fix local netowork warning

Enable cachix and push to it in the pipeline.yml workflow. This won't
cache a huge amount yet but will automatically extend our caching as we
build more of the repo with Nix in CI. It can also be used by local
users by accepting our cache to improve the speed of local builds.

Test plan:
- CI

.github/workflows/build-app.yml

@@ -1,6 +1,7 @@
 name: Build EXO macOS DMG
 
 on:
+  workflow_dispatch:
   push:
     tags:
       - "v*"
@@ -35,7 +36,7 @@ jobs:
 
       - name: Derive release version from tag
         run: |
-          if [[ "$GITHUB_REF_NAME" == "test-app" ]]; then
+          if [[ "$GITHUB_REF_NAME" == "test-app" || "${{ github.event_name }}" == "workflow_dispatch" ]]; then
             VERSION="0.0.0-alpha.0"
             echo "IS_ALPHA=true" >> $GITHUB_ENV
           else

.github/workflows/pipeline.yml

@@ -20,6 +20,12 @@ jobs:
         with:
           nix_path: nixpkgs=channel:nixos-unstable
 
+      - uses: cachix/cachix-action@v14
+        name: Configure Cachix
+        with:
+          name: exo
+          authToken: "${{ secrets.CACHIX_AUTH_TOKEN }}"
+
       - name: Configure git user
         run: |
           git config --local user.email "github-actions@users.noreply.github.com"
@@ -101,6 +107,12 @@ jobs:
         with:
           nix_path: nixpkgs=channel:nixos-unstable
 
+      - uses: cachix/cachix-action@v14
+        name: Configure Cachix
+        with:
+          name: exo
+          authToken: "${{ secrets.CACHIX_AUTH_TOKEN }}"
+
       - name: Run nix flake check
         run: |
           nix flake check

README.md

@@ -305,7 +305,10 @@ curl -X DELETE http://localhost:52415/instance/YOUR_INSTANCE_ID
 - List all models: `curl http://localhost:52415/models`
 - Inspect instance IDs and deployment state: `curl http://localhost:52415/state`
 
-For further details, see API types and endpoints in [src/exo/master/api.py](src/exo/master/api.py).
+For further details, see:
+
+- API basic documentation in [docs/api.md](docs/api.md).
+- API types and endpoints in [src/exo/master/api.py](src/exo/master/api.py).
 
 ---
 

app/EXO/EXO/ContentView.swift

@@ -56,8 +56,12 @@ struct ContentView: View {
     }
 
     private var shouldShowLocalNetworkWarning: Bool {
+        // Only show warning if:
+        // 1. Local network is not working
+        // 2. EXO is running
+        // 3. We've had a successful connection before (avoids false positive on fresh install)
         if case .notWorking = localNetworkChecker.status {
-            return controller.status != .stopped
+            return controller.status != .stopped && localNetworkChecker.hasWorkedBefore
         }
         return false
     }

app/EXO/EXO/Services/LocalNetworkChecker.swift

@@ -7,6 +7,8 @@ import os.log
 /// macOS local network permission can appear enabled in System Preferences but not
 /// actually work after a restart. This service detects this by creating a UDP
 /// connection to the mDNS multicast address (224.0.0.251:5353).
+///
+/// Only shows warnings if permission previously worked (to avoid false positives on fresh install).
 @MainActor
 final class LocalNetworkChecker: ObservableObject {
     enum Status: Equatable {
@@ -35,10 +37,14 @@ final class LocalNetworkChecker: ObservableObject {
     }
 
     private static let logger = Logger(subsystem: "io.exo.EXO", category: "LocalNetworkChecker")
+    private static let hasWorkedBeforeKey = "LocalNetworkChecker.hasWorkedBefore"
 
     @Published private(set) var status: Status = .unknown
     @Published private(set) var lastConnectionState: String = "none"
 
+    /// True if we've ever had a successful connection (persisted across launches)
+    @Published private(set) var hasWorkedBefore: Bool = UserDefaults.standard.bool(forKey: hasWorkedBeforeKey)
+
     private var connection: NWConnection?
     private var checkTask: Task<Void, Never>?
 
