fix chat completions call_

.dockerignore

@@ -1,15 +0,0 @@
-.venv/
-.direnv/
-target/
-.git/
-.idea/
-.pytest_cache/
-.ruff_cache/
-dashboard/node_modules/
-dashboard/.svelte-kit/
-dashboard/build/
-dist/
-*.pdb
-**/__pycache__
-**/.DS_Store
-.mlx_typings/

.github/workflows/build-app.yml

@@ -396,7 +396,7 @@ jobs:
           path: output/EXO-${{ env.RELEASE_VERSION }}.dmg
 
       - name: Upload to S3
-        if: env.SPARKLE_S3_BUCKET != ''
+        if: env.SPARKLE_S3_BUCKET != '' && github.ref_type == 'tag'
         env:
           AWS_ACCESS_KEY_ID: ${{ secrets.AWS_ACCESS_KEY_ID }}
           AWS_SECRET_ACCESS_KEY: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
@@ -412,12 +412,6 @@ jobs:
             PREFIX="${PREFIX}/"
           fi
           DMG_NAME="EXO-${RELEASE_VERSION}.dmg"
-
-          if [[ "${{ github.ref_type }}" != "tag" ]]; then
-            aws s3 cp "$DMG_NAME" "s3://${SPARKLE_S3_BUCKET}/${PREFIX}EXO-${GITHUB_SHA}.dmg"
-            exit 0
-          fi
-
           aws s3 cp "$DMG_NAME" "s3://${SPARKLE_S3_BUCKET}/${PREFIX}${DMG_NAME}"
           if [[ "$IS_ALPHA" != "true" ]]; then
             aws s3 cp "$DMG_NAME" "s3://${SPARKLE_S3_BUCKET}/${PREFIX}EXO-latest.dmg"

.github/workflows/e2e.yml

@@ -1,44 +0,0 @@
-name: e2e-tests
-
-on:
-  push:
-    branches:
-      - e2e-tests
-  pull_request:
-    branches:
-      - staging
-      - main
-
-jobs:
-  e2e:
-    runs-on: ubuntu-latest
-    timeout-minutes: 45
-    steps:
-      - name: Free up disk space
-        run: |
-          sudo rm -rf /usr/share/dotnet /usr/local/lib/android /opt/ghc \
-            /opt/hostedtoolcache /usr/local/share/boost /usr/share/swift \
-            /opt/microsoft /opt/az
-          docker system prune -af
-          df -h /
-
-      - name: Checkout repository
-        uses: actions/checkout@v4
-        with:
-          lfs: false
-
-      - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v3
-
-      - name: Build E2E image with cache
-        uses: docker/build-push-action@v6
-        with:
-          context: .
-          file: e2e/Dockerfile
-          tags: exo-e2e:latest
-          load: true
-          cache-from: type=gha
-          cache-to: type=gha,mode=max
-
-      - name: Run E2E tests
-        run: python3 e2e/run_all.py

.github/workflows/pipeline.yml

@@ -8,6 +8,33 @@ on:
       - main
 
 jobs:
+  typecheck:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+        with:
+          lfs: false
+
+      - uses: cachix/install-nix-action@v31
+        with:
+          nix_path: nixpkgs=channel:nixos-unstable
+
+      - uses: cachix/cachix-action@v14
+        name: Configure Cachix
+        with:
+          name: exo
+          authToken: "${{ secrets.CACHIX_AUTH_TOKEN }}"
+
+      - name: Load nix develop environment
+        run: nix run github:nicknovitski/nix-develop/v1
+
+      - name: Sync dependencies
+        run: uv sync --all-packages
+
+      - name: Run type checker
+        run: uv run basedpyright --project pyproject.toml
+
   nix:
     name: Build and check (${{ matrix.system }})
     runs-on: ${{ matrix.runner }}

.mlx_typings/mlx/core/__init__.pyi

@@ -2366,7 +2366,7 @@ class custom_function:
 def default_device() -> Device:
     """Get the default device."""
 
-def default_stream(device: Device | DeviceType) -> Stream:
+def default_stream(device: Device) -> Stream:
     """Get the device's default stream."""
 
 def degrees(a: array, /, *, stream: Stream | Device | None = ...) -> array:

.mlx_typings/mlx_lm/models/step3p5.pyi

@@ -1,151 +0,0 @@
-from dataclasses import dataclass
-from typing import Any, Dict, List, Optional
-
-import mlx.core as mx
-import mlx.nn as nn
-
-from .base import BaseModelArgs
-from .switch_layers import SwitchGLU
-
-@dataclass
-class ModelArgs(BaseModelArgs):
-    model_type: str
-    hidden_size: int
-    num_hidden_layers: int
-    vocab_size: int
-    num_attention_heads: int
-    num_attention_groups: int
-    head_dim: int
-    intermediate_size: int
-    rms_norm_eps: float
-    rope_theta: float
-    rope_scaling: Optional[Dict[str, Any]]
-    max_position_embeddings: int
-    sliding_window: int
-    layer_types: Optional[List[str]]
-    yarn_only_types: Optional[List[str]]
-    partial_rotary_factors: Optional[List[float]]
-    attention_other_setting: Optional[Dict[str, Any]]
-    use_head_wise_attn_gate: bool
-    moe_num_experts: int
-    moe_top_k: int
-    moe_intermediate_size: int
-    share_expert_dim: int
-    moe_layers_enum: Optional[str]
-    moe_router_scaling_factor: float
-    norm_expert_weight: bool
-    swiglu_limits: Optional[List[float]]
-    swiglu_limits_shared: Optional[List[float]]
-    tie_word_embeddings: bool
-
-class Step3p5MLP(nn.Module):
-    hidden_size: int
-    intermediate_size: int
-    gate_proj: nn.Linear
-    up_proj: nn.Linear
-    down_proj: nn.Linear
-    limit: Optional[float]
-
-    def __init__(
-        self, args: ModelArgs, intermediate_size: int, swiglu_limit: float = 0
-    ) -> None: ...
-    def __call__(self, x: mx.array) -> mx.array: ...
-
-class Step3p5MoEGate(nn.Module):
-    top_k: int
-    n_routed_experts: int
-    routed_scaling_factor: float
-    norm_topk_prob: bool
-    gate: nn.Linear
-    router_bias: mx.array
-
-    def __init__(self, args: ModelArgs) -> None: ...
-    def __call__(self, x: mx.array) -> tuple[mx.array, mx.array]: ...
-
-class Step3p5MoE(nn.Module):
-    gate: Step3p5MoEGate
-    switch_mlp: SwitchGLU
-    share_expert: Step3p5MLP
-    sharding_group: Optional[mx.distributed.Group]
-
-    def __init__(self, args: ModelArgs, layer_idx: int) -> None: ...
-    def __call__(self, x: mx.array) -> mx.array: ...
-
-class Step3p5Attention(nn.Module):
-    is_sliding: bool
-    num_heads: int
-    num_kv_heads: int
-    head_dim: int
-    scale: float
-    q_proj: nn.Linear
-    k_proj: nn.Linear
-    v_proj: nn.Linear
-    o_proj: nn.Linear
-    q_norm: nn.Module
-    k_norm: nn.Module
-    use_head_wise_attn_gate: bool
-    g_proj: nn.Linear
-    rope: nn.Module
-
-    def __init__(self, args: ModelArgs, layer_idx: int) -> None: ...
-    def __call__(
-        self,
-        x: mx.array,
-        mask: Optional[mx.array] = None,
-        cache: Optional[Any] = None,
-    ) -> mx.array: ...
-
-class Step3p5DecoderLayer(nn.Module):
-    self_attn: Step3p5Attention
-    is_sliding: bool
-    is_moe_layer: bool
-    mlp: Step3p5MLP | Step3p5MoE
-    input_layernorm: nn.Module
-    post_attention_layernorm: nn.Module
-
-    def __init__(self, args: ModelArgs, layer_idx: int) -> None: ...
-    def __call__(
-        self,
-        x: mx.array,
-        mask: Optional[mx.array] = None,
-        cache: Optional[Any] = None,
-    ) -> mx.array: ...
-
-class Step3p5Model(nn.Module):
-    args: ModelArgs
-    vocab_size: int
-    num_layers: int
-    embed_tokens: nn.Embedding
-    layers: list[Step3p5DecoderLayer]
-    norm: nn.Module
-    _swa_idx: Optional[int]
-    _full_idx: Optional[int]
-
-    def __init__(self, args: ModelArgs) -> None: ...
-    def __call__(
-        self,
-        x: mx.array,
-        cache: Optional[List[Any]] = None,
-    ) -> mx.array: ...
-
-class Model(nn.Module):
-    args: ModelArgs
-    model_type: str
-    model: Step3p5Model
-    lm_head: nn.Linear
-
-    def __init__(self, args: ModelArgs) -> None: ...
-    def __call__(
-        self,
-        inputs: mx.array,
-        cache: Optional[List[Any]] = None,
-    ) -> mx.array: ...
-    def sanitize(self, weights: dict[str, Any]) -> dict[str, Any]: ...
-    def shard(self, group: Optional[mx.distributed.Group] = None) -> None: ...
-    @property
-    def layers(self) -> list[Step3p5DecoderLayer]: ...
-    def make_cache(self) -> list[Any]: ...
-    @property
-    def cast_predicate(self) -> Any: ...
-    @property
-    def quant_predicate(self) -> Any: ...

AGENTS.md

@@ -119,78 +119,3 @@ From .cursorrules:
 ## Testing
 
 Tests use pytest-asyncio with `asyncio_mode = "auto"`. Tests are in `tests/` subdirectories alongside the code they test. The `EXO_TESTS=1` env var is set during tests.
-
-## Dashboard UI Testing & Screenshots
-
-### Building and Running the Dashboard
-```bash
-# Build the dashboard (must be done before running exo)
-cd dashboard && npm install && npm run build && cd ..
-
-# Start exo (serves the dashboard at http://localhost:52415)
-uv run exo &
-sleep 8  # Wait for server to start
-```
-
-### Taking Headless Screenshots with Playwright
-Use Playwright with headless Chromium for programmatic screenshots — no manual browser interaction needed.
-
-**Setup (one-time):**
-```bash
-npx --yes playwright install chromium
-cd /tmp && npm init -y && npm install playwright
-```
-
-**Taking screenshots:**
-```javascript
-// Run from /tmp where playwright is installed: cd /tmp && node -e "..."
-const { chromium } = require('playwright');
-(async () => {
-  const browser = await chromium.launch({ headless: true });
-  const page = await browser.newPage({ viewport: { width: 1280, height: 800 } });
-  await page.goto('http://localhost:52415', { waitUntil: 'networkidle' });
-  await page.waitForTimeout(2000);
-
-  // Inject test data into localStorage if needed (e.g., recent models)
-  await page.evaluate(() => {
-    localStorage.setItem('exo-recent-models', JSON.stringify([
-      { modelId: 'mlx-community/Qwen3-30B-A3B-4bit', launchedAt: Date.now() },
-    ]));
-  });
-  await page.reload({ waitUntil: 'networkidle' });
-  await page.waitForTimeout(2000);
-
-  // Interact with UI elements
-  await page.locator('text=SELECT MODEL').click();
-  await page.waitForTimeout(1000);
-
-  // Take screenshot
-  await page.screenshot({ path: '/tmp/screenshot.png', fullPage: false });
-  await browser.close();
-})();
-```
-
-### Uploading Images to GitHub PRs
-GitHub's API doesn't support direct image upload for PR comments. Workaround:
-
-1. **Commit images to the branch** (temporarily):
-   ```bash
-   cp /tmp/screenshot.png .
-   git add screenshot.png
-   git commit -m "temp: add screenshots for PR"
-   git push origin <branch>
-   COMMIT_SHA=$(git rev-parse HEAD)
-   ```
-
-2. **Post PR comment** referencing the raw image URL (uses permanent commit SHA so images survive deletion):
-   ```bash
-   gh pr comment <PR_NUMBER> --body "![Screenshot](https://raw.githubusercontent.com/exo-explore/exo/${COMMIT_SHA}/screenshot.png)"
-   ```
-
-3. **Remove the images** from the branch:
-   ```bash
-   git rm screenshot.png
-   git commit -m "chore: remove temporary screenshot files"
-   git push origin <branch>
-   ```
-   The images still render in the PR comment because they reference the permanent commit SHA.

Cargo.lock

@@ -353,6 +353,31 @@ dependencies = [
  "generic-array",
 ]
 
+[[package]]
+name = "bon"
+version = "3.8.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ebeb9aaf9329dff6ceb65c689ca3db33dbf15f324909c60e4e5eef5701ce31b1"
+dependencies = [
+ "bon-macros",
+ "rustversion",
+]
+
+[[package]]
+name = "bon-macros"
+version = "3.8.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "77e9d642a7e3a318e37c2c9427b5a6a48aa1ad55dcd986f3034ab2239045a645"
+dependencies = [
+ "darling",
+ "ident_case",
+ "prettyplease",
+ "proc-macro2",
+ "quote",
+ "rustversion",
+ "syn 2.0.111",
+]
+
 [[package]]
 name = "bs58"
 version = "0.5.1"
@@ -675,6 +700,41 @@ dependencies = [
  "syn 2.0.111",
 ]
 
+[[package]]
+name = "darling"
+version = "0.21.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9cdf337090841a411e2a7f3deb9187445851f91b309c0c0a29e05f74a00a48c0"
+dependencies = [
+ "darling_core",
+ "darling_macro",
+]
+
+[[package]]
+name = "darling_core"
+version = "0.21.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1247195ecd7e3c85f83c8d2a366e4210d588e802133e1e355180a9870b517ea4"
+dependencies = [
+ "fnv",
+ "ident_case",
+ "proc-macro2",
+ "quote",
+ "strsim",
+ "syn 2.0.111",
+]
+
+[[package]]
+name = "darling_macro"
+version = "0.21.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d38308df82d1080de0afee5d069fa14b0326a88c14f15c5ccda35b4a6c414c81"
+dependencies = [
+ "darling_core",
+ "quote",
+ "syn 2.0.111",
+]
+
 [[package]]
 name = "data-encoding"
 version = "2.9.0"
@@ -1565,6 +1625,12 @@ dependencies = [
  "zerovec",
 ]
 
+[[package]]
+name = "ident_case"
+version = "1.0.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b9e0384b61958566e926dc50660321d12159025e767c18e043daf26b70104c39"
+
 [[package]]
 name = "idna"
 version = "1.1.0"
@@ -1679,6 +1745,15 @@ dependencies = [
  "generic-array",
 ]
 
+[[package]]
+name = "internment"
+version = "0.8.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "636d4b0f6a39fd684effe2a73f5310df16a3fa7954c26d36833e98f44d1977a2"
+dependencies = [
+ "hashbrown 0.15.5",
+]
+
 [[package]]
 name = "inventory"
 version = "0.3.21"
@@ -3232,6 +3307,16 @@ dependencies = [
  "zerocopy",
 ]
 
+[[package]]
+name = "prettyplease"
+version = "0.2.37"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "479ca8adacdd7ce8f1fb39ce9ecccbfe93a3f1344b3d0d97f20bc0196208f62b"
+dependencies = [
+ "proc-macro2",
+ "syn 2.0.111",
+]
+
 [[package]]
 name = "primeorder"
 version = "0.13.6"
@@ -3655,6 +3740,12 @@ dependencies = [
  "yasna",
 ]
 
+[[package]]
+name = "recursion"
+version = "0.5.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9dba2197bf7b1d87b4dd460c195f4edeb45a94e82e8054f8d5f317c1f0e93ca1"
+
 [[package]]
 name = "redox_syscall"
 version = "0.5.18"
@@ -4716,6 +4807,15 @@ checksum = "06abde3611657adf66d383f00b093d7faecc7fa57071cce2578660c9f1010821"
 [[package]]
 name = "util"
 version = "0.0.1"
+dependencies = [
+ "bon",
+ "derive_more",
+ "extend",
+ "internment",
+ "once_cell",
+ "recursion",
+ "thiserror 2.0.17",
+]
 
 [[package]]
 name = "uuid"

MISSED_THINGS.md

@@ -5,21 +5,21 @@
 [X] Fetching download status of all models on start
 [X] Deduplication of tasks in plan_step.
 [X] resolve_allow_patterns should just be wildcard now.
-[X] no mx_barrier in genreate.py mlx_generate at the end.
+[] no mx_barrier in genreate.py mlx_generate at the end.
 [] cache assertion not needed in auto_parallel.py PipelineLastLayer.
-[X] GPTOSS support dropped in auto_parallel.py.
-[X] sharding changed "all-to-sharded" became _all_to_sharded in auto_parallel.py.
-[X] same as above with "sharded-to-all" became _sharded_to_all in auto_parallel.py.
-[X] Dropped support for Ministral3Model, DeepseekV32Model, Glm4MoeModel, Qwen3NextModel, GptOssMode in auto_parallel.py.
+[] GPTOSS support dropped in auto_parallel.py.
+[] sharding changed "all-to-sharded" became _all_to_sharded in auto_parallel.py.
+[] same as above with "sharded-to-all" became _sharded_to_all in auto_parallel.py.
+[] Dropped support for Ministral3Model, DeepseekV32Model, Glm4MoeModel, Qwen3NextModel, GptOssMode in auto_parallel.py.
 [] Dropped prefill/decode code in auto_parallel.py and utils_mlx.py.
 [X] KV_CACHE_BITS should be None to disable quantized KV cache.
-[X] Dropped _set_nofile_limit in utils_mlx.py.
-[X] We have group optional in load_mlx_items in utils_mlx.py.
-[X] Dropped add_missing_chat_templates for GptOss in load_mlx_items in utils_mlx.py.
-[X] Dropped model.make_cache in make_kv_cache in utils_mlx.py.
+[] Dropped _set_nofile_limit in utils_mlx.py.
+[] We have group optional in load_mlx_items in utils_mlx.py.
+[] Dropped add_missing_chat_templates for GptOss in load_mlx_items in utils_mlx.py.
+[] Dropped model.make_cache in make_kv_cache in utils_mlx.py.
 [X] We put cache limit back in utils_mlx.py.
-[X] topology.py remove_node removes the connections after checking if node is is in self._node_id_to_rx_id_map. on beta_1 it checks after, so would remove stale connections I guess?
-[X] Missing Glm 4.7 model cards (this isn't ready yet but should be picked up, probably create an issue... the blocker is transforemrs version doesn't support the tokenizer for Glm 4.7. rc-1 does but we can't upgrade as it breaks other things.)
+[] topology.py remove_node removes the connections after checking if node is is in self._node_id_to_rx_id_map. on beta_1 it checks after, so would remove stale connections I guess?
+[] Missing Glm 4.7 model cards (this isn't ready yet but should be picked up, probably create an issue... the blocker is transforemrs version doesn't support the tokenizer for Glm 4.7. rc-1 does but we can't upgrade as it breaks other things.)
 [] try-except in _command_processor only excepts ValueError. This was silently failing leading to un-debuggable errors (we had a KeyError that was happening ). Changed this to catch Exception instead of ValueError. See exo-v2 89ae38405e0052e3c22405daf094b065878aa873 and fb99fea69b5a39017efc90c5dad0072e677455f0.
 [X] In placement.py, place_instance no longer looks at model_meta.supports_tensor and check if this tensor parallel number of nodes is supported by the model's tensor dimensions.
 [X] In placement.py, place_instanec, we no longer have the special case to exclude DeepSeek v3.1 pipeline parallel (it doesn't work).

TODO.md

@@ -1,14 +1,28 @@
+2. Currently a lot of requests from the API are timing out, but we still process those requests internally. If an API request times out, we should cancel all corresponding tasks to that API request (why process a request with nobody listening).
 3. Task cancellation. When API http request gets cancelled, it should cancel corresponding task.
 4. I'd like to see profiled network latency / bandwidth.
 5. I'd like to see how much bandwidth each link is using.
+6. We should handle the case where one machine doesn't have the model downloaded and then other machines are waiting on it. In this case we get loads of timeout errors because the others are waiting for the one that needs to download the model.
 7. Solve the problem of in continuous batching when a new prompt comes in, it will block decode of the current batch until the prefill is complete.
 8. We want people to be able to copy models over to a new device without ever connecting EXO to the internet. Right now EXO require internet connection once to cache some files to check if a download is complete. Instead, we should simply check if there is a non-empty model folder locally with no .partial files. This indicates it's a fully downloaded model that can be loaded.
+10. More granular control over how to deploy instances.
+12. Nix is great but installing it is a pain and we have ended up in a lot of cases having PATH issues or installation issues. For example, after rebooting mike it seemed to no longer have a nix installation and needed reinstalling. It has a bunch of broken symlinks left over from nix that caused ssh to fail, making it even harder to debug. We need consistent environments (perhaps MDM) so we can guarantee nix is installed properly on each machine.
 13. Memory pressure instead of memory used.
 14. Show the type of each connection (TB5, Ethernet, etc.) in the UI. Refer to old exo: https://github.com/exo-explore/exo/blob/56f783b38dc6b08ce606b07a5386dc40dae00330/exo/helpers.py#L251
 15. Prioritise certain connection types (or by latency). TB5 > Ethernet > WiFi. Refer to old exo: https://github.com/exo-explore/exo/blob/56f783b38dc6b08ce606b07a5386dc40dae00330/exo/helpers.py#L251
 16. Dynamically switch to higher priority connection when it becomes available. Probably bring back InstanceReplacedAtomically.
 17. Faster model loads by streaming model from other devices in cluster.
 18. Add support for specifying the type of network connection to use in a test. Depends on 15/16.
+20. Add chat completion cancellations (e.g OpenWebUI has something for cancelling an ongoing request).
+23. Do we need cache_limit? We went back and forth on that a lot because we thought it might be causing issues. One problem is it sets it relative to model size. So if you have multiple models loaded in it will take the most recent model size for the cache_limit. This is problematic if you launch DeepSeek -> Llama for example.
+24. further openai/lmstudio api compatibility
 25. Rethink retry logic
+26. Task cancellation. When API http request gets cancelled, it should cancel corresponding task.
 27. Log cleanup - per-module log filters and default to DEBUG log levels
 28. Validate RDMA connections with ibv_devinfo in the info gatherer
+
+Potential refactors:
+
+2. Topology can be simplified
+
+Random errors we've run into:

app/EXO/EXO/ContentView.swift

@@ -563,45 +563,21 @@ struct ContentView: View {
     }
 
     private var rdmaStatusView: some View {
-        let rdmaStatuses = stateService.latestSnapshot?.nodeRdmaCtl ?? [:]
-        let localNodeId = stateService.localNodeId
-        let nodeProfiles = stateService.latestSnapshot?.nodeProfiles ?? [:]
-        let localDevices = networkStatusService.status.localRdmaDevices
-        let localPorts = networkStatusService.status.localRdmaActivePorts
-
+        let rdma = networkStatusService.status.rdmaStatus
         return VStack(alignment: .leading, spacing: 1) {
-            if rdmaStatuses.isEmpty {
-                Text("Cluster RDMA: No data")
-                    .font(.caption2)
-                    .foregroundColor(.secondary)
-            } else {
-                Text("Cluster RDMA Status:")
-                    .font(.caption2)
-                    .foregroundColor(.secondary)
-                ForEach(Array(rdmaStatuses.keys.sorted()), id: \.self) { nodeId in
-                    if let status = rdmaStatuses[nodeId] {
-                        let nodeName =
-                            nodeProfiles[nodeId]?.friendlyName ?? String(nodeId.prefix(8))
-                        let isLocal = nodeId == localNodeId
-                        let prefix = isLocal ? "  \(nodeName) (local):" : "  \(nodeName):"
-                        let statusText = status.enabled ? "Enabled" : "Disabled"
-                        let color: Color = status.enabled ? .green : .orange
-                        Text("\(prefix) \(statusText)")
-                            .font(.caption2)
-                            .foregroundColor(color)
-                    }
-                }
-            }
-            if !localDevices.isEmpty {
-                Text("  Local Devices: \(localDevices.joined(separator: ", "))")
+            Text("RDMA: \(rdmaStatusText(rdma))")
+                .font(.caption2)
+                .foregroundColor(rdmaStatusColor(rdma))
+            if !rdma.devices.isEmpty {
+                Text("  Devices: \(rdma.devices.joined(separator: ", "))")
                     .font(.caption2)
                     .foregroundColor(.secondary)
             }
-            if !localPorts.isEmpty {
-                Text("  Local Active Ports:")
+            if !rdma.activePorts.isEmpty {
+                Text("  Active Ports:")
                     .font(.caption2)
                     .foregroundColor(.secondary)
-                ForEach(localPorts, id: \.device) { port in
+                ForEach(rdma.activePorts, id: \.device) { port in
                     Text("    \(port.device) port \(port.port): \(port.state)")
                         .font(.caption2)
                         .foregroundColor(.green)
@@ -610,6 +586,28 @@ struct ContentView: View {
         }
     }
 
+    private func rdmaStatusText(_ rdma: RDMAStatus) -> String {
+        switch rdma.rdmaCtlEnabled {
+        case .some(true):
+            return "Enabled"
+        case .some(false):
+            return "Disabled"
+        case nil:
+            return rdma.devices.isEmpty ? "Not Available" : "Available"
+        }
+    }
+
+    private func rdmaStatusColor(_ rdma: RDMAStatus) -> Color {
+        switch rdma.rdmaCtlEnabled {
+        case .some(true):
+            return .green
+        case .some(false):
+            return .orange
+        case nil:
+            return rdma.devices.isEmpty ? .secondary : .green
+        }
+    }
+
     private var sendBugReportButton: some View {
         VStack(alignment: .leading, spacing: 4) {
             Button {

app/EXO/EXO/ExoProcessController.swift

@@ -28,10 +28,6 @@ final class ExoProcessController: ObservableObject {
         }
     }
 
-    static let exoDirectoryURL: URL = {
-        URL(fileURLWithPath: NSHomeDirectory()).appendingPathComponent(".exo")
-    }()
-
     @Published private(set) var status: Status = .stopped
     @Published private(set) var lastError: String?
     @Published private(set) var launchCountdownSeconds: Int?
@@ -82,11 +78,7 @@ final class ExoProcessController: ObservableObject {
 
             let child = Process()
             child.executableURL = executableURL
-            let exoHomeURL = Self.exoDirectoryURL
-            try? FileManager.default.createDirectory(
-                at: exoHomeURL, withIntermediateDirectories: true
-            )
-            child.currentDirectoryURL = exoHomeURL
+            child.currentDirectoryURL = runtimeURL
             child.environment = makeEnvironment(for: runtimeURL)
 
             child.standardOutput = FileHandle.nullDevice

app/EXO/EXO/Models/ClusterState.swift

@@ -15,7 +15,6 @@ struct ClusterState: Decodable {
     let nodeMemory: [String: MemoryInfo]
     let nodeSystem: [String: SystemInfo]
     let nodeThunderboltBridge: [String: ThunderboltBridgeStatus]
-    let nodeRdmaCtl: [String: NodeRdmaCtlStatus]
 
     /// Computed property for backwards compatibility - merges granular state into NodeProfile
     var nodeProfiles: [String: NodeProfile] {
@@ -66,10 +65,6 @@ struct ClusterState: Decodable {
             try container.decodeIfPresent(
                 [String: ThunderboltBridgeStatus].self, forKey: .nodeThunderboltBridge
             ) ?? [:]
-        self.nodeRdmaCtl =
-            try container.decodeIfPresent(
-                [String: NodeRdmaCtlStatus].self, forKey: .nodeRdmaCtl
-            ) ?? [:]
     }
 
     private enum CodingKeys: String, CodingKey {
@@ -83,7 +78,6 @@ struct ClusterState: Decodable {
         case nodeMemory
         case nodeSystem
         case nodeThunderboltBridge
-        case nodeRdmaCtl
     }
 }
 
@@ -165,10 +159,6 @@ struct ThunderboltBridgeStatus: Decodable {
     let serviceName: String?
 }
 
-struct NodeRdmaCtlStatus: Decodable {
-    let enabled: Bool
-}
-
 struct MemoryInfo: Decodable {
     let ramTotal: MemoryValue?
     let ramAvailable: MemoryValue?

app/EXO/EXO/Services/BugReportService.swift

@@ -44,12 +44,16 @@ struct BugReportService {
         let dayPrefix = Self.dayPrefixString(now)
         let prefix = "reports/\(dayPrefix)/\(timestamp)/"
 
-        let logFiles = readAllLogs()
+        let logData = readLog()
         let ifconfigText = try await captureIfconfig()
         let hostName = Host.current().localizedName ?? "unknown"
         let debugInfo = readDebugInfo()
 
-        let stateData = try await fetch(url: baseURL.appendingPathComponent("state"))
+        async let stateResult = fetch(url: baseURL.appendingPathComponent("state"))
+        async let eventsResult = fetch(url: baseURL.appendingPathComponent("events"))
+
+        let stateData = try await stateResult
+        let eventsData = try await eventsResult
 
         // Extract cluster TB bridge status from exo state
         let clusterTbBridgeStatus = extractClusterTbBridgeStatus(from: stateData)
@@ -63,19 +67,12 @@ struct BugReportService {
             clusterTbBridgeStatus: clusterTbBridgeStatus
         )
 
-        let eventLogFiles = readAllEventLogs()
-
-        var uploads: [(path: String, data: Data?)] = logFiles.map { (path, data) in
-            ("\(prefix)\(path)", data)
-        }
-        uploads.append(
-            contentsOf: eventLogFiles.map { (path, data) in
-                ("\(prefix)\(path)", data as Data?)
-            })
-        uploads.append(contentsOf: [
+        let uploads: [(path: String, data: Data?)] = [
+            ("\(prefix)exo.log", logData),
             ("\(prefix)state.json", stateData),
+            ("\(prefix)events.json", eventsData),
             ("\(prefix)report.json", reportJSON),
-        ])
+        ]
 
         let uploadItems: [(key: String, body: Data)] = uploads.compactMap { item in
             guard let body = item.data else { return nil }
@@ -152,40 +149,11 @@ struct BugReportService {
         return decoded.urls
     }
 
-    private func readAllLogs() -> [(path: String, data: Data)] {
-        let dir = URL(fileURLWithPath: NSHomeDirectory())
+    private func readLog() -> Data? {
+        let logURL = URL(fileURLWithPath: NSHomeDirectory())
             .appendingPathComponent(".exo")
-            .appendingPathComponent("exo_log")
-        var results: [(path: String, data: Data)] = []
-
-        let contents = (try? FileManager.default.contentsOfDirectory(atPath: dir.path)) ?? []
-        for name in contents {
-            if let data = try? Data(contentsOf: dir.appendingPathComponent(name)) {
-                results.append(("exo_log/\(name)", data))
-            }
-        }
-
-        return results
-    }
-
-    private func readAllEventLogs() -> [(path: String, data: Data)] {
-        let eventLogDir = URL(fileURLWithPath: NSHomeDirectory())
-            .appendingPathComponent(".exo")
-            .appendingPathComponent("event_log")
-        var results: [(path: String, data: Data)] = []
-
-        for subdir in ["master", "api"] {
-            let dir = eventLogDir.appendingPathComponent(subdir)
-            let contents =
-                (try? FileManager.default.contentsOfDirectory(atPath: dir.path)) ?? []
-            for name in contents where name.hasPrefix("events.") {
-                if let data = try? Data(contentsOf: dir.appendingPathComponent(name)) {
-                    results.append(("event_log/\(subdir)/\(name)", data))
-                }
-            }
-        }
-
-        return results
+            .appendingPathComponent("exo.log")
+        return try? Data(contentsOf: logURL)
     }
 
     private func captureIfconfig() async throws -> String {

app/EXO/EXO/Services/NetworkStatusService.swift

@@ -35,18 +35,28 @@ struct NetworkStatus: Equatable {
     let thunderboltBridgeState: ThunderboltState?
     let bridgeInactive: Bool?
     let interfaceStatuses: [InterfaceIpStatus]
-    let localRdmaDevices: [String]
-    let localRdmaActivePorts: [RDMAPort]
+    let rdmaStatus: RDMAStatus
 
     static let empty = NetworkStatus(
         thunderboltBridgeState: nil,
         bridgeInactive: nil,
         interfaceStatuses: [],
-        localRdmaDevices: [],
-        localRdmaActivePorts: []
+        rdmaStatus: .empty
     )
 }
 
+struct RDMAStatus: Equatable {
+    let rdmaCtlEnabled: Bool?
+    let devices: [String]
+    let activePorts: [RDMAPort]
+
+    var isAvailable: Bool {
+        rdmaCtlEnabled == true || !devices.isEmpty
+    }
+
+    static let empty = RDMAStatus(rdmaCtlEnabled: nil, devices: [], activePorts: [])
+}
+
 struct RDMAPort: Equatable {
     let device: String
     let port: String
@@ -70,11 +80,31 @@ private struct NetworkStatusFetcher {
             thunderboltBridgeState: readThunderboltBridgeState(),
             bridgeInactive: readBridgeInactive(),
             interfaceStatuses: readInterfaceStatuses(),
-            localRdmaDevices: readRDMADevices(),
-            localRdmaActivePorts: readRDMAActivePorts()
+            rdmaStatus: readRDMAStatus()
         )
     }
 
+    private func readRDMAStatus() -> RDMAStatus {
+        let rdmaCtlEnabled = readRDMACtlEnabled()
+        let devices = readRDMADevices()
+        let activePorts = readRDMAActivePorts()
+        return RDMAStatus(
+            rdmaCtlEnabled: rdmaCtlEnabled, devices: devices, activePorts: activePorts)
+    }
+
+    private func readRDMACtlEnabled() -> Bool? {
+        let result = runCommand(["rdma_ctl", "status"])
+        guard result.exitCode == 0 else { return nil }
+        let output = result.output.lowercased().trimmingCharacters(in: .whitespacesAndNewlines)
+        if output.contains("enabled") {
+            return true
+        }
+        if output.contains("disabled") {
+            return false
+        }
+        return nil
+    }
+
     private func readRDMADevices() -> [String] {
         let result = runCommand(["ibv_devices"])
         guard result.exitCode == 0 else { return [] }

bench/exo_bench.py

@@ -19,11 +19,6 @@ from urllib.parse import urlencode
 from loguru import logger
 from transformers import AutoTokenizer
 
-# Backoff constants for cluster settling retry
-_SETTLE_INITIAL_BACKOFF_S = 1.0
-_SETTLE_MAX_BACKOFF_S = 60.0
-_SETTLE_BACKOFF_MULTIPLIER = 2.0
-
 # Monkey-patch for transformers 5.x compatibility
 # Kimi's tokenization_kimi.py imports bytes_to_unicode from the old location
 # which was moved in transformers 5.0.0rc2
@@ -288,151 +283,6 @@ def resolve_model_short_id(client: ExoClient, model_arg: str) -> tuple[str, str]
     raise ValueError(f"Model not found in /models: {model_arg}")
 
 
-def run_planning_phase(
-    client: ExoClient,
-    full_model_id: str,
-    preview: dict[str, Any],
-    danger_delete: bool,
-    timeout: float,
-    settle_deadline: float | None,
-) -> None:
-    """Check disk space and ensure model is downloaded before benchmarking."""
-    # Get model size from /models
-    models = client.request_json("GET", "/models") or {}
-    model_bytes = 0
-    for m in models.get("data", []):
-        if m.get("hugging_face_id") == full_model_id:
-            model_bytes = m.get("storage_size_megabytes", 0) * 1024 * 1024
-            break
-
-    if not model_bytes:
-        logger.warning(
-            f"Could not determine size for {full_model_id}, skipping disk check"
-        )
-        return
-
-    # Get nodes from preview
-    inner = unwrap_instance(preview["instance"])
-    node_ids = list(inner["shardAssignments"]["nodeToRunner"].keys())
-    runner_to_shard = inner["shardAssignments"]["runnerToShard"]
-
-    state = client.request_json("GET", "/state")
-    downloads = state.get("downloads", {})
-    node_disk = state.get("nodeDisk", {})
-
-    for node_id in node_ids:
-        node_downloads = downloads.get(node_id, [])
-
-        # Check if model already downloaded on this node
-        already_downloaded = any(
-            "DownloadCompleted" in p
-            and unwrap_instance(p["DownloadCompleted"]["shardMetadata"])["modelCard"][
-                "modelId"
-            ]
-            == full_model_id
-            for p in node_downloads
-        )
-        if already_downloaded:
-            continue
-
-        # Wait for disk info if settle_deadline is set
-        disk_info = node_disk.get(node_id, {})
-        backoff = _SETTLE_INITIAL_BACKOFF_S
-        while not disk_info and settle_deadline and time.monotonic() < settle_deadline:
-            remaining = settle_deadline - time.monotonic()
-            logger.info(
-                f"Waiting for disk info on {node_id} ({remaining:.0f}s remaining)..."
-            )
-            time.sleep(min(backoff, remaining))
-            backoff = min(backoff * _SETTLE_BACKOFF_MULTIPLIER, _SETTLE_MAX_BACKOFF_S)
-            state = client.request_json("GET", "/state")
-            node_disk = state.get("nodeDisk", {})
-            disk_info = node_disk.get(node_id, {})
-
-        if not disk_info:
-            logger.warning(f"No disk info for {node_id}, skipping space check")
-            continue
-
-        avail = disk_info.get("available", {}).get("inBytes", 0)
-        if avail >= model_bytes:
-            continue
-
-        if not danger_delete:
-            raise RuntimeError(
-                f"Insufficient disk on {node_id}: need {model_bytes // (1024**3)}GB, "
-                f"have {avail // (1024**3)}GB. Use --danger-delete-downloads to free space."
-            )
-
-        # Delete from smallest to largest
-        completed = [
-            (
-                unwrap_instance(p["DownloadCompleted"]["shardMetadata"])["modelCard"][
-                    "modelId"
-                ],
-                p["DownloadCompleted"]["totalBytes"]["inBytes"],
-            )
-            for p in node_downloads
-            if "DownloadCompleted" in p
-        ]
-        for del_model, size in sorted(completed, key=lambda x: x[1]):
-            logger.info(f"Deleting {del_model} from {node_id} ({size // (1024**2)}MB)")
-            client.request_json("DELETE", f"/download/{node_id}/{del_model}")
-            avail += size
-            if avail >= model_bytes:
-                break
-
-        if avail < model_bytes:
-            raise RuntimeError(f"Could not free enough space on {node_id}")
-
-    # Start downloads (idempotent)
-    for node_id in node_ids:
-        runner_id = inner["shardAssignments"]["nodeToRunner"][node_id]
-        shard = runner_to_shard[runner_id]
-        client.request_json(
-            "POST",
-            "/download/start",
-            body={
-                "targetNodeId": node_id,
-                "shardMetadata": shard,
-            },
-        )
-        logger.info(f"Started download on {node_id}")
-
-    # Wait for downloads
-    start = time.time()
-    while time.time() - start < timeout:
-        state = client.request_json("GET", "/state")
-        downloads = state.get("downloads", {})
-        all_done = True
-        for node_id in node_ids:
-            done = any(
-                "DownloadCompleted" in p
-                and unwrap_instance(p["DownloadCompleted"]["shardMetadata"])[
-                    "modelCard"
-                ]["modelId"]
-                == full_model_id
-                for p in downloads.get(node_id, [])
-            )
-            failed = [
-                p["DownloadFailed"]["errorMessage"]
-                for p in downloads.get(node_id, [])
-                if "DownloadFailed" in p
-                and unwrap_instance(p["DownloadFailed"]["shardMetadata"])["modelCard"][
-                    "modelId"
-                ]
-                == full_model_id
-            ]
-            if failed:
-                raise RuntimeError(f"Download failed on {node_id}: {failed[0]}")
-            if not done:
-                all_done = False
-        if all_done:
-            return
-        time.sleep(1)
-
-    raise TimeoutError("Downloads did not complete in time")
-
-
 def placement_filter(instance_meta: str, wanted: str) -> bool:
     s = (instance_meta or "").lower()
     if wanted == "both":
@@ -538,66 +388,6 @@ class PromptSizer:
         return content, tok
 
 
-def fetch_and_filter_placements(
-    client: ExoClient, full_model_id: str, args: argparse.Namespace
-) -> list[dict[str, Any]]:
-    previews_resp = client.request_json(
-        "GET", "/instance/previews", params={"model_id": full_model_id}
-    )
-    previews = previews_resp.get("previews") or []
-
-    selected: list[dict[str, Any]] = []
-    for p in previews:
-        if p.get("error") is not None:
-            continue
-        if not placement_filter(str(p.get("instance_meta", "")), args.instance_meta):
-            continue
-        if not sharding_filter(str(p.get("sharding", "")), args.sharding):
-            continue
-
-        instance = p.get("instance")
-        if not isinstance(instance, dict):
-            continue
-
-        n = nodes_used_in_instance(instance)
-        # Skip tensor ring single node as it is pointless when pipeline ring
-        if n == 1 and (
-            (args.sharding == "both" and "tensor" in p.get("sharding", "").lower())
-            or (
-                args.instance_meta == "both"
-                and "jaccl" in p.get("instance_meta", "").lower()
-            )
-        ):
-            continue
-
-        if (
-            args.skip_pipeline_jaccl
-            and (
-                args.instance_meta == "both"
-                and "jaccl" in p.get("instance_meta", "").lower()
-            )
-            and (
-                args.sharding == "both" and "pipeline" in p.get("sharding", "").lower()
-            )
-        ):
-            continue
-
-        if (
-            args.skip_tensor_ring
-            and (
-                args.instance_meta == "both"
-                and "ring" in p.get("instance_meta", "").lower()
-            )
-            and (args.sharding == "both" and "tensor" in p.get("sharding", "").lower())
-        ):
-            continue
-
-        if args.min_nodes <= n <= args.max_nodes:
-            selected.append(p)
-
-    return selected
-
-
 def main() -> int:
     ap = argparse.ArgumentParser(
         prog="exo-bench",
@@ -674,17 +464,6 @@ def main() -> int:
         action="store_true",
         help="Force all pp×tg combinations (cartesian product) even when lists have equal length.",
     )
-    ap.add_argument(
-        "--settle-timeout",
-        type=float,
-        default=0,
-        help="Max seconds to wait for the cluster to produce valid placements (0 = try once).",
-    )
-    ap.add_argument(
-        "--danger-delete-downloads",
-        action="store_true",
-        help="Delete existing models from smallest to largest to make room for benchmark model.",
-    )
     args = ap.parse_args()
 
     pp_list = parse_int_list(args.pp)
@@ -708,6 +487,11 @@ def main() -> int:
     client = ExoClient(args.host, args.port, timeout_s=args.timeout)
     short_id, full_model_id = resolve_model_short_id(client, args.model)
 
+    previews_resp = client.request_json(
+        "GET", "/instance/previews", params={"model_id": full_model_id}
+    )
+    previews = previews_resp.get("previews") or []
+
     tokenizer = load_tokenizer_for_bench(full_model_id)
     if tokenizer is None:
         raise RuntimeError("[exo-bench] tokenizer load failed")
@@ -719,23 +503,54 @@ def main() -> int:
         logger.error("[exo-bench] tokenizer usable but prompt sizing failed")
         raise
 
-    settle_deadline = (
-        time.monotonic() + args.settle_timeout if args.settle_timeout > 0 else None
-    )
+    selected: list[dict[str, Any]] = []
+    for p in previews:
+        if p.get("error") is not None:
+            continue
+        if not placement_filter(str(p.get("instance_meta", "")), args.instance_meta):
+            continue
+        if not sharding_filter(str(p.get("sharding", "")), args.sharding):
+            continue
 
-    selected = fetch_and_filter_placements(client, full_model_id, args)
+        instance = p.get("instance")
+        if not isinstance(instance, dict):
+            continue
 
-    if not selected and settle_deadline:
-        backoff = _SETTLE_INITIAL_BACKOFF_S
-        while not selected and time.monotonic() < settle_deadline:
-            remaining = settle_deadline - time.monotonic()
-            logger.warning(
-                f"No valid placements yet (cluster may still be settling). "
-                f"Retrying in {backoff:.1f}s ({remaining:.0f}s remaining)..."
+        n = nodes_used_in_instance(instance)
+        # Skip tensor ring single node as it is pointless when pipeline ring
+        if n == 1 and (
+            (args.sharding == "both" and "tensor" in p.get("sharding", "").lower())
+            or (
+                args.instance_meta == "both"
+                and "jaccl" in p.get("instance_meta", "").lower()
             )
-            time.sleep(min(backoff, remaining))
-            backoff = min(backoff * _SETTLE_BACKOFF_MULTIPLIER, _SETTLE_MAX_BACKOFF_S)
-            selected = fetch_and_filter_placements(client, full_model_id, args)
+        ):
+            continue
+
+        if (
+            args.skip_pipeline_jaccl
+            and (
+                args.instance_meta == "both"
+                and "jaccl" in p.get("instance_meta", "").lower()
+            )
+            and (
+                args.sharding == "both" and "pipeline" in p.get("sharding", "").lower()
+            )
+        ):
+            continue
+
+        if (
+            args.skip_tensor_ring
+            and (
+                args.instance_meta == "both"
+                and "ring" in p.get("instance_meta", "").lower()
+            )
+            and (args.sharding == "both" and "tensor" in p.get("sharding", "").lower())
+        ):
+            continue
+
+        if args.min_nodes <= n <= args.max_nodes:
+            selected.append(p)
 
     if not selected:
         logger.error("No valid placements matched your filters.")
@@ -760,16 +575,6 @@ def main() -> int:
     if args.dry_run:
         return 0
 
-    logger.info("Planning phase: checking downloads...")
-    run_planning_phase(
-        client,
-        full_model_id,
-        selected[0],
-        args.danger_delete_downloads,
-        args.timeout,
-        settle_deadline,
-    )
-
     all_rows: list[dict[str, Any]] = []
 
     for preview in selected:

bench/pyproject.toml

@@ -1,16 +0,0 @@
-[project]
-name = "exo-bench"
-version = "0.1.0"
-description = "Benchmarking tool for exo distributed inference"
-requires-python = ">=3.13"
-dependencies = [
-    "loguru>=0.7.3",
-    "transformers>=5.0.0",
-    "huggingface-hub>=0.33.4",
-    "tiktoken>=0.12.0",
-    "jinja2>=3.1.0",
-]
-
-[build-system]
-requires = ["hatchling"]
-build-backend = "hatchling.build"

conftest.py

@@ -1 +0,0 @@
-collect_ignore = ["tests/start_distributed_test.py"]

dashboard/src/lib/components/ChatForm.svelte

@@ -12,8 +12,6 @@
     ttftMs,
     tps,
     totalTokens,
-    thinkingEnabled as thinkingEnabledStore,
-    setConversationThinking,
   } from "$lib/stores/app.svelte";
   import ChatAttachments from "./ChatAttachments.svelte";
   import ImageParamsPanel from "./ImageParamsPanel.svelte";
@@ -27,7 +25,6 @@
     autofocus?: boolean;
     showModelSelector?: boolean;
     modelTasks?: Record<string, string[]>;
-    modelCapabilities?: Record<string, string[]>;
   }
 
   let {
@@ -37,7 +34,6 @@
     autofocus = true,
     showModelSelector = false,
     modelTasks = {},
-    modelCapabilities = {},
   }: Props = $props();
 
   let message = $state("");
@@ -45,7 +41,6 @@
   let fileInputRef: HTMLInputElement | undefined = $state();
   let uploadedFiles = $state<ChatUploadedFile[]>([]);
   let isDragOver = $state(false);
-  const thinkingEnabled = $derived(thinkingEnabledStore());
   let loading = $derived(isLoading());
   const currentModel = $derived(selectedChatModel());
   const instanceData = $derived(instances());
@@ -100,12 +95,6 @@
     );
   });
 
-  const modelSupportsThinking = $derived(() => {
-    if (!currentModel) return false;
-    const caps = modelCapabilities[currentModel] || [];
-    return caps.includes("thinking") && caps.includes("text");
-  });
-
   const isEditOnlyWithoutImage = $derived(
     currentModel !== null &&
       modelSupportsOnlyImageEditing(currentModel) &&
@@ -265,7 +254,6 @@
 
   function handleSubmit() {
     if ((!message.trim() && uploadedFiles.length === 0) || loading) return;
-    if (isEditOnlyWithoutImage) return;
 
     const content = message.trim();
     const files = [...uploadedFiles];
@@ -290,19 +278,11 @@
       if (imageFile.preview) {
         editImage(content, imageFile.preview);
       }
-    } else if (
-      currentModel &&
-      modelSupportsTextToImage(currentModel) &&
-      content
-    ) {
+    } else if (isImageModel() && content) {
       // Use image generation for text-to-image models
       generateImage(content);
     } else {
-      sendMessage(
-        content,
-        files,
-        modelSupportsThinking() ? thinkingEnabled : null,
-      );
+      sendMessage(content, files);
     }
 
     // Refocus the textarea after sending
@@ -540,35 +520,6 @@
             </div>
           {/if}
         </div>
-        <!-- Thinking toggle -->
-        {#if modelSupportsThinking()}
-          <button
-            type="button"
-            onclick={() => setConversationThinking(!thinkingEnabled)}
-            class="flex items-center gap-1.5 px-2 py-1 rounded text-xs font-mono tracking-wide transition-all duration-200 flex-shrink-0 cursor-pointer border {thinkingEnabled
-              ? 'bg-exo-yellow/15 border-exo-yellow/40 text-exo-yellow'
-              : 'bg-exo-medium-gray/30 border-exo-medium-gray/50 text-exo-light-gray/60 hover:text-exo-light-gray'}"
-            title={thinkingEnabled
-              ? "Thinking enabled — click to disable"
-              : "Thinking disabled — click to enable"}
-          >
-            <svg
-              class="w-3.5 h-3.5"
-              viewBox="0 0 24 24"
-              fill="none"
-              stroke="currentColor"
-              stroke-width="1.5"
-            >
-              <path
-                d="M12 2a7 7 0 0 0-7 7c0 2.38 1.19 4.47 3 5.74V17a1 1 0 0 0 1 1h6a1 1 0 0 0 1-1v-2.26c1.81-1.27 3-3.36 3-5.74a7 7 0 0 0-7-7zM9 20h6M10 22h4"
-                stroke-linecap="round"
-                stroke-linejoin="round"
-              />
-            </svg>
-            <span>{thinkingEnabled ? "THINK" : "NO THINK"}</span>
-          </button>
-        {/if}
-
         <!-- Performance stats -->
         {#if currentTtft !== null || currentTps !== null}
           <div class="flex items-center gap-4 text-xs font-mono flex-shrink-0">
@@ -648,8 +599,9 @@
             : isImageModel()
               ? "Describe the image you want to generate..."
               : placeholder}
+        disabled={loading}
         rows={1}
-        class="flex-1 resize-none bg-transparent text-foreground placeholder:text-exo-light-gray/60 placeholder:text-sm placeholder:tracking-[0.15em] placeholder:leading-7 focus:outline-none focus:ring-0 focus:border-none text-sm leading-7 font-mono"
+        class="flex-1 resize-none bg-transparent text-foreground placeholder:text-exo-light-gray/60 placeholder:text-sm placeholder:tracking-[0.15em] placeholder:leading-7 focus:outline-none focus:ring-0 focus:border-none disabled:opacity-50 text-sm leading-7 font-mono"
         style="min-height: 28px; max-height: 150px;"
       ></textarea>
 

dashboard/src/lib/components/ChatMessages.svelte

@@ -13,7 +13,6 @@
   import type { MessageAttachment } from "$lib/stores/app.svelte";
   import MarkdownContent from "./MarkdownContent.svelte";
   import TokenHeatmap from "./TokenHeatmap.svelte";
-  import ImageLightbox from "./ImageLightbox.svelte";
 
   interface Props {
     class?: string;
@@ -102,9 +101,6 @@
   let copiedMessageId = $state<string | null>(null);
   let expandedThinkingMessageIds = $state<Set<string>>(new Set());
 
-  // Lightbox state
-  let expandedImageSrc = $state<string | null>(null);
-
   // Uncertainty heatmap toggle
   let heatmapMessageIds = $state<Set<string>>(new Set());
 
@@ -225,7 +221,6 @@
   }
 
   function handleDeleteClick(messageId: string) {
-    if (loading) return;
     deleteConfirmId = messageId;
   }
 
@@ -256,7 +251,7 @@
 </script>
 
 <div class="flex flex-col gap-4 sm:gap-6 {className}">
-  {#each messageList as message, i (message.id)}
+  {#each messageList as message (message.id)}
     <div
       class="group flex {message.role === 'user'
         ? 'justify-end'
@@ -318,11 +313,9 @@
           <!-- Delete confirmation -->
           <div class="bg-red-500/10 border border-red-500/30 rounded-lg p-3">
             <p class="text-xs text-red-400 mb-3">
-              {#if i === messageList.length - 1}
-                Delete this message?
-              {:else}
-                Delete this message and all messages after it?
-              {/if}
+              Delete this message{message.role === "user"
+                ? " and all responses after it"
+                : ""}?
             </p>
             <div class="flex gap-2 justify-end">
               <button
@@ -396,15 +389,10 @@
                         class="flex items-center gap-2 bg-exo-dark-gray/60 border border-exo-yellow/20 rounded px-2 py-1 text-xs font-mono"
                       >
                         {#if attachment.type === "image" && attachment.preview}
-                          <!-- svelte-ignore a11y_no_noninteractive_element_interactions, a11y_click_events_have_key_events -->
                           <img
                             src={attachment.preview}
                             alt={attachment.name}
-                            class="w-12 h-12 object-cover rounded border border-exo-yellow/20 cursor-pointer hover:border-exo-yellow/50 transition-colors"
-                            onclick={() => {
-                              if (attachment.preview)
-                                expandedImageSrc = attachment.preview;
-                            }}
+                            class="w-12 h-12 object-cover rounded border border-exo-yellow/20"
                           />
                         {:else}
                           <span>{getAttachmentIcon(attachment)}</span>
@@ -478,44 +466,15 @@
                   <div class="mb-3">
                     {#each message.attachments.filter((a) => a.type === "generated-image") as attachment}
                       <div class="relative group/img inline-block">
-                        <!-- svelte-ignore a11y_no_noninteractive_element_interactions, a11y_click_events_have_key_events -->
                         <img
                           src={attachment.preview}
                           alt=""
-                          class="max-w-full max-h-[512px] rounded-lg border border-exo-yellow/20 shadow-lg shadow-black/20 cursor-pointer"
-                          onclick={() => {
-                            if (attachment.preview)
-                              expandedImageSrc = attachment.preview;
-                          }}
+                          class="max-w-full max-h-[512px] rounded-lg border border-exo-yellow/20 shadow-lg shadow-black/20"
                         />
                         <!-- Button overlay -->
                         <div
                           class="absolute top-2 right-2 flex gap-1 opacity-0 group-hover/img:opacity-100 transition-opacity"
                         >
-                          <!-- Expand button -->
-                          <button
-                            type="button"
-                            class="p-2 rounded-lg bg-exo-dark-gray/80 border border-exo-yellow/30 text-exo-yellow hover:bg-exo-dark-gray hover:border-exo-yellow/50 cursor-pointer"
-                            onclick={() => {
-                              if (attachment.preview)
-                                expandedImageSrc = attachment.preview;
-                            }}
-                            title="Expand image"
-                          >
-                            <svg
-                              class="w-4 h-4"
-                              fill="none"
-                              viewBox="0 0 24 24"
-                              stroke="currentColor"
-                              stroke-width="2"
-                            >
-                              <path
-                                stroke-linecap="round"
-                                stroke-linejoin="round"
-                                d="M4 8V4m0 0h4M4 4l5 5m11-1V4m0 0h-4m4 0l-5 5M4 16v4m0 0h4m-4 0l5-5m11 5l-5-5m5 5v-4m0 4h-4"
-                              />
-                            </svg>
-                          </button>
                           <!-- Edit button -->
                           <button
                             type="button"
@@ -754,13 +713,8 @@
             <!-- Delete button -->
             <button
               onclick={() => handleDeleteClick(message.id)}
-              disabled={loading}
-              class="p-1.5 transition-colors rounded {loading
-                ? 'text-exo-light-gray/30 cursor-not-allowed'
-                : 'text-exo-light-gray hover:text-red-400 hover:bg-red-500/10 cursor-pointer'}"
-              title={loading
-                ? "Cannot delete while generating"
-                : "Delete message"}
+              class="p-1.5 text-exo-light-gray hover:text-red-400 transition-colors rounded hover:bg-red-500/10 cursor-pointer"
+              title="Delete message"
             >
               <svg
                 class="w-3.5 h-3.5"
@@ -835,8 +789,3 @@
     </button>
   {/if}
 </div>
-
-<ImageLightbox
-  src={expandedImageSrc}
-  onclose={() => (expandedImageSrc = null)}
-/>

dashboard/src/lib/components/FamilyLogos.svelte

@@ -13,12 +13,6 @@
       d="M12 2l3.09 6.26L22 9.27l-5 4.87 1.18 6.88L12 17.77l-6.18 3.25L7 14.14 2 9.27l6.91-1.01L12 2z"
     />
   </svg>
-{:else if family === "recents"}
-  <svg class="w-6 h-6 {className}" viewBox="0 0 24 24" fill="currentColor">
-    <path
-      d="M13 3a9 9 0 0 0-9 9H1l3.89 3.89.07.14L9 12H6c0-3.87 3.13-7 7-7s7 3.13 7 7-3.13 7-7 7c-1.93 0-3.68-.79-4.94-2.06l-1.42 1.42A8.954 8.954 0 0 0 13 21a9 9 0 0 0 0-18zm-1 5v5l4.28 2.54.72-1.21-3.5-2.08V8H12z"
-    />
-  </svg>
 {:else if family === "llama" || family === "meta"}
   <svg class="w-6 h-6 {className}" viewBox="0 0 24 24" fill="currentColor">
     <path
@@ -64,18 +58,6 @@
       d="M17.962 1.844h-4.326l-3.425 7.81H5.369V1.878H1.5V22h3.87v-8.477h6.824a3.025 3.025 0 002.743-1.75V22h3.87v-8.477a3.87 3.87 0 00-3.588-3.86v-.01h-2.125a3.94 3.94 0 002.323-2.12l2.545-5.689z"
     />
   </svg>
-{:else if family === "flux"}
-  <svg class="w-6 h-6 {className}" viewBox="0 0 24 24" fill="currentColor">
-    <path
-      d="M12 2L2 19h7.5l2.5-4.5L14.5 19H22L12 2zm0 4.5L16.5 17h-3l-1.5-2.7L10.5 17h-3L12 6.5z"
-    />
-  </svg>
-{:else if family === "qwen-image"}
-  <svg class="w-6 h-6 {className}" viewBox="0 0 24 24" fill="currentColor">
-    <path
-      d="M12.604 1.34c.393.69.784 1.382 1.174 2.075a.18.18 0 00.157.091h5.552c.174 0 .322.11.446.327l1.454 2.57c.19.337.24.478.024.837-.26.43-.513.864-.76 1.3l-.367.658c-.106.196-.223.28-.04.512l2.652 4.637c.172.301.111.494-.043.77-.437.785-.882 1.564-1.335 2.34-.159.272-.352.375-.68.37-.777-.016-1.552-.01-2.327.016a.099.099 0 00-.081.05 575.097 575.097 0 01-2.705 4.74c-.169.293-.38.363-.725.364-.997.003-2.002.004-3.017.002a.537.537 0 01-.465-.271l-1.335-2.323a.09.09 0 00-.083-.049H4.982c-.285.03-.553-.001-.805-.092l-1.603-2.77a.543.543 0 01-.002-.54l1.207-2.12a.198.198 0 000-.197 550.951 550.951 0 01-1.875-3.272l-.79-1.395c-.16-.31-.173-.496.095-.965.465-.813.927-1.625 1.387-2.436.132-.234.304-.334.584-.335a338.3 338.3 0 012.589-.001.124.124 0 00.107-.063l2.806-4.895a.488.488 0 01.422-.246c.524-.001 1.053 0 1.583-.006L11.704 1c.341-.003.724.032.9.34zm-3.432.403a.06.06 0 00-.052.03L6.254 6.788a.157.157 0 01-.135.078H3.253c-.056 0-.07.025-.041.074l5.81 10.156c.025.042.013.062-.034.063l-2.795.015a.218.218 0 00-.2.116l-1.32 2.31c-.044.078-.021.118.068.118l5.716.008c.046 0 .08.02.104.061l1.403 2.454c.046.081.092.082.139 0l5.006-8.76.783-1.382a.055.055 0 01.096 0l1.424 2.53a.122.122 0 00.107.062l2.763-.02a.04.04 0 00.035-.02.041.041 0 000-.04l-2.9-5.086a.108.108 0 010-.113l.293-.507 1.12-1.977c.024-.041.012-.062-.035-.062H9.2c-.059 0-.073-.026-.043-.077l1.434-2.505a.107.107 0 000-.114L9.225 1.774a.06.06 0 00-.053-.031zm6.29 8.02c.046 0 .058.02.034.06l-.832 1.465-2.613 4.585a.056.056 0 01-.05.029.058.058 0 01-.05-.029L8.498 9.841c-.02-.034-.01-.052.028-.054l.216-.012 6.722-.012z"
-    />
-  </svg>
 {:else if family === "huggingface"}
   <svg class="w-6 h-6 {className}" viewBox="0 0 24 24" fill="currentColor">
     <path

dashboard/src/lib/components/FamilySidebar.svelte

@@ -5,22 +5,15 @@
     families: string[];
     selectedFamily: string | null;
     hasFavorites: boolean;
-    hasRecents: boolean;
     onSelect: (family: string | null) => void;
   };
 
-  let {
-    families,
-    selectedFamily,
-    hasFavorites,
-    hasRecents,
-    onSelect,
-  }: FamilySidebarProps = $props();
+  let { families, selectedFamily, hasFavorites, onSelect }: FamilySidebarProps =
+    $props();
 
   // Family display names
   const familyNames: Record<string, string> = {
     favorites: "Favorites",
-    recents: "Recent",
     huggingface: "Hub",
     llama: "Meta",
     qwen: "Qwen",
@@ -29,8 +22,6 @@
     glm: "GLM",
     minimax: "MiniMax",
     kimi: "Kimi",
-    flux: "FLUX",
-    "qwen-image": "Qwen Img",
   };
 
   function getFamilyName(family: string): string {
@@ -41,7 +32,7 @@
 </script>
 
 <div
-  class="flex flex-col gap-1 py-2 px-1 border-r border-exo-yellow/10 bg-exo-medium-gray/30 min-w-[64px] overflow-y-auto scrollbar-hide"
+  class="flex flex-col gap-1 py-2 px-1 border-r border-exo-yellow/10 bg-exo-medium-gray/30 min-w-[64px]"
 >
   <!-- All models (no filter) -->
   <button
@@ -96,31 +87,6 @@
     </button>
   {/if}
 
-  <!-- Recent (only show if has recent models) -->
-  {#if hasRecents}
-    <button
-      type="button"
-      onclick={() => onSelect("recents")}
-      class="group flex flex-col items-center justify-center p-2 rounded transition-all duration-200 cursor-pointer {selectedFamily ===
-      'recents'
-        ? 'bg-exo-yellow/20 border-l-2 border-exo-yellow'
-        : 'hover:bg-white/5 border-l-2 border-transparent'}"
-      title="Recently launched models"
-    >
-      <FamilyLogos
-        family="recents"
-        class={selectedFamily === "recents"
-          ? "text-exo-yellow"
-          : "text-white/50 group-hover:text-white/70"}
-      />
-      <span
-        class="text-[9px] font-mono mt-0.5 {selectedFamily === 'recents'
-          ? 'text-exo-yellow'
-          : 'text-white/40 group-hover:text-white/60'}">Recent</span
-      >
-    </button>
-  {/if}
-
   <!-- HuggingFace Hub -->
   <button
     type="button"

dashboard/src/lib/components/ImageLightbox.svelte

@@ -1,96 +0,0 @@
-<script lang="ts">
-  import { fade, fly } from "svelte/transition";
-  import { cubicOut } from "svelte/easing";
-
-  interface Props {
-    src: string | null;
-    onclose: () => void;
-  }
-
-  let { src, onclose }: Props = $props();
-
-  function handleKeydown(e: KeyboardEvent) {
-    if (e.key === "Escape") {
-      onclose();
-    }
-  }
-
-  function extensionFromSrc(dataSrc: string): string {
-    const match = dataSrc.match(/^data:image\/(\w+)/);
-    if (match) return match[1] === "jpeg" ? "jpg" : match[1];
-    const urlMatch = dataSrc.match(/\.(\w+)(?:\?|$)/);
-    if (urlMatch) return urlMatch[1];
-    return "png";
-  }
-
-  function handleDownload(e: MouseEvent) {
-    e.stopPropagation();
-    if (!src) return;
-    const link = document.createElement("a");
-    link.href = src;
-    link.download = `image-${Date.now()}.${extensionFromSrc(src)}`;
-    link.click();
-  }
-
-  function handleClose(e: MouseEvent) {
-    e.stopPropagation();
-    onclose();
-  }
-</script>
-
-<svelte:window onkeydown={src ? handleKeydown : undefined} />
-
-{#if src}
-  <div
-    class="fixed inset-0 z-50 bg-black/90 backdrop-blur-sm flex items-center justify-center"
-    transition:fade={{ duration: 200 }}
-    onclick={onclose}
-    role="presentation"
-    onintrostart={() => (document.body.style.overflow = "hidden")}
-    onoutroend={() => (document.body.style.overflow = "")}
-  >
-    <div class="absolute top-4 right-4 flex gap-2 z-10">
-      <button
-        type="button"
-        class="p-2 rounded-lg bg-exo-dark-gray/80 border border-exo-yellow/30 text-exo-yellow hover:bg-exo-dark-gray hover:border-exo-yellow/50 cursor-pointer transition-colors"
-        onclick={handleDownload}
-        title="Download image"
-      >
-        <svg
-          class="w-5 h-5"
-          fill="none"
-          viewBox="0 0 24 24"
-          stroke="currentColor"
-          stroke-width="2"
-        >
-          <path
-            stroke-linecap="round"
-            stroke-linejoin="round"
-            d="M4 16v1a3 3 0 003 3h10a3 3 0 003-3v-1m-4-4l-4 4m0 0l-4-4m4 4V4"
-          />
-        </svg>
-      </button>
-      <button
-        type="button"
-        class="p-2 rounded-lg bg-exo-dark-gray/80 border border-exo-yellow/30 text-exo-yellow hover:bg-exo-dark-gray hover:border-exo-yellow/50 cursor-pointer transition-colors"
-        onclick={handleClose}
-        title="Close"
-      >
-        <svg class="w-5 h-5" viewBox="0 0 24 24" fill="currentColor">
-          <path
-            d="M19 6.41L17.59 5 12 10.59 6.41 5 5 6.41 10.59 12 5 17.59 6.41 19 12 13.41 17.59 19 19 17.59 13.41 12 19 6.41z"
-          />
-        </svg>
-      </button>
-    </div>
-
-    <!-- svelte-ignore a11y_no_noninteractive_element_interactions, a11y_click_events_have_key_events -->
-    <img
-      {src}
-      alt=""
-      class="max-w-[90vw] max-h-[90vh] object-contain rounded-lg shadow-2xl"
-      transition:fly={{ y: 20, duration: 300, easing: cubicOut }}
-      onclick={(e) => e.stopPropagation()}
-    />
-  </div>
-{/if}

dashboard/src/lib/components/ModelCard.svelte

@@ -422,16 +422,9 @@
     const bToACandidates: Array<{ ip: string; iface: string | null }> = [];
 
     for (const edge of topology.edges) {
-      let ip: string;
-      let iface: string | null;
-
-      if (edge.sourceRdmaIface || edge.sinkRdmaIface) {
-        ip = "RDMA";
-        iface = `${edge.sourceRdmaIface || "?"} \u2192 ${edge.sinkRdmaIface || "?"}`;
-      } else {
-        ip = edge.sendBackIp || "?";
-        iface = edge.sendBackInterface || getInterfaceForIp(edge.source, ip);
-      }
+      const ip = edge.sendBackIp || "?";
+      const iface =
+        edge.sendBackInterface || getInterfaceForIp(edge.source, ip);
 
       if (edge.source === nodeId1 && edge.target === nodeId2) {
         aToBCandidates.push({ ip, iface });

dashboard/src/lib/components/ModelFilterPopover.svelte

@@ -24,8 +24,6 @@
     { id: "thinking", label: "Thinking" },
     { id: "code", label: "Code" },
     { id: "vision", label: "Vision" },
-    { id: "image_gen", label: "Image Gen" },
-    { id: "image_edit", label: "Image Edit" },
   ];
 
   // Size ranges
@@ -144,45 +142,6 @@
                   stroke-linejoin="round"
                 /><circle cx="12" cy="12" r="3" /></svg
               >
-            {:else if cap.id === "image_gen"}
-              <svg
-                class="w-3.5 h-3.5 inline-block"
-                viewBox="0 0 24 24"
-                fill="none"
-                stroke="currentColor"
-                stroke-width="1.5"
-                ><rect
-                  x="3"
-                  y="3"
-                  width="18"
-                  height="18"
-                  rx="2"
-                  ry="2"
-                  stroke-linecap="round"
-                  stroke-linejoin="round"
-                /><circle cx="8.5" cy="8.5" r="1.5" /><path
-                  d="M21 15l-5-5L5 21"
-                  stroke-linecap="round"
-                  stroke-linejoin="round"
-                /></svg
-              >
-            {:else if cap.id === "image_edit"}
-              <svg
-                class="w-3.5 h-3.5 inline-block"
-                viewBox="0 0 24 24"
-                fill="none"
-                stroke="currentColor"
-                stroke-width="1.5"
-                ><path
-                  d="M11 4H4a2 2 0 0 0-2 2v14a2 2 0 0 0 2 2h14a2 2 0 0 0 2-2v-7"
-                  stroke-linecap="round"
-                  stroke-linejoin="round"
-                /><path
-                  d="M18.5 2.5a2.121 2.121 0 0 1 3 3L12 15l-4 1 1-4 9.5-9.5z"
-                  stroke-linecap="round"
-                  stroke-linejoin="round"
-                /></svg
-              >
             {/if}
             <span class="ml-1">{cap.label}</span>
           </button>

dashboard/src/lib/components/ModelPickerGroup.svelte

@@ -26,7 +26,6 @@
     nodeNames: string[];
     nodeIds: string[];
   };
-  type ModelFitStatus = "fits_now" | "fits_cluster_capacity" | "too_large";
 
   type ModelPickerGroupProps = {
     group: ModelGroup;
@@ -34,13 +33,11 @@
     isFavorite: boolean;
     selectedModelId: string | null;
     canModelFit: (id: string) => boolean;
-    getModelFitStatus: (id: string) => ModelFitStatus;
     onToggleExpand: () => void;
     onSelectModel: (modelId: string) => void;
     onToggleFavorite: (baseModelId: string) => void;
     onShowInfo: (group: ModelGroup) => void;
     downloadStatusMap?: Map<string, DownloadAