "release"]
+        cmd.extend(hosts)
+        self._run(cmd, timeout=timeout)
+
+    def logs(
+        self, hosts: list[str], lines: int = 500, timeout: int = 60
+    ) -> dict[str, list[str]]:
+        """Fetch recent logs from cluster hosts."""
+        cmd: list[str] = ["eco", "--json", "logs"]
+        cmd.extend(hosts)
+        cmd.extend(["-n", str(lines), "--raw"])
+        result = self._run(cmd, check=False, timeout=timeout)
+        if result.returncode != 0:
+            return {"_error": [result.stderr]}
+        try:
+            return json.loads(result.stdout)
+        except json.JSONDecodeError:
+            return {"_raw": result.stdout.splitlines()}
+
+    def exec(self, hosts: list[str], command: str, timeout: int = 120) -> str:
+        """Run an arbitrary command on the given hosts via eco."""
+        cmd: list[str] = ["eco", "exec"]
+        cmd.extend(hosts)
+        cmd.append("--")
+        cmd.extend(command.split())
+        result = self._run(cmd, check=False, timeout=timeout)
+        return result.stdout
+
+
+def make_client(cluster: ClusterInfo, timeout_s: float = 7200.0) -> ExoClient:
+    """Create an ExoClient from a ClusterInfo."""
+    return cluster.make_client(timeout_s=timeout_s)
+
+
+def make_client_from_url(url: str, timeout_s: float = 7200.0) -> ExoClient:
+    """Create an ExoClient from a URL string like 'http://host:port'."""
+    url_clean = url.replace("http://", "").replace("https://", "")
+    parts = url_clean.split(":")
+    host = parts[0]
+    port = int(parts[1]) if len(parts) > 1 else 52415
+    return ExoClient(host, port, timeout_s=timeout_s)

tools/src/exo_tools/harness.py

@@ -1,129 +1,39 @@
 # type: ignore
+"""Instance lifecycle helpers for exo clusters.
+
+Provides utilities for placing instances, waiting for readiness,
+managing downloads, filtering placements, and common CLI arguments.
+"""
+
 from __future__ import annotations
 
 import argparse
-import http.client
-import json
+import contextlib
 import os
 import time
-from collections.abc import Iterator
+from enum import Enum
 from typing import Any
-from urllib.parse import urlencode
 
 from loguru import logger
 
+from .client import ExoClient, ExoHttpError
+
+
+class Sharding(str, Enum):
+    PIPELINE = "Pipeline"  # layers split across nodes
+    TENSOR = "Tensor"  # layers split within (across nodes)
+
+
+class Comm(str, Enum):
+    RING = "MlxRing"  # ring all-reduce over network
+    JACCL = "MlxJaccl"  # RDMA over Thunderbolt
+
+
 _SETTLE_INITIAL_BACKOFF_S = 1.0
 _SETTLE_MAX_BACKOFF_S = 60.0
 _SETTLE_BACKOFF_MULTIPLIER = 2.0
 
 
-class ExoHttpError(RuntimeError):
-    def __init__(self, status: int, reason: str, body_preview: str):
-        super().__init__(f"HTTP {status} {reason}: {body_preview}")
-        self.status = status
-
-
-class ExoClient:
-    def __init__(self, host: str, port: int, timeout_s: float = 7200.0):
-        self.host = host
-        self.port = port
-        self.timeout_s = timeout_s
-
-    def request_json(
-        self,
-        method: str,
-        path: str,
-        params: dict[str, Any] | None = None,
-        body: dict[str, Any] | None = None,
-        headers: dict[str, str] | None = None,
-    ) -> Any:
-        if not path.startswith("/"):
-            path = "/" + path
-        if params:
-            path = path + "?" + urlencode(params)
-
-        conn = http.client.HTTPConnection(self.host, self.port, timeout=self.timeout_s)
-        try:
-            payload: bytes | None = None
-            hdrs: dict[str, str] = {"Accept": "application/json"}
-
-            if body is not None:
-                payload = json.dumps(body).encode("utf-8")
-                hdrs["Content-Type"] = "application/json"
-            if headers:
-                hdrs.update(headers)
-
-            conn.request(method.upper(), path, body=payload, headers=hdrs)
-            resp = conn.getresponse()
-            raw = resp.read()
-            text = raw.decode("utf-8", errors="replace") if raw else ""
-
-            if resp.status >= 400:
-                raise ExoHttpError(resp.status, resp.reason, text[:300])
-
-            if not text:
-                return None
-            return json.loads(text)
-        finally:
-            conn.close()
-
-    def post_bench_chat_completions(self, payload: dict[str, Any]) -> dict[str, Any]:
-        return self.request_json("POST", "/bench/chat/completions", body=payload)
-
-    def stream_bench_chat_completions(self, payload: dict[str, Any]) -> Iterator[str]:
-        """POST /bench/chat/completions with stream=True, yielding raw SSE lines."""
-        payload = {**payload, "stream": True}
-        data = json.dumps(payload).encode("utf-8")
-        conn = http.client.HTTPConnection(self.host, self.port, timeout=self.timeout_s)
-        try:
-            conn.request(
-                "POST",
-                "/bench/chat/completions",
-                body=data,
-                headers={
-                    "Content-Type": "application/json",
-                    "Accept": "text/event-stream",
-                },
-            )
-            resp = conn.getresponse()
-            if resp.status >= 400:
-                raw = resp.read().decode("utf-8", errors="replace")
-                raise ExoHttpError(resp.status, resp.reason, raw[:300])
-            for line in resp:
-                yield line.decode("utf-8", errors="replace")
-        finally:
-            conn.close()
-
-    def get_state_path(self, path: str) -> Any:
-        try:
-            return self.request_json("GET", f"/state/{path}")
-        except ExoHttpError as e:
-            if e.status == 404:
-                return None
-            raise
-
-    def get_instance(self, instance_id: str) -> dict[str, Any] | None:
-        return self.get_state_path(f"instances/{instance_id}")
-
-    def get_runner(self, runner_id: str) -> dict[str, Any] | None:
-        return self.get_state_path(f"runners/{runner_id}")
-
-    def get_node_downloads(self, node_id: str) -> list[dict[str, Any]] | None:
-        return self.get_state_path(f"downloads/{node_id}")
-
-    def get_node_disk(self, node_id: str) -> dict[str, Any] | None:
-        return self.get_state_path(f"nodeDisk/{node_id}")
-
-    def get_node_system(self, node_id: str) -> dict[str, Any] | None:
-        return self.get_state_path(f"nodeSystem/{node_id}")
-
-    def get_node_identities(self) -> dict[str, Any] | None:
-        return self.get_state_path("nodeIdentities")
-
-    def get_topology(self) -> dict[str, Any] | None:
-        return self.get_state_path("topology")
-
-
 def unwrap_instance(instance: dict[str, Any]) -> dict[str, Any]:
     if len(instance) != 1:
         raise KeyError(f"Expected 1 key, got keys={list(instance.keys())}")
@@ -555,7 +465,6 @@ def find_existing_instance(client: ExoClient, model_id: str) -> str | None:
     except Exception:
         return None
     for inst_id, inst in state.get("instances", {}).items():
-        # Instance structure is nested: {"MlxJacclInstance": {"shardAssignments": {"modelId": ...}}}
         for _inst_type, inner in inst.items():
             if not isinstance(inner, dict):
                 continue
@@ -623,3 +532,112 @@ def add_common_instance_args(ap: argparse.ArgumentParser) -> None:
         action="store_true",
         help="Reuse an existing running instance for this model instead of creating a new one.",
     )
+
+
+# ---------------------------------------------------------------------------
+# Cluster/instance orchestration helpers (used by tests, bench, eval)
+# ---------------------------------------------------------------------------
+
+
+def get_instance_ids(client: ExoClient) -> set[str]:
+    """Return the set of current instance IDs from cluster state."""
