Revert state compaction (#1259) (#1275)

## Summary

Reverts the state compaction feature (#1259) to investigate issues with
nodes staying as "unknown" after joining a cluster.

## Test plan

- [ ] Verify nodes properly show up after joining cluster
- [ ] Verify state catchup works correctly without compaction

🤖 Generated with [Claude Code](https://claude.com/claude-code)

app/EXO/EXO/EXOApp.swift

@@ -45,8 +45,8 @@ struct EXOApp: App {
         let thunderboltBridge = ThunderboltBridgeService(clusterStateService: service)
         _thunderboltBridgeService = StateObject(wrappedValue: thunderboltBridge)
         enableLaunchAtLoginIfNeeded()
-        // Remove old LaunchDaemon components if they exist (from previous versions)
-        cleanupLegacyNetworkSetup()
+        // Install LaunchDaemon to disable Thunderbolt Bridge on startup (prevents network loops)
+        NetworkSetupHelper.promptAndInstallIfNeeded()
         // Check local network access periodically (warning disappears when user grants permission)
         localNetwork.startPeriodicChecking(interval: 10)
         controller.scheduleLaunch(after: 15)
@@ -136,36 +136,6 @@ struct EXOApp: App {
         }
     }
 
-    private func cleanupLegacyNetworkSetup() {
-        guard NetworkSetupHelper.hasInstalledComponents() else { return }
-        // Dispatch async to ensure app is ready before showing alert
-        DispatchQueue.main.async {
-            let alert = NSAlert()
-            alert.messageText = "EXO Network Configuration"
-            alert.informativeText =
-                "EXO needs to configure local network discovery on your device. This requires granting permission once."
-            alert.alertStyle = .informational
-            alert.addButton(withTitle: "Continue")
-            alert.addButton(withTitle: "Later")
-
-            let response = alert.runModal()
-            guard response == .alertFirstButtonReturn else {
-                Logger().info("User deferred legacy network setup cleanup")
-                return
-            }
-
-            do {
-                try NetworkSetupHelper.uninstall()
-                Logger().info("Cleaned up legacy network setup components")
-            } catch {
-                // Non-fatal: user may have cancelled admin prompt or cleanup may have
-                // partially succeeded. The app will continue normally.
-                Logger().warning(
-                    "Could not clean up legacy network setup (non-fatal): \(error.localizedDescription)"
-                )
-            }
-        }
-    }
 }
 
 /// Helper for managing EXO's launch-at-login registration

app/EXO/EXO/Services/NetworkSetupHelper.swift

@@ -11,6 +11,68 @@ enum NetworkSetupHelper {
     private static let legacyScriptDestination =
         "/Library/Application Support/EXO/disable_bridge_enable_dhcp.sh"
     private static let plistDestination = "/Library/LaunchDaemons/io.exo.networksetup.plist"
+    private static let requiredStartInterval: Int = 1786
+
+    private static let setupScript = """
+        #!/usr/bin/env bash
+
+        set -euo pipefail
+
+        PREFS="/Library/Preferences/SystemConfiguration/preferences.plist"
+
+        # Remove bridge0 interface
+        ifconfig bridge0 &>/dev/null && {
+          ifconfig bridge0 | grep -q 'member' && {
+            ifconfig bridge0 | awk '/member/ {print $2}' | xargs -n1 ifconfig bridge0 deletem 2>/dev/null || true
+          }
+          ifconfig bridge0 destroy 2>/dev/null || true
+        }
+
+        # Remove Thunderbolt Bridge from VirtualNetworkInterfaces in preferences.plist
+        /usr/libexec/PlistBuddy -c "Delete :VirtualNetworkInterfaces:Bridge:bridge0" "$PREFS" 2>/dev/null || true
+
+        networksetup -listnetworkservices | grep -q "Thunderbolt Bridge" && {
+          networksetup -setnetworkserviceenabled "Thunderbolt Bridge" off
+        } || true
+        """
+
+    /// Prompts user and installs the LaunchDaemon if not already installed.
+    /// Shows an alert explaining what will be installed before requesting admin privileges.
+    static func promptAndInstallIfNeeded() {
+        // Use .utility priority to match NSAppleScript's internal QoS and avoid priority inversion
+        Task.detached(priority: .utility) {
+            // If already correctly installed, skip
+            if daemonAlreadyInstalled() {
+                return
+            }
+
+            // Show alert on main thread
+            let shouldInstall = await MainActor.run {
+                let alert = NSAlert()
+                alert.messageText = "EXO Network Configuration"
+                alert.informativeText =
+                    "EXO needs to install a system service to automatically disable Thunderbolt Bridge on startup. This prevents network loops when connecting multiple Macs via Thunderbolt.\n\nYou will be prompted for your administrator password."
+                alert.alertStyle = .informational
+                alert.addButton(withTitle: "Install")
+                alert.addButton(withTitle: "Not Now")
+                return alert.runModal() == .alertFirstButtonReturn
+            }
+
+            guard shouldInstall else {
+                logger.info("User deferred network setup daemon installation")
+                return
+            }
+
+            do {
+                try installLaunchDaemon()
+                logger.info("Network setup launch daemon installed and started")
+            } catch {
+                logger.error(
+                    "Network setup launch daemon failed: \(error.localizedDescription, privacy: .public)"
+                )
+            }
+        }
+    }
 