@@ -52,7 +58,14 @@ final class LocalNetworkChecker: ObservableObject {
             guard let self else { return }
             let result = await self.performCheck()
             self.status = result
-            Self.logger.info("Local network check complete: \(result.displayText)")
+
+            // Record success so we can detect regressions on future launches
+            if case .working = result {
+                self.hasWorkedBefore = true
+                UserDefaults.standard.set(true, forKey: Self.hasWorkedBeforeKey)
+            }
+
+            Self.logger.info("Local network check complete: \(result.displayText), hasWorkedBefore: \(self.hasWorkedBefore)")
         }
     }
 

dashboard/src/routes/downloads/+page.svelte

@@ -199,7 +199,13 @@
 					const rawProgress = (downloadPayload as Record<string, unknown>).download_progress
 						?? (downloadPayload as Record<string, unknown>).downloadProgress
 						?? {};
-					const totalBytes = getBytes((rawProgress as Record<string, unknown>).total_bytes ?? (rawProgress as Record<string, unknown>).totalBytes);
+					// For DownloadCompleted, total_bytes is at top level; for DownloadOngoing, it's inside download_progress
+					const totalBytes = getBytes(
+						(downloadPayload as Record<string, unknown>).total_bytes
+						?? (downloadPayload as Record<string, unknown>).totalBytes
+						?? (rawProgress as Record<string, unknown>).total_bytes
+						?? (rawProgress as Record<string, unknown>).totalBytes
+					);
 					const downloadedBytes = getBytes((rawProgress as Record<string, unknown>).downloaded_bytes ?? (rawProgress as Record<string, unknown>).downloadedBytes);
 					const speed = (rawProgress as Record<string, unknown>).speed as number ?? 0;
 					const etaMs = (rawProgress as Record<string, unknown>).eta_ms as number ?? (rawProgress as Record<string, unknown>).etaMs as number ?? 0;
@@ -332,8 +338,13 @@
 								<div class="text-lg font-mono text-white truncate">{node.nodeName}</div>
 								<div class="text-xs text-exo-light-gray font-mono truncate">{node.nodeId}</div>
 							</div>
-							<div class="text-xs font-mono uppercase tracking-wider whitespace-nowrap shrink-0">
-								<span class="text-green-400">{node.models.filter(m => m.status === 'completed').length}</span><span class="text-exo-yellow"> /{node.models.length} models</span>
+							<div class="text-xs font-mono uppercase tracking-wider whitespace-nowrap shrink-0 text-right">
+								<div>
+									<span class="text-green-400">{node.models.filter(m => m.status === 'completed').length}</span><span class="text-exo-yellow"> / {node.models.length} models</span>
+								</div>
+								<div class="text-exo-light-gray normal-case tracking-normal">
+									{formatBytes(node.models.filter(m => m.status === 'completed').reduce((sum, m) => sum + m.totalBytes, 0))} on disk
+								</div>
 							</div>
 						</div>
 
@@ -385,7 +396,7 @@
 								</div>
 
 								<div class="flex items-center justify-between text-xs font-mono text-exo-light-gray">
-									<span>{model.status === 'completed' ? 'Completed' : `${formatSpeed(model.speed)} • ETA ${formatEta(model.etaMs)}`}</span>
+									<span>{model.status === 'completed' ? `Completed (${formatBytes(model.totalBytes)})` : `${formatSpeed(model.speed)} • ETA ${formatEta(model.etaMs)}`}</span>
 									{#if model.status !== 'completed'}
 										<span>{model.files.length} file{model.files.length === 1 ? '' : 's'}</span>
 									{/if}

docs/api.md

@@ -0,0 +1,212 @@
+# EXO API – Technical Reference
+
+This document describes the REST API exposed by the **EXO ** service, as implemented in:
+
+`src/exo/master/api.py`
+
+The API is used to manage model instances in the cluster, inspect cluster state, and perform inference using an OpenAI-compatible interface.
+
+Base URL example:
+
+```
+http://localhost:52415
+```
+
+## 1. General / Meta Endpoints
+
+### Get Master Node ID
+
+**GET** `/node_id`
+
+Returns the identifier of the current master node.
+
+**Response (example):**
+
+```json
+{
+  "node_id": "node-1234"
+}
+```
+
+### Get Cluster State
+
+**GET** `/state`
+
+Returns the current state of the cluster, including nodes and active instances.
+
+**Response:**
+JSON object describing topology, nodes, and instances.
+
+### Get Events
+
+**GET** `/events`
+
+Returns the list of internal events recorded by the master (mainly for debugging and observability).
+
+**Response:**
+Array of event objects.
+
+## 2. Model Instance Management
+
+### Create Instance
+
+**POST** `/instance`
+
+Creates a new model instance in the cluster.
+
+**Request body (example):**
+
+```json
+{
+  "instance": {
+    "model_id": "llama-3.2-1b",
+    "placement": { }
+  }
+}
+```
+
+**Response:**
+JSON description of the created instance.
+
+### Delete Instance
+
+**DELETE** `/instance/{instance_id}`
+
+Deletes an existing instance by ID.
+
+**Path parameters:**
+
+* `instance_id`: string, ID of the instance to delete
+
+**Response:**
+Status / confirmation JSON.
+
+### Get Instance
+
+**GET** `/instance/{instance_id}`
+
+Returns details of a specific instance.
+
+**Path parameters:**
+
+* `instance_id`: string
+
+**Response:**
+JSON description of the instance.
+
+### Preview Placements
+
+**GET** `/instance/previews?model_id=...`
+
+Returns possible placement previews for a given model.
+
+**Query parameters:**
+
+* `model_id`: string, required
+
+**Response:**
+Array of placement preview objects.
+
+### Compute Placement
+
+**GET** `/instance/placement`
+
+Computes a placement for a potential instance without creating it.
+
+**Query parameters (typical):**
+
+* `model_id`: string
+* `sharding`: string or config
+* `instance_meta`: JSON-encoded metadata
+* `min_nodes`: integer
+
+**Response:**
+JSON object describing the proposed placement / instance configuration.
+
+### Place Instance (Dry Operation)
+
+**POST** `/place_instance`
+
+Performs a placement operation for an instance (planning step), without necessarily creating it.
+
+**Request body:**
+JSON describing the instance to be placed.
+
+**Response:**
+Placement result.
+
+## 3. Models
+
+### List Models
+
+**GET** `/models`
+**GET** `/v1/models` (alias)
+
+Returns the list of available models and their metadata.
+
+**Response:**
+Array of model descriptors.
+
+## 4. Inference / Chat Completions
+
+### OpenAI-Compatible Chat Completions
+
+**POST** `/v1/chat/completions`
+
+Executes a chat completion request using an OpenAI-compatible schema. Supports streaming and non-streaming modes.
+
+**Request body (example):**
+
+```json
+{
+  "model": "llama-3.2-1b",
+  "messages": [
+    { "role": "system", "content": "You are a helpful assistant." },
+    { "role": "user", "content": "Hello" }
+  ],
+  "stream": false
+}
+```
+
+**Response:**
+OpenAI-compatible chat completion response.
+
+### Benchmarked Chat Completions
+
+**POST** `/bench/chat/completions`
+
+Same as `/v1/chat/completions`, but also returns performance and generation statistics.
+
+**Request body:**
+Same schema as `/v1/chat/completions`.
+
+**Response:**
+Chat completion plus benchmarking metrics.
+
+## 5. Complete Endpoint Summary
+
+```
+GET     /node_id
+GET     /state
+GET     /events
+
+POST    /instance
+GET     /instance/{instance_id}
+DELETE  /instance/{instance_id}
+
+GET     /instance/previews
+GET     /instance/placement
+POST    /place_instance
+
+GET     /models
+GET     /v1/models
+
+POST    /v1/chat/completions
+POST    /bench/chat/completions
+```
+
+## 6. Notes
+
+* The `/v1/chat/completions` endpoint is compatible with the OpenAI API format, so existing OpenAI clients can be pointed to EXO by changing the base URL.
+* The instance placement endpoints allow you to plan and preview cluster allocations before actually creating instances.
+* The `/events` and `/state` endpoints are primarily intended for operational visibility and debugging.

flake.nix

@@ -16,12 +16,11 @@
     };
   };
 
-  # TODO: figure out caching story
-  # nixConfig = {
-  #   # nix community cachix
-  #   extra-trusted-public-keys = "nix-community.cachix.org-1:mB9FSh9qf2dCimDSUo8Zy7bkq5CX+/rkCWyvRCYg3Fs=";
-  #   extra-substituters = "https://nix-community.cachix.org";
-  # };
+  nixConfig = {
+    # nix community cachix
+    extra-trusted-public-keys = "exo.cachix.org-1:okq7hl624TBeAR3kV+g39dUFSiaZgLRkLsFBCuJ2NZI=";
+    extra-substituters = "https://exo.cachix.org";
+  };
 
   outputs =
     inputs:
@@ -73,6 +72,9 @@
           packages =
             with pkgs;
             [
+              # FORMATTING
+              treefmtEval.config.build.wrapper
+
               # PYTHON
               python313
               uv

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

@@ -2,6 +2,7 @@ from exo.shared.apply import apply_node_download_progress
 from exo.shared.tests.conftest import get_pipeline_shard_metadata
 from exo.shared.types.common import NodeId
 from exo.shared.types.events import NodeDownloadProgress
+from exo.shared.types.memory import Memory
 from exo.shared.types.state import State
 from exo.shared.types.worker.downloads import DownloadCompleted
 from exo.worker.tests.constants import MODEL_A_ID, MODEL_B_ID
@@ -13,6 +14,7 @@ def test_apply_node_download_progress():
     event = DownloadCompleted(
         node_id=NodeId("node-1"),
         shard_metadata=shard1,
+        total_bytes=Memory(),
     )
 
     new_state = apply_node_download_progress(
@@ -28,10 +30,12 @@ def test_apply_two_node_download_progress():
     event1 = DownloadCompleted(
         node_id=NodeId("node-1"),
         shard_metadata=shard1,
+        total_bytes=Memory(),
     )
     event2 = DownloadCompleted(
         node_id=NodeId("node-1"),
         shard_metadata=shard2,
+        total_bytes=Memory(),
     )
     state = State(downloads={NodeId("node-1"): [event1]})
 

src/exo/shared/types/worker/downloads.py

@@ -28,7 +28,7 @@ class DownloadPending(BaseDownloadProgress):
 
 
 class DownloadCompleted(BaseDownloadProgress):
-    pass
+    total_bytes: Memory
 
 
 class DownloadFailed(BaseDownloadProgress):

src/exo/worker/main.py

@@ -217,7 +217,9 @@ class Worker:
                     )
                     if initial_progress.status == "complete":
                         progress = DownloadCompleted(
-                            shard_metadata=shard, node_id=self.node_id
+                            shard_metadata=shard,
+                            node_id=self.node_id,
+                            total_bytes=initial_progress.total_bytes,
                         )
                         self.download_status[shard.model_meta.model_id] = progress
                         await self.event_sender.send(
@@ -364,7 +366,11 @@ class Worker:
             nonlocal self
             nonlocal last_progress_time
             if progress.status == "complete":
-                status = DownloadCompleted(shard_metadata=shard, node_id=self.node_id)
+                status = DownloadCompleted(
+                    shard_metadata=shard,
+                    node_id=self.node_id,
+                    total_bytes=progress.total_bytes,
+                )
                 self.download_status[shard.model_meta.model_id] = status
                 # Footgun!
                 self.event_sender.send_nowait(
@@ -457,7 +463,9 @@ class Worker:
                 ) in self.shard_downloader.get_shard_download_status():
                     if progress.status == "complete":
                         status = DownloadCompleted(
-                            node_id=self.node_id, shard_metadata=progress.shard
+                            node_id=self.node_id,
+                            shard_metadata=progress.shard,
+                            total_bytes=progress.total_bytes,
                         )
                     elif progress.status in ["in_progress", "not_started"]:
                         if progress.downloaded_bytes_this_session.in_bytes == 0:

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

@@ -1,5 +1,6 @@
 import exo.worker.plan as plan_mod
 from exo.shared.types.common import NodeId
+from exo.shared.types.memory import Memory
 from exo.shared.types.models import ModelId
 from exo.shared.types.tasks import LoadModel
 from exo.shared.types.worker.downloads import DownloadCompleted, DownloadProgress
@@ -94,13 +95,23 @@ def test_plan_loads_model_when_all_shards_downloaded_and_waiting():
 
     # Local node has already marked its shard as downloaded (not actually used by _load_model)
     local_download_status = {
-        MODEL_A_ID: DownloadCompleted(shard_metadata=shard1, node_id=NODE_A)
+        MODEL_A_ID: DownloadCompleted(
+            shard_metadata=shard1, node_id=NODE_A, total_bytes=Memory()
+        )
     }
 
     # Global view has completed downloads for both nodes
     global_download_status = {
-        NODE_A: [DownloadCompleted(shard_metadata=shard1, node_id=NODE_A)],
-        NODE_B: [DownloadCompleted(shard_metadata=shard2, node_id=NODE_B)],
+        NODE_A: [
+            DownloadCompleted(
+                shard_metadata=shard1, node_id=NODE_A, total_bytes=Memory()
+            )
+        ],
+        NODE_B: [
+            DownloadCompleted(
+                shard_metadata=shard2, node_id=NODE_B, total_bytes=Memory()
+            )
+        ],
     }
 
     result = plan_mod.plan(
@@ -140,7 +151,9 @@ def test_plan_does_not_request_download_when_shard_already_downloaded():
 
     # Local status claims the shard is downloaded already
     local_download_status = {
-        MODEL_A_ID: DownloadCompleted(shard_metadata=shard, node_id=NODE_A)
+        MODEL_A_ID: DownloadCompleted(
+            shard_metadata=shard, node_id=NODE_A, total_bytes=Memory()
+        )
     }
 
     # Global view hasn't caught up yet (no completed shards recorded for NODE_A)
@@ -192,10 +205,16 @@ def test_plan_does_not_load_model_until_all_shards_downloaded_globally():
 
     # Only NODE_A's shard is recorded as downloaded globally
     local_download_status = {
-        MODEL_A_ID: DownloadCompleted(shard_metadata=shard1, node_id=NODE_A)
+        MODEL_A_ID: DownloadCompleted(
+            shard_metadata=shard1, node_id=NODE_A, total_bytes=Memory()
+        )
     }
     global_download_status = {
-        NODE_A: [DownloadCompleted(shard_metadata=shard1, node_id=NODE_A)],
+        NODE_A: [
+            DownloadCompleted(
+                shard_metadata=shard1, node_id=NODE_A, total_bytes=Memory()
+            )
+        ],
         NODE_B: [],  # NODE_B has no downloads completed yet
     }
 
@@ -212,9 +231,15 @@ def test_plan_does_not_load_model_until_all_shards_downloaded_globally():
     assert result is None
 
     global_download_status = {
-        NODE_A: [DownloadCompleted(shard_metadata=shard1, node_id=NODE_A)],
+        NODE_A: [
+            DownloadCompleted(
+                shard_metadata=shard1, node_id=NODE_A, total_bytes=Memory()
+            )
+        ],
         NODE_B: [
-            DownloadCompleted(shard_metadata=shard2, node_id=NODE_B)
+            DownloadCompleted(
+                shard_metadata=shard2, node_id=NODE_B, total_bytes=Memory()
+            )
         ],  # NODE_B has no downloads completed yet
     }