+    state = client.request_json("GET", "/state") or {}
+    result: set[str] = set()
+    for instance in state.get("instances", {}).values():
+        with contextlib.suppress(Exception):
+            result.add(instance_id_from_instance(instance))
+    return result
+
+
+def wait_for_cluster_ready(
+    client: ExoClient, expected_nodes: int = 1, timeout: float = 120.0
+) -> None:
+    """Wait until the cluster has all expected nodes visible and reporting memory.
+
+    Placement requires nodeMemory for all nodes in a cycle. This polls until
+    both nodeIdentities and nodeMemory have at least `expected_nodes` entries.
+    """
+    start = time.time()
+    while time.time() - start < timeout:
+        try:
+            state = client.request_json("GET", "/state") or {}
+            if (
+                len(state.get("nodeIdentities", {})) >= expected_nodes
+                and len(state.get("nodeMemory", {})) >= expected_nodes
+            ):
+                return
+        except Exception:
+            pass
+        time.sleep(1.0)
+    raise TimeoutError(f"Cluster not ready: expected {expected_nodes} nodes")
+
+
+def place_instance(
+    client: ExoClient,
+    model_id: str,
+    *,
+    sharding: Sharding = Sharding.PIPELINE,
+    comm: Comm = Comm.RING,
+    min_nodes: int = 1,
+    timeout: float = 600.0,
+    placement_retries: int = 10,
+    placement_retry_delay: float = 10.0,
+) -> str:
+    """Place an instance and wait for it to be ready. Returns the instance_id.
+
+    The /place_instance API returns a command_id, but instances are stored
+    under a separately-generated instance_id. This polls cluster state for the
+    new instance, retrying placement if the cluster is still settling.
+    """
+    wait_for_cluster_ready(client, expected_nodes=min_nodes)
+
+    body = {
+        "model_id": model_id,
+        "sharding": sharding.value,
+        "instance_meta": comm.value,
+        "min_nodes": min_nodes,
+    }
+
+    instance_id: str | None = None
+    for attempt in range(placement_retries):
+        before_ids = get_instance_ids(client)
+        client.request_json("POST", "/place_instance", body=body)
+
+        poll_deadline = time.time() + 30.0
+        while time.time() < poll_deadline:
+            new_ids = get_instance_ids(client) - before_ids
+            if new_ids:
+                instance_id = next(iter(new_ids))
+                break
+            time.sleep(1.0)
+
+        if instance_id is not None:
+            break
+
+        if attempt < placement_retries - 1:
+            time.sleep(placement_retry_delay)
+
+    if instance_id is None:
+        raise TimeoutError(
+            f"Placement failed after {placement_retries} attempts "
+            f"({sharding.value}/{comm.value} for {model_id})"
+        )
+
+    wait_for_instance_ready(client, instance_id, timeout=timeout)
+    return instance_id
+
+
+def cleanup_all_instances(client: ExoClient) -> None:
+    """Remove all running instances from the cluster."""
+    state = client.request_json("GET", "/state") or {}
+    for instance in state.get("instances", {}).values():
+        with contextlib.suppress(Exception):
+            iid = instance_id_from_instance(instance)
+            client.request_json("DELETE", f"/instance/{iid}")
+            wait_for_instance_gone(client, iid, timeout=30.0)
+
+
+def is_model_downloaded(client: ExoClient, model_id: str) -> bool:
+    response = client.request_json("GET", "/models", params={"status": "downloaded"})
+    data = (response or {}).get("data", [])
+    return all(model.get("id") == model_id for model in data)

uv.lock

@@ -23,10 +23,11 @@ members = [
     "exo",
     "exo-bench",
     "exo-pyo3-bindings",
+    "exo-tools",
 ]
 constraints = [{ name = "transformers", specifier = ">=5.6.2" }]
 overrides = [
-    { name = "mlx", marker = "sys_platform == 'darwin'", git = "https://github.com/rltakashige/mlx-jaccl-fix-small-recv.git?branch=address-rdma-gpu-locks" },
+    { name = "mlx", marker = "sys_platform == 'darwin'", git = "https://github.com/rltakashige/mlx-jaccl-fix-small-recv.git?branch=leo%2Forder-distributed-ops" },
     { name = "mlx", marker = "sys_platform == 'linux'", specifier = "==0.31.1" },
 ]
 
@@ -394,7 +395,7 @@ dependencies = [
     { name = "loguru", marker = "sys_platform == 'darwin' or sys_platform == 'linux' or (extra == 'extra-3-exo-cpu' and extra == 'extra-3-exo-cuda12') or (extra == 'extra-3-exo-cpu' and extra == 'extra-3-exo-cuda13') or (extra == 'extra-3-exo-cuda12' and extra == 'extra-3-exo-cuda13')" },
     { name = "mflux", marker = "sys_platform == 'darwin' or (extra == 'extra-3-exo-cpu' and extra == 'extra-3-exo-cuda12') or (extra == 'extra-3-exo-cpu' and extra == 'extra-3-exo-cuda13') or (extra == 'extra-3-exo-cuda12' and extra == 'extra-3-exo-cuda13')" },