     /// Removes all EXO network setup components from the system.
     /// This includes the LaunchDaemon, scripts, logs, and network location.
@@ -30,6 +92,100 @@ enum NetworkSetupHelper {
         return scriptExists || legacyScriptExists || plistExists
     }
 
+    private static func daemonAlreadyInstalled() -> Bool {
+        let manager = FileManager.default
+        let scriptExists = manager.fileExists(atPath: scriptDestination)
+        let plistExists = manager.fileExists(atPath: plistDestination)
+        guard scriptExists, plistExists else { return false }
+        guard
+            let installedScript = try? String(contentsOfFile: scriptDestination, encoding: .utf8),
+            installedScript.trimmingCharacters(in: .whitespacesAndNewlines)
+                == setupScript.trimmingCharacters(in: .whitespacesAndNewlines)
+        else {
+            return false
+        }
+        guard
+            let data = try? Data(contentsOf: URL(fileURLWithPath: plistDestination)),
+            let plist = try? PropertyListSerialization.propertyList(
+                from: data, options: [], format: nil) as? [String: Any]
+        else {
+            return false
+        }
+        guard
+            let interval = plist["StartInterval"] as? Int,
+            interval == requiredStartInterval
+        else {
+            return false
+        }
+        if let programArgs = plist["ProgramArguments"] as? [String],
+            programArgs.contains(scriptDestination) == false
+        {
+            return false
+        }
+        return true
+    }
+
+    private static func installLaunchDaemon() throws {
+        let installerScript = makeInstallerScript()
+        try runShellAsAdmin(installerScript)
+    }
+
+    private static func makeInstallerScript() -> String {
+        """
+        set -euo pipefail
+
+        LABEL="\(daemonLabel)"
+        SCRIPT_DEST="\(scriptDestination)"
+        LEGACY_SCRIPT_DEST="\(legacyScriptDestination)"
+        PLIST_DEST="\(plistDestination)"
+        LOG_OUT="/var/log/\(daemonLabel).log"
+        LOG_ERR="/var/log/\(daemonLabel).err.log"
+
+        # First, completely remove any existing installation
+        launchctl bootout system/"$LABEL" 2>/dev/null || true
+        rm -f "$PLIST_DEST"
+        rm -f "$SCRIPT_DEST"
+        rm -f "$LEGACY_SCRIPT_DEST"
+        rm -f "$LOG_OUT" "$LOG_ERR"
+
+        # Install fresh
+        mkdir -p "$(dirname "$SCRIPT_DEST")"
+
+        cat > "$SCRIPT_DEST" <<'EOF_SCRIPT'
+        \(setupScript)
+        EOF_SCRIPT
+        chmod 755 "$SCRIPT_DEST"
+
+        cat > "$PLIST_DEST" <<'EOF_PLIST'
+        <?xml version="1.0" encoding="UTF-8"?>
+        <!DOCTYPE plist PUBLIC "-//Apple//DTD PLIST 1.0//EN" "http://www.apple.com/DTDs/PropertyList-1.0.dtd">
+        <plist version="1.0">
+        <dict>
+          <key>Label</key>
+          <string>\(daemonLabel)</string>
+          <key>ProgramArguments</key>
+          <array>
+            <string>/bin/bash</string>
+            <string>\(scriptDestination)</string>
+          </array>
+          <key>StartInterval</key>
+          <integer>\(requiredStartInterval)</integer>
+          <key>RunAtLoad</key>
+          <true/>
+          <key>StandardOutPath</key>
+          <string>/var/log/\(daemonLabel).log</string>
+          <key>StandardErrorPath</key>
+          <string>/var/log/\(daemonLabel).err.log</string>
+        </dict>
+        </plist>
+        EOF_PLIST
+
+        launchctl bootstrap system "$PLIST_DEST"
+        launchctl enable system/"$LABEL"
+        launchctl kickstart -k system/"$LABEL"
+        """
+    }
+
     private static func makeUninstallScript() -> String {
         """
         set -euo pipefail

src/exo/master/placement_utils.py

@@ -257,7 +257,13 @@ def _find_ip_prioritised(
     ip_to_type = {
         iface.ip_address: iface.interface_type for iface in other_network.interfaces
     }
-    priority = {"ethernet": 0, "wifi": 1, "unknown": 2, "thunderbolt": 3}
+    priority = {
+        "ethernet": 0,
+        "wifi": 1,
+        "unknown": 2,
+        "maybe_ethernet": 3,
+        "thunderbolt": 4,
+    }
     return min(ips, key=lambda ip: priority.get(ip_to_type.get(ip, "unknown"), 2))
 
 

src/exo/shared/types/profiling.py

@@ -48,7 +48,7 @@ class SystemPerformanceProfile(CamelCaseModel):
     ecpu_usage: float = 0.0
 
 
-InterfaceType = Literal["wifi", "ethernet", "thunderbolt", "unknown"]
+InterfaceType = Literal["wifi", "ethernet", "maybe_ethernet", "thunderbolt", "unknown"]
 
 
 class NetworkInterfaceInfo(CamelCaseModel):

src/exo/utils/info_gatherer/info_gatherer.py

@@ -400,7 +400,7 @@ class InfoGatherer:
             return
         old_nics = []
         while True:
-            nics = get_network_interfaces()
+            nics = await get_network_interfaces()
             if nics != old_nics:
                 old_nics = nics
                 await self.info_sender.send(NodeNetworkInterfaces(ifaces=nics))

src/exo/utils/info_gatherer/system_info.py

@@ -1,6 +1,6 @@
 import socket
 import sys
-from subprocess import CalledProcessError, run
+from subprocess import CalledProcessError
 
 import psutil
 from anyio import run_process
@@ -16,8 +16,7 @@ async def get_friendly_name() -> str:
     """
     hostname = socket.gethostname()
 
-    # TODO: better non mac support
-    if sys.platform != "darwin":  # 'darwin' is the platform name for macOS
+    if sys.platform != "darwin":
         return hostname
 
     try:
@@ -28,21 +27,20 @@ async def get_friendly_name() -> str:
     return process.stdout.decode("utf-8", errors="replace").strip() or hostname
 
 
-def _get_interface_types_from_networksetup() -> dict[str, InterfaceType]:
+async def _get_interface_types_from_networksetup() -> dict[str, InterfaceType]:
     """Parse networksetup -listallhardwareports to get interface types."""
     if sys.platform != "darwin":
         return {}
+
     try:
-        result = run(
-            ["networksetup", "-listallhardwareports"], capture_output=True, text=True
-        )
-    except Exception:
+        result = await run_process(["networksetup", "-listallhardwareports"])
+    except CalledProcessError:
         return {}
 
     types: dict[str, InterfaceType] = {}
     current_type: InterfaceType = "unknown"
 
-    for line in result.stdout.splitlines():
+    for line in result.stdout.decode().splitlines():
         if line.startswith("Hardware Port:"):
             port_name = line.split(":", 1)[1].strip()
             if "Wi-Fi" in port_name:
@@ -55,12 +53,15 @@ def _get_interface_types_from_networksetup() -> dict[str, InterfaceType]:
                 current_type = "unknown"
         elif line.startswith("Device:"):
             device = line.split(":", 1)[1].strip()
+            # enX is ethernet adapters or thunderbolt - these must be deprioritised
+            if device.startswith("en") and device not in ["en0", "en1"]:
+                current_type = "maybe_ethernet"
             types[device] = current_type
 
     return types
 
 
-def get_network_interfaces() -> list[NetworkInterfaceInfo]:
+async def get_network_interfaces() -> list[NetworkInterfaceInfo]:
     """
     Retrieves detailed network interface information on macOS.
     Parses output from 'networksetup -listallhardwareports' and 'ifconfig'
@@ -68,7 +69,7 @@ def get_network_interfaces() -> list[NetworkInterfaceInfo]:
     Returns a list of NetworkInterfaceInfo objects.
     """
     interfaces_info: list[NetworkInterfaceInfo] = []
-    interface_types = _get_interface_types_from_networksetup()
+    interface_types = await _get_interface_types_from_networksetup()
 
     for iface, services in psutil.net_if_addrs().items():
         for service in services:

src/exo/worker/runner/runner.py

@@ -240,10 +240,6 @@ def main(
                             prompt=prompt,
                         )
 
-                        # GPT-OSS specific parsing to match other model formats.
-                        if isinstance(model, GptOssModel):
-                            mlx_generator = parse_gpt_oss(mlx_generator)
-
                         # For other thinking models (GLM, etc.), check if we need to
                         # prepend the thinking tag that was consumed by the chat template
                         if detect_thinking_prompt_suffix(prompt, tokenizer):
@@ -257,10 +253,16 @@ def main(
                             patch_kimi_tokenizer(tokenizer)
 
                         # GLM models need patched parser (upstream has bug with None regex match)
-                        if "glm" in shard_metadata.model_card.model_id.lower():
+                        elif "glm" in shard_metadata.model_card.model_id.lower():
                             patch_glm_tokenizer(tokenizer)
 
-                        if tokenizer.has_tool_calling:
+                        # GPT-OSS specific parsing to match other model formats.
+                        elif isinstance(model, GptOssModel):
+                            mlx_generator = parse_gpt_oss(mlx_generator)
+
+                        if tokenizer.has_tool_calling and not isinstance(
+                            model, GptOssModel
+                        ):
                             assert tokenizer.tool_call_start
                             assert tokenizer.tool_call_end
                             assert tokenizer.tool_parser  # pyright: ignore[reportAny]
@@ -489,9 +491,10 @@ def get_gpt_oss_encoding():
 
 
 def filter_kimi_tokens(
-    responses: Generator[GenerationResponse],
+    responses: Generator[GenerationResponse | ToolCallResponse],
 ) -> Generator[GenerationResponse]:
     for resp in responses:
+        assert isinstance(resp, GenerationResponse)
         if (
             resp.text == "<|tool_calls_section_begin|>"
             or resp.text == "<|tool_calls_section_end|>"
@@ -501,17 +504,44 @@ def filter_kimi_tokens(
 
 
 def parse_gpt_oss(
-    responses: Generator[GenerationResponse],
-) -> Generator[GenerationResponse]:
+    responses: Generator[GenerationResponse | ToolCallResponse],
+) -> Generator[GenerationResponse | ToolCallResponse]:
     encoding = get_gpt_oss_encoding()
     stream = StreamableParser(encoding, role=Role.ASSISTANT)
     thinking = False
+    current_tool_name: str | None = None
+    tool_arg_parts: list[str] = []
 
     for response in responses:
+        assert isinstance(response, GenerationResponse)
         stream.process(response.token)
 
         delta = stream.last_content_delta
         ch = stream.current_channel
+        recipient = stream.current_recipient
+
+        if recipient != current_tool_name:
+            if current_tool_name is not None:
+                prefix = "functions."
+                if current_tool_name.startswith(prefix):
+                    current_tool_name = current_tool_name[len(prefix) :]
+                yield ToolCallResponse(
+                    tool_calls=[
+                        ToolCallItem(
+                            name=current_tool_name,
+                            arguments="".join(tool_arg_parts).strip(),
+                        )
+                    ]
+                )
+                tool_arg_parts = []
+                break
+            current_tool_name = recipient
+
+        # If inside a tool call, accumulate arguments
+        if current_tool_name is not None:
+            if delta:
+                tool_arg_parts.append(delta)
+            continue
 
         if ch == "analysis" and not thinking:
             thinking = True
@@ -528,13 +558,12 @@ def parse_gpt_oss(
             if thinking:
                 yield response.model_copy(update={"text": "</think>"})
             yield response
-            break
 
 
 def parse_thinking_models(
-    responses: Generator[GenerationResponse],
+    responses: Generator[GenerationResponse | ToolCallResponse],
     tokenizer: TokenizerWrapper,
-) -> Generator[GenerationResponse]:
+) -> Generator[GenerationResponse | ToolCallResponse]:
     """
     For models that inject thinking tags in the prompt (like GLM-4.7),
     prepend the thinking tag to the output stream so the frontend
@@ -542,6 +571,9 @@ def parse_thinking_models(
     """
     first = True
     for response in responses:
+        if isinstance(response, ToolCallResponse):
+            yield response
+            continue
         if first:
             first = False
             yield response.model_copy(
@@ -622,7 +654,7 @@ def _process_image_response(
 
 
 def parse_tool_calls(
-    responses: Generator[GenerationResponse],
+    responses: Generator[GenerationResponse | ToolCallResponse],
     tool_call_start: str,
     tool_call_end: str,
     tool_parser: Callable[[str], dict[str, Any] | list[dict[str, Any]]],
@@ -630,6 +662,7 @@ def parse_tool_calls(
     in_tool_call = False
     tool_call_text_parts: list[str] = []
     for response in responses:
+        assert isinstance(response, GenerationResponse)
         # assumption: the tool call start is one token
         if response.text == tool_call_start:
             in_tool_call = True

src/exo/worker/tests/unittests/test_plan/test_download_and_loading.py

@@ -154,7 +154,7 @@ def test_plan_does_not_request_download_when_shard_already_downloaded():
         tasks={},
     )
 
-    assert result is None
+    assert not isinstance(result, plan_mod.DownloadModel)
 
 
 def test_plan_does_not_load_model_until_all_shards_downloaded_globally():