     { name = "mlx", version = "0.31.1", source = { registry = "https://pypi.org/simple" }, marker = "sys_platform == 'linux' or (extra == 'extra-3-exo-cpu' and extra == 'extra-3-exo-cuda12') or (extra == 'extra-3-exo-cpu' and extra == 'extra-3-exo-cuda13') or (extra == 'extra-3-exo-cuda12' and extra == 'extra-3-exo-cuda13')" },
-    { name = "mlx", version = "0.32.0.dev20260427+cc3f3e60", source = { git = "https://github.com/rltakashige/mlx-jaccl-fix-small-recv.git?branch=address-rdma-gpu-locks#cc3f3e60be1289506125f2fa19b73b05aa770df8" }, marker = "sys_platform == 'darwin' or (extra == 'extra-3-exo-cpu' and extra == 'extra-3-exo-cuda12') or (extra == 'extra-3-exo-cpu' and extra == 'extra-3-exo-cuda13') or (extra == 'extra-3-exo-cuda12' and extra == 'extra-3-exo-cuda13')" },
+    { name = "mlx", version = "0.32.0.dev20260508+df6a7891", source = { git = "https://github.com/rltakashige/mlx-jaccl-fix-small-recv.git?branch=leo%2Forder-distributed-ops#df6a7891226d3262b88fe21a918e4223b552b819" }, marker = "sys_platform == 'darwin' or (extra == 'extra-3-exo-cpu' and extra == 'extra-3-exo-cuda12') or (extra == 'extra-3-exo-cpu' and extra == 'extra-3-exo-cuda13') or (extra == 'extra-3-exo-cuda12' and extra == 'extra-3-exo-cuda13')" },
     { name = "mlx-lm", marker = "sys_platform == 'darwin' or (extra == 'extra-3-exo-cpu' and extra == 'extra-3-exo-cuda12') or (extra == 'extra-3-exo-cpu' and extra == 'extra-3-exo-cuda13') or (extra == 'extra-3-exo-cuda12' and extra == 'extra-3-exo-cuda13')" },
     { name = "mlx-vlm", marker = "sys_platform == 'darwin' or (extra == 'extra-3-exo-cpu' and extra == 'extra-3-exo-cuda12') or (extra == 'extra-3-exo-cpu' and extra == 'extra-3-exo-cuda13') or (extra == 'extra-3-exo-cuda12' and extra == 'extra-3-exo-cuda13')" },
     { name = "msgspec", marker = "sys_platform == 'darwin' or sys_platform == 'linux' or (extra == 'extra-3-exo-cpu' and extra == 'extra-3-exo-cuda12') or (extra == 'extra-3-exo-cpu' and extra == 'extra-3-exo-cuda13') or (extra == 'extra-3-exo-cuda12' and extra == 'extra-3-exo-cuda13')" },
@@ -416,21 +417,21 @@ build = [
 ]
 cpu = [
     { name = "mlx", version = "0.31.1", source = { registry = "https://pypi.org/simple" }, marker = "(sys_platform == 'linux' and extra == 'extra-3-exo-cpu') or (extra == 'extra-3-exo-cpu' and extra == 'extra-3-exo-cuda12') or (extra == 'extra-3-exo-cpu' and extra == 'extra-3-exo-cuda13') or (extra == 'extra-3-exo-cuda12' and extra == 'extra-3-exo-cuda13')" },
-    { name = "mlx", version = "0.32.0.dev20260427+cc3f3e60", source = { git = "https://github.com/rltakashige/mlx-jaccl-fix-small-recv.git?branch=address-rdma-gpu-locks#cc3f3e60be1289506125f2fa19b73b05aa770df8" }, marker = "(sys_platform == 'darwin' and extra == 'extra-3-exo-cpu') or (extra == 'extra-3-exo-cpu' and extra == 'extra-3-exo-cuda12') or (extra == 'extra-3-exo-cpu' and extra == 'extra-3-exo-cuda13') or (extra == 'extra-3-exo-cuda12' and extra == 'extra-3-exo-cuda13')" },
+    { name = "mlx", version = "0.32.0.dev20260508+df6a7891", source = { git = "https://github.com/rltakashige/mlx-jaccl-fix-small-recv.git?branch=leo%2Forder-distributed-ops#df6a7891226d3262b88fe21a918e4223b552b819" }, marker = "(sys_platform == 'darwin' and extra == 'extra-3-exo-cpu') or (extra == 'extra-3-exo-cpu' and extra == 'extra-3-exo-cuda12') or (extra == 'extra-3-exo-cpu' and extra == 'extra-3-exo-cuda13') or (extra == 'extra-3-exo-cuda12' and extra == 'extra-3-exo-cuda13')" },
     { name = "mlx-cpu", marker = "sys_platform == 'linux'" },
     { name = "mlx-lm", marker = "sys_platform == 'linux'" },
     { name = "mlx-vlm", marker = "sys_platform == 'linux'" },
 ]
 cuda12 = [
     { name = "mlx", version = "0.31.1", source = { registry = "https://pypi.org/simple" }, marker = "(sys_platform == 'linux' and extra == 'extra-3-exo-cuda12') or (extra == 'extra-3-exo-cuda12' and extra == 'extra-3-exo-cuda13') or (extra == 'extra-3-exo-cpu' and extra == 'extra-3-exo-cuda12') or (extra == 'extra-3-exo-cpu' and extra == 'extra-3-exo-cuda13')" },
-    { name = "mlx", version = "0.32.0.dev20260427+cc3f3e60", source = { git = "https://github.com/rltakashige/mlx-jaccl-fix-small-recv.git?branch=address-rdma-gpu-locks#cc3f3e60be1289506125f2fa19b73b05aa770df8" }, marker = "(sys_platform == 'darwin' and extra == 'extra-3-exo-cuda12') or (extra == 'extra-3-exo-cuda12' and extra == 'extra-3-exo-cuda13') or (extra == 'extra-3-exo-cpu' and extra == 'extra-3-exo-cuda12') or (extra == 'extra-3-exo-cpu' and extra == 'extra-3-exo-cuda13')" },
+    { name = "mlx", version = "0.32.0.dev20260508+df6a7891", source = { git = "https://github.com/rltakashige/mlx-jaccl-fix-small-recv.git?branch=leo%2Forder-distributed-ops#df6a7891226d3262b88fe21a918e4223b552b819" }, marker = "(sys_platform == 'darwin' and extra == 'extra-3-exo-cuda12') or (extra == 'extra-3-exo-cuda12' and extra == 'extra-3-exo-cuda13') or (extra == 'extra-3-exo-cpu' and extra == 'extra-3-exo-cuda12') or (extra == 'extra-3-exo-cpu' and extra == 'extra-3-exo-cuda13')" },
     { name = "mlx-cuda-12", marker = "sys_platform == 'linux'" },
     { name = "mlx-lm", marker = "sys_platform == 'linux'" },
     { name = "mlx-vlm", marker = "sys_platform == 'linux'" },
 ]
 cuda13 = [
     { name = "mlx", version = "0.31.1", source = { registry = "https://pypi.org/simple" }, marker = "(sys_platform == 'linux' and extra == 'extra-3-exo-cuda13') or (extra == 'extra-3-exo-cuda12' and extra == 'extra-3-exo-cuda13') or (extra == 'extra-3-exo-cpu' and extra == 'extra-3-exo-cuda12') or (extra == 'extra-3-exo-cpu' and extra == 'extra-3-exo-cuda13')" },
-    { name = "mlx", version = "0.32.0.dev20260427+cc3f3e60", source = { git = "https://github.com/rltakashige/mlx-jaccl-fix-small-recv.git?branch=address-rdma-gpu-locks#cc3f3e60be1289506125f2fa19b73b05aa770df8" }, marker = "(sys_platform == 'darwin' and extra == 'extra-3-exo-cuda13') or (extra == 'extra-3-exo-cuda12' and extra == 'extra-3-exo-cuda13') or (extra == 'extra-3-exo-cpu' and extra == 'extra-3-exo-cuda12') or (extra == 'extra-3-exo-cpu' and extra == 'extra-3-exo-cuda13')" },
+    { name = "mlx", version = "0.32.0.dev20260508+df6a7891", source = { git = "https://github.com/rltakashige/mlx-jaccl-fix-small-recv.git?branch=leo%2Forder-distributed-ops#df6a7891226d3262b88fe21a918e4223b552b819" }, marker = "(sys_platform == 'darwin' and extra == 'extra-3-exo-cuda13') or (extra == 'extra-3-exo-cuda12' and extra == 'extra-3-exo-cuda13') or (extra == 'extra-3-exo-cpu' and extra == 'extra-3-exo-cuda12') or (extra == 'extra-3-exo-cpu' and extra == 'extra-3-exo-cuda13')" },
     { name = "mlx-cuda-13", marker = "sys_platform == 'linux'" },
     { name = "mlx-lm", marker = "sys_platform == 'linux'" },
     { name = "mlx-vlm", marker = "sys_platform == 'linux'" },
@@ -439,6 +440,7 @@ cuda13 = [
 [package.dev-dependencies]
 dev = [
     { name = "basedpyright", marker = "sys_platform == 'darwin' or sys_platform == 'linux' or (extra == 'extra-3-exo-cpu' and extra == 'extra-3-exo-cuda12') or (extra == 'extra-3-exo-cpu' and extra == 'extra-3-exo-cuda13') or (extra == 'extra-3-exo-cuda12' and extra == 'extra-3-exo-cuda13')" },
+    { name = "playwright", marker = "sys_platform == 'darwin' or sys_platform == 'linux' or (extra == 'extra-3-exo-cpu' and extra == 'extra-3-exo-cuda12') or (extra == 'extra-3-exo-cpu' and extra == 'extra-3-exo-cuda13') or (extra == 'extra-3-exo-cuda12' and extra == 'extra-3-exo-cuda13')" },
     { name = "pyinstaller", marker = "sys_platform == 'darwin' or sys_platform == 'linux' or (extra == 'extra-3-exo-cpu' and extra == 'extra-3-exo-cuda12') or (extra == 'extra-3-exo-cpu' and extra == 'extra-3-exo-cuda13') or (extra == 'extra-3-exo-cuda12' and extra == 'extra-3-exo-cuda13')" },
     { name = "pytest", marker = "sys_platform == 'darwin' or sys_platform == 'linux' or (extra == 'extra-3-exo-cpu' and extra == 'extra-3-exo-cuda12') or (extra == 'extra-3-exo-cpu' and extra == 'extra-3-exo-cuda13') or (extra == 'extra-3-exo-cuda12' and extra == 'extra-3-exo-cuda13')" },
     { name = "pytest-asyncio", marker = "sys_platform == 'darwin' or sys_platform == 'linux' or (extra == 'extra-3-exo-cpu' and extra == 'extra-3-exo-cuda12') or (extra == 'extra-3-exo-cpu' and extra == 'extra-3-exo-cuda13') or (extra == 'extra-3-exo-cuda12' and extra == 'extra-3-exo-cuda13')" },
@@ -459,7 +461,7 @@ requires-dist = [
     { name = "hypercorn", specifier = ">=0.18.0" },
     { name = "loguru", specifier = ">=0.7.3" },
     { name = "mflux", marker = "sys_platform == 'darwin'", specifier = "==0.17.2" },
-    { name = "mlx", marker = "sys_platform == 'darwin'", git = "https://github.com/rltakashige/mlx-jaccl-fix-small-recv.git?branch=address-rdma-gpu-locks" },
+    { name = "mlx", marker = "sys_platform == 'darwin'", git = "https://github.com/rltakashige/mlx-jaccl-fix-small-recv.git?branch=leo%2Forder-distributed-ops" },
     { name = "mlx", marker = "sys_platform == 'linux' and extra == 'cpu'", specifier = "==0.31.1" },
     { name = "mlx", marker = "sys_platform == 'linux' and extra == 'cuda12'", specifier = "==0.31.1" },
     { name = "mlx", marker = "sys_platform == 'linux' and extra == 'cuda13'", specifier = "==0.31.1" },
@@ -498,6 +500,7 @@ provides-extras = ["build", "cpu", "cuda12", "cuda13"]
 [package.metadata.requires-dev]
 dev = [
     { name = "basedpyright", specifier = ">=1.29.0" },
+    { name = "playwright", specifier = ">=1.52.0" },
     { name = "pyinstaller", specifier = ">=6.17.0" },
     { name = "pytest", specifier = ">=8.4.0" },
     { name = "pytest-asyncio", specifier = ">=1.0.0" },
@@ -561,6 +564,17 @@ dev = [
     { name = "pytest-asyncio", specifier = ">=1.0.0" },
 ]
 
+[[package]]
+name = "exo-tools"
+version = "0.1.0"
+source = { editable = "tools" }
+dependencies = [
+    { name = "loguru", marker = "sys_platform == 'darwin' or sys_platform == 'linux' or (extra == 'extra-3-exo-cpu' and extra == 'extra-3-exo-cuda12') or (extra == 'extra-3-exo-cpu' and extra == 'extra-3-exo-cuda13') or (extra == 'extra-3-exo-cuda12' and extra == 'extra-3-exo-cuda13')" },
+]
+
+[package.metadata]
+requires-dist = [{ name = "loguru", specifier = ">=0.7.3" }]
+
 [[package]]
 name = "fastapi"
 version = "0.128.0"
@@ -669,6 +683,24 @@ http = [
     { name = "aiohttp", marker = "sys_platform == 'darwin' or sys_platform == 'linux' or (extra == 'extra-3-exo-cpu' and extra == 'extra-3-exo-cuda12') or (extra == 'extra-3-exo-cpu' and extra == 'extra-3-exo-cuda13') or (extra == 'extra-3-exo-cuda12' and extra == 'extra-3-exo-cuda13')" },
 ]
 
+[[package]]
+name = "greenlet"
+version = "3.5.0"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/3c/3f/dbf99fb14bfeb88c28f16729215478c0e265cacd6dc22270c8f31bb6892f/greenlet-3.5.0.tar.gz", hash = "sha256:d419647372241bc68e957bf38d5c1f98852155e4146bd1e4121adea81f4f01e4", size = 196995, upload-time = "2026-04-27T13:37:15.544Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/0c/58/fc576f99037ce19c5aa16628e4c3226b6d1419f72a62c79f5f40576e6eb3/greenlet-3.5.0-cp313-cp313-macosx_11_0_universal2.whl", hash = "sha256:5a5ed18de6a0f6cc7087f1563f6bd93fc7df1c19165ca01e9bde5a5dc281d106", size = 285066, upload-time = "2026-04-27T12:23:05.033Z" },
+    { url = "https://files.pythonhosted.org/packages/4a/ba/b28ddbe6bfad6a8ac196ef0e8cff37bc65b79735995b9e410923fffeeb70/greenlet-3.5.0-cp313-cp313-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:3a717fbc46d8a354fa675f7c1e813485b6ba3885f9bef0cd56e5ba27d758ff5b", size = 604414, upload-time = "2026-04-27T12:52:42.358Z" },
+    { url = "https://files.pythonhosted.org/packages/09/06/4b69f8f0b67603a8be2790e55107a190b376f2627fe0eaf5695d85ffb3cd/greenlet-3.5.0-cp313-cp313-manylinux_2_24_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:ddc090c5c1792b10246a78e8c2163ebbe04cf877f9d785c230a7b27b39ad038e", size = 617349, upload-time = "2026-04-27T12:59:43.32Z" },
+    { url = "https://files.pythonhosted.org/packages/6a/15/a643b4ecd09969e30b8a150d5919960caae0abe4f5af75ab040b1ab85e78/greenlet-3.5.0-cp313-cp313-manylinux_2_24_s390x.manylinux_2_28_s390x.whl", hash = "sha256:4964101b8585c144cbda5532b1aa644255126c08a265dae90c16e7a0e63aaa9d", size = 623234, upload-time = "2026-04-27T13:02:40.611Z" },
+    { url = "https://files.pythonhosted.org/packages/8a/17/a3918541fd0ddefe024a69de6d16aa7b46d36ac19562adaa63c7fa180eff/greenlet-3.5.0-cp313-cp313-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:2094acd54b272cb6eae8c03dd87b3fa1820a4cef18d6889c378d503500a1dc13", size = 613927, upload-time = "2026-04-27T12:25:30.28Z" },
+    { url = "https://files.pythonhosted.org/packages/77/18/3b13d5ef1275b0ffaf933b05efa21408ac4ca95823c7411d79682e4fdcff/greenlet-3.5.0-cp313-cp313-manylinux_2_39_riscv64.whl", hash = "sha256:7022615368890680e67b9965d33f5773aade330d5343bbe25560135aaa849eae", size = 425243, upload-time = "2026-04-27T13:05:15.689Z" },
+    { url = "https://files.pythonhosted.org/packages/ee/e1/bd0af6213c7dd33175d8a462d4c1fe1175124ebed4855bc1475a5b5242c2/greenlet-3.5.0-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:5e05ba267789ea87b5a155cf0e810b1ab88bf18e9e8740813945ceb8ee4350ba", size = 1570893, upload-time = "2026-04-27T12:53:29.483Z" },
+    { url = "https://files.pythonhosted.org/packages/9b/2a/0789702f864f5382cb476b93d7a9c823c10472658102ccd65f415747d2e2/greenlet-3.5.0-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:0ecec963079cd58cbd14723582384f11f166fd58883c15dcbfb342e0bc9b5846", size = 1636060, upload-time = "2026-04-27T12:25:28.845Z" },
+    { url = "https://files.pythonhosted.org/packages/b2/8f/22bf9df92bbff0eb07842b60f7e63bf7675a9742df628437a9f02d09137f/greenlet-3.5.0-cp313-cp313-win_amd64.whl", hash = "sha256:728d9667d8f2f586644b748dbd9bb67e50d6a9381767d1357714ea6825bb3bf5", size = 238740, upload-time = "2026-04-27T12:24:01.341Z" },
+    { url = "https://files.pythonhosted.org/packages/b6/b7/9c5c3d653bd4ff614277c049ac676422e2c557db47b4fe43e6313fc005dc/greenlet-3.5.0-cp313-cp313-win_arm64.whl", hash = "sha256:47422135b1d308c14b2c6e758beedb1acd33bb91679f5670edf77bf46244722b", size = 235525, upload-time = "2026-04-27T12:23:12.308Z" },
+]
+
 [[package]]
 name = "h11"
 version = "0.16.0"
@@ -1213,7 +1245,7 @@ dependencies = [
     { name = "hf-transfer", marker = "sys_platform == 'darwin' or (extra == 'extra-3-exo-cpu' and extra == 'extra-3-exo-cuda12') or (extra == 'extra-3-exo-cpu' and extra == 'extra-3-exo-cuda13') or (extra == 'extra-3-exo-cuda12' and extra == 'extra-3-exo-cuda13')" },
     { name = "huggingface-hub", marker = "sys_platform == 'darwin' or (extra == 'extra-3-exo-cpu' and extra == 'extra-3-exo-cuda12') or (extra == 'extra-3-exo-cpu' and extra == 'extra-3-exo-cuda13') or (extra == 'extra-3-exo-cuda12' and extra == 'extra-3-exo-cuda13')" },
     { name = "matplotlib", marker = "sys_platform == 'darwin' or (extra == 'extra-3-exo-cpu' and extra == 'extra-3-exo-cuda12') or (extra == 'extra-3-exo-cpu' and extra == 'extra-3-exo-cuda13') or (extra == 'extra-3-exo-cuda12' and extra == 'extra-3-exo-cuda13')" },
-    { name = "mlx", version = "0.32.0.dev20260427+cc3f3e60", source = { git = "https://github.com/rltakashige/mlx-jaccl-fix-small-recv.git?branch=address-rdma-gpu-locks#cc3f3e60be1289506125f2fa19b73b05aa770df8" }, marker = "sys_platform == 'darwin' or (extra == 'extra-3-exo-cpu' and extra == 'extra-3-exo-cuda12') or (extra == 'extra-3-exo-cpu' and extra == 'extra-3-exo-cuda13') or (extra == 'extra-3-exo-cuda12' and extra == 'extra-3-exo-cuda13')" },
+    { name = "mlx", version = "0.32.0.dev20260508+df6a7891", source = { git = "https://github.com/rltakashige/mlx-jaccl-fix-small-recv.git?branch=leo%2Forder-distributed-ops#df6a7891226d3262b88fe21a918e4223b552b819" }, marker = "sys_platform == 'darwin' or (extra == 'extra-3-exo-cpu' and extra == 'extra-3-exo-cuda12') or (extra == 'extra-3-exo-cpu' and extra == 'extra-3-exo-cuda13') or (extra == 'extra-3-exo-cuda12' and extra == 'extra-3-exo-cuda13')" },
     { name = "numpy", marker = "sys_platform == 'darwin' or (extra == 'extra-3-exo-cpu' and extra == 'extra-3-exo-cuda12') or (extra == 'extra-3-exo-cpu' and extra == 'extra-3-exo-cuda13') or (extra == 'extra-3-exo-cuda12' and extra == 'extra-3-exo-cuda13')" },
     { name = "opencv-python", marker = "sys_platform == 'darwin' or (extra == 'extra-3-exo-cpu' and extra == 'extra-3-exo-cuda12') or (extra == 'extra-3-exo-cpu' and extra == 'extra-3-exo-cuda13') or (extra == 'extra-3-exo-cuda12' and extra == 'extra-3-exo-cuda13')" },
     { name = "piexif", marker = "sys_platform == 'darwin' or (extra == 'extra-3-exo-cpu' and extra == 'extra-3-exo-cuda12') or (extra == 'extra-3-exo-cpu' and extra == 'extra-3-exo-cuda13') or (extra == 'extra-3-exo-cuda12' and extra == 'extra-3-exo-cuda13')" },
@@ -1263,8 +1295,8 @@ wheels = [
 
 [[package]]
 name = "mlx"
-version = "0.32.0.dev20260427+cc3f3e60"
-source = { git = "https://github.com/rltakashige/mlx-jaccl-fix-small-recv.git?branch=address-rdma-gpu-locks#cc3f3e60be1289506125f2fa19b73b05aa770df8" }
+version = "0.32.0.dev20260508+df6a7891"
+source = { git = "https://github.com/rltakashige/mlx-jaccl-fix-small-recv.git?branch=leo%2Forder-distributed-ops#df6a7891226d3262b88fe21a918e4223b552b819" }
 resolution-markers = [
     "sys_platform == 'darwin'",
 ]
@@ -1315,7 +1347,7 @@ source = { git = "https://github.com/rltakashige/mlx-lm?branch=leo%2Fdeepseek-v4
 dependencies = [
     { name = "jinja2", marker = "sys_platform == 'darwin' or (sys_platform == 'linux' and extra == 'extra-3-exo-cpu') or (sys_platform == 'linux' and extra == 'extra-3-exo-cuda12') or (sys_platform == 'linux' and extra == 'extra-3-exo-cuda13') or (extra == 'extra-3-exo-cpu' and extra == 'extra-3-exo-cuda12') or (extra == 'extra-3-exo-cpu' and extra == 'extra-3-exo-cuda13') or (extra == 'extra-3-exo-cuda12' and extra == 'extra-3-exo-cuda13')" },
     { name = "mlx", version = "0.31.1", source = { registry = "https://pypi.org/simple" }, marker = "(sys_platform == 'linux' and extra == 'extra-3-exo-cpu') or (sys_platform == 'linux' and extra == 'extra-3-exo-cuda12') or (sys_platform == 'linux' and extra == 'extra-3-exo-cuda13') or (extra == 'extra-3-exo-cpu' and extra == 'extra-3-exo-cuda12') or (extra == 'extra-3-exo-cpu' and extra == 'extra-3-exo-cuda13') or (extra == 'extra-3-exo-cuda12' and extra == 'extra-3-exo-cuda13')" },
-    { name = "mlx", version = "0.32.0.dev20260427+cc3f3e60", source = { git = "https://github.com/rltakashige/mlx-jaccl-fix-small-recv.git?branch=address-rdma-gpu-locks#cc3f3e60be1289506125f2fa19b73b05aa770df8" }, marker = "sys_platform == 'darwin' or (extra == 'extra-3-exo-cpu' and extra == 'extra-3-exo-cuda12') or (extra == 'extra-3-exo-cpu' and extra == 'extra-3-exo-cuda13') or (extra == 'extra-3-exo-cuda12' and extra == 'extra-3-exo-cuda13')" },
+    { name = "mlx", version = "0.32.0.dev20260508+df6a7891", source = { git = "https://github.com/rltakashige/mlx-jaccl-fix-small-recv.git?branch=leo%2Forder-distributed-ops#df6a7891226d3262b88fe21a918e4223b552b819" }, marker = "sys_platform == 'darwin' or (extra == 'extra-3-exo-cpu' and extra == 'extra-3-exo-cuda12') or (extra == 'extra-3-exo-cpu' and extra == 'extra-3-exo-cuda13') or (extra == 'extra-3-exo-cuda12' and extra == 'extra-3-exo-cuda13')" },
     { name = "numpy", marker = "sys_platform == 'darwin' or (sys_platform == 'linux' and extra == 'extra-3-exo-cpu') or (sys_platform == 'linux' and extra == 'extra-3-exo-cuda12') or (sys_platform == 'linux' and extra == 'extra-3-exo-cuda13') or (extra == 'extra-3-exo-cpu' and extra == 'extra-3-exo-cuda12') or (extra == 'extra-3-exo-cpu' and extra == 'extra-3-exo-cuda13') or (extra == 'extra-3-exo-cuda12' and extra == 'extra-3-exo-cuda13')" },
     { name = "protobuf", marker = "sys_platform == 'darwin' or (sys_platform == 'linux' and extra == 'extra-3-exo-cpu') or (sys_platform == 'linux' and extra == 'extra-3-exo-cuda12') or (sys_platform == 'linux' and extra == 'extra-3-exo-cuda13') or (extra == 'extra-3-exo-cpu' and extra == 'extra-3-exo-cuda12') or (extra == 'extra-3-exo-cpu' and extra == 'extra-3-exo-cuda13') or (extra == 'extra-3-exo-cuda12' and extra == 'extra-3-exo-cuda13')" },
     { name = "pyyaml", marker = "sys_platform == 'darwin' or (sys_platform == 'linux' and extra == 'extra-3-exo-cpu') or (sys_platform == 'linux' and extra == 'extra-3-exo-cuda12') or (sys_platform == 'linux' and extra == 'extra-3-exo-cuda13') or (extra == 'extra-3-exo-cpu' and extra == 'extra-3-exo-cuda12') or (extra == 'extra-3-exo-cpu' and extra == 'extra-3-exo-cuda13') or (extra == 'extra-3-exo-cuda12' and extra == 'extra-3-exo-cuda13')" },
@@ -1332,7 +1364,7 @@ dependencies = [
     { name = "fastapi", marker = "sys_platform == 'darwin' or (sys_platform == 'linux' and extra == 'extra-3-exo-cpu') or (sys_platform == 'linux' and extra == 'extra-3-exo-cuda12') or (sys_platform == 'linux' and extra == 'extra-3-exo-cuda13') or (extra == 'extra-3-exo-cpu' and extra == 'extra-3-exo-cuda12') or (extra == 'extra-3-exo-cpu' and extra == 'extra-3-exo-cuda13') or (extra == 'extra-3-exo-cuda12' and extra == 'extra-3-exo-cuda13')" },
     { name = "miniaudio", marker = "sys_platform == 'darwin' or (sys_platform == 'linux' and extra == 'extra-3-exo-cpu') or (sys_platform == 'linux' and extra == 'extra-3-exo-cuda12') or (sys_platform == 'linux' and extra == 'extra-3-exo-cuda13') or (extra == 'extra-3-exo-cpu' and extra == 'extra-3-exo-cuda12') or (extra == 'extra-3-exo-cpu' and extra == 'extra-3-exo-cuda13') or (extra == 'extra-3-exo-cuda12' and extra == 'extra-3-exo-cuda13')" },
     { name = "mlx", version = "0.31.1", source = { registry = "https://pypi.org/simple" }, marker = "(sys_platform == 'linux' and extra == 'extra-3-exo-cpu') or (sys_platform == 'linux' and extra == 'extra-3-exo-cuda12') or (sys_platform == 'linux' and extra == 'extra-3-exo-cuda13') or (extra == 'extra-3-exo-cpu' and extra == 'extra-3-exo-cuda12') or (extra == 'extra-3-exo-cpu' and extra == 'extra-3-exo-cuda13') or (extra == 'extra-3-exo-cuda12' and extra == 'extra-3-exo-cuda13')" },
-    { name = "mlx", version = "0.32.0.dev20260427+cc3f3e60", source = { git = "https://github.com/rltakashige/mlx-jaccl-fix-small-recv.git?branch=address-rdma-gpu-locks#cc3f3e60be1289506125f2fa19b73b05aa770df8" }, marker = "sys_platform == 'darwin' or (extra == 'extra-3-exo-cpu' and extra == 'extra-3-exo-cuda12') or (extra == 'extra-3-exo-cpu' and extra == 'extra-3-exo-cuda13') or (extra == 'extra-3-exo-cuda12' and extra == 'extra-3-exo-cuda13')" },
+    { name = "mlx", version = "0.32.0.dev20260508+df6a7891", source = { git = "https://github.com/rltakashige/mlx-jaccl-fix-small-recv.git?branch=leo%2Forder-distributed-ops#df6a7891226d3262b88fe21a918e4223b552b819" }, marker = "sys_platform == 'darwin' or (extra == 'extra-3-exo-cpu' and extra == 'extra-3-exo-cuda12') or (extra == 'extra-3-exo-cpu' and extra == 'extra-3-exo-cuda13') or (extra == 'extra-3-exo-cuda12' and extra == 'extra-3-exo-cuda13')" },
     { name = "mlx-lm", marker = "sys_platform == 'darwin' or (sys_platform == 'linux' and extra == 'extra-3-exo-cpu') or (sys_platform == 'linux' and extra == 'extra-3-exo-cuda12') or (sys_platform == 'linux' and extra == 'extra-3-exo-cuda13') or (extra == 'extra-3-exo-cpu' and extra == 'extra-3-exo-cuda12') or (extra == 'extra-3-exo-cpu' and extra == 'extra-3-exo-cuda13') or (extra == 'extra-3-exo-cuda12' and extra == 'extra-3-exo-cuda13')" },
     { name = "numpy", marker = "sys_platform == 'darwin' or (sys_platform == 'linux' and extra == 'extra-3-exo-cpu') or (sys_platform == 'linux' and extra == 'extra-3-exo-cuda12') or (sys_platform == 'linux' and extra == 'extra-3-exo-cuda13') or (extra == 'extra-3-exo-cpu' and extra == 'extra-3-exo-cuda12') or (extra == 'extra-3-exo-cpu' and extra == 'extra-3-exo-cuda13') or (extra == 'extra-3-exo-cuda12' and extra == 'extra-3-exo-cuda13')" },
     { name = "opencv-python", marker = "sys_platform == 'darwin' or (sys_platform == 'linux' and extra == 'extra-3-exo-cpu') or (sys_platform == 'linux' and extra == 'extra-3-exo-cuda12') or (sys_platform == 'linux' and extra == 'extra-3-exo-cuda13') or (extra == 'extra-3-exo-cpu' and extra == 'extra-3-exo-cuda12') or (extra == 'extra-3-exo-cpu' and extra == 'extra-3-exo-cuda13') or (extra == 'extra-3-exo-cuda12' and extra == 'extra-3-exo-cuda13')" },
@@ -1768,6 +1800,25 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/cb/28/3bfe2fa5a7b9c46fe7e13c97bda14c895fb10fa2ebf1d0abb90e0cea7ee1/platformdirs-4.5.1-py3-none-any.whl", hash = "sha256:d03afa3963c806a9bed9d5125c8f4cb2fdaf74a55ab60e5d59b3fde758104d31", size = 18731, upload-time = "2025-12-05T13:52:56.823Z" },
 ]
 
+[[package]]
+name = "playwright"
+version = "1.58.0"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "greenlet", marker = "sys_platform == 'darwin' or sys_platform == 'linux' or (extra == 'extra-3-exo-cpu' and extra == 'extra-3-exo-cuda12') or (extra == 'extra-3-exo-cpu' and extra == 'extra-3-exo-cuda13') or (extra == 'extra-3-exo-cuda12' and extra == 'extra-3-exo-cuda13')" },
+    { name = "pyee", marker = "sys_platform == 'darwin' or sys_platform == 'linux' or (extra == 'extra-3-exo-cpu' and extra == 'extra-3-exo-cuda12') or (extra == 'extra-3-exo-cpu' and extra == 'extra-3-exo-cuda13') or (extra == 'extra-3-exo-cuda12' and extra == 'extra-3-exo-cuda13')" },
+]
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/f8/c9/9c6061d5703267f1baae6a4647bfd1862e386fbfdb97d889f6f6ae9e3f64/playwright-1.58.0-py3-none-macosx_10_13_x86_64.whl", hash = "sha256:96e3204aac292ee639edbfdef6298b4be2ea0a55a16b7068df91adac077cc606", size = 42251098, upload-time = "2026-01-30T15:09:24.028Z" },
+    { url = "https://files.pythonhosted.org/packages/e0/40/59d34a756e02f8c670f0fee987d46f7ee53d05447d43cd114ca015cb168c/playwright-1.58.0-py3-none-macosx_11_0_arm64.whl", hash = "sha256:70c763694739d28df71ed578b9c8202bb83e8fe8fb9268c04dd13afe36301f71", size = 41039625, upload-time = "2026-01-30T15:09:27.558Z" },
+    { url = "https://files.pythonhosted.org/packages/e1/ee/3ce6209c9c74a650aac9028c621f357a34ea5cd4d950700f8e2c4b7fe2c4/playwright-1.58.0-py3-none-macosx_11_0_universal2.whl", hash = "sha256:185e0132578733d02802dfddfbbc35f42be23a45ff49ccae5081f25952238117", size = 42251098, upload-time = "2026-01-30T15:09:30.461Z" },
+    { url = "https://files.pythonhosted.org/packages/f1/af/009958cbf23fac551a940d34e3206e6c7eed2b8c940d0c3afd1feb0b0589/playwright-1.58.0-py3-none-manylinux1_x86_64.whl", hash = "sha256:c95568ba1eda83812598c1dc9be60b4406dffd60b149bc1536180ad108723d6b", size = 46235268, upload-time = "2026-01-30T15:09:33.787Z" },
+    { url = "https://files.pythonhosted.org/packages/d9/a6/0e66ad04b6d3440dae73efb39540c5685c5fc95b17c8b29340b62abbd952/playwright-1.58.0-py3-none-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:8f9999948f1ab541d98812de25e3a8c410776aa516d948807140aff797b4bffa", size = 45964214, upload-time = "2026-01-30T15:09:36.751Z" },
+    { url = "https://files.pythonhosted.org/packages/0e/4b/236e60ab9f6d62ed0fd32150d61f1f494cefbf02304c0061e78ed80c1c32/playwright-1.58.0-py3-none-win32.whl", hash = "sha256:1e03be090e75a0fabbdaeab65ce17c308c425d879fa48bb1d7986f96bfad0b99", size = 36815998, upload-time = "2026-01-30T15:09:39.627Z" },
+    { url = "https://files.pythonhosted.org/packages/41/f8/5ec599c5e59d2f2f336a05b4f318e733077cd5044f24adb6f86900c3e6a7/playwright-1.58.0-py3-none-win_amd64.whl", hash = "sha256:a2bf639d0ce33b3ba38de777e08697b0d8f3dc07ab6802e4ac53fb65e3907af8", size = 36816005, upload-time = "2026-01-30T15:09:42.449Z" },
+    { url = "https://files.pythonhosted.org/packages/c8/c4/cc0229fea55c87d6c9c67fe44a21e2cd28d1d558a5478ed4d617e9fb0c93/playwright-1.58.0-py3-none-win_arm64.whl", hash = "sha256:32ffe5c303901a13a0ecab91d1c3f74baf73b84f4bedbb6b935f5bc11cc98e1b", size = 33085919, upload-time = "2026-01-30T15:09:45.71Z" },
+]
+
 [[package]]
 name = "pluggy"
 version = "1.6.0"
@@ -1941,6 +1992,18 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/73/7d/f2f9db34af103bea3e09735bb40b021788a5e834c81eedb541991badf8f5/pydantic_core-2.41.5-cp313-cp313-win_arm64.whl", hash = "sha256:3f84d5c1b4ab906093bdc1ff10484838aca54ef08de4afa9de0f5f14d69639cd", size = 1981005, upload-time = "2025-11-04T13:40:54.734Z" },
 ]
 
+[[package]]
+name = "pyee"
+version = "13.0.1"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "typing-extensions", marker = "sys_platform == 'darwin' or sys_platform == 'linux' or (extra == 'extra-3-exo-cpu' and extra == 'extra-3-exo-cuda12') or (extra == 'extra-3-exo-cpu' and extra == 'extra-3-exo-cuda13') or (extra == 'extra-3-exo-cuda12' and extra == 'extra-3-exo-cuda13')" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/8b/04/e7c1fe4dc78a6fdbfd6c337b1c3732ff543b8a397683ab38378447baa331/pyee-13.0.1.tar.gz", hash = "sha256:0b931f7c14535667ed4c7e0d531716368715e860b988770fc7eb8578d1f67fc8", size = 31655, upload-time = "2026-02-14T21:12:28.044Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/a0/c4/b4d4827c93ef43c01f599ef31453ccc1c132b353284fc6c87d535c233129/pyee-13.0.1-py3-none-any.whl", hash = "sha256:af2f8fede4171ef667dfded53f96e2ed0d6e6bd7ee3bb46437f77e3b57689228", size = 15659, upload-time = "2026-02-14T21:12:26.263Z" },
+]
+
 [[package]]
 name = "pygments"
 version = "2.19.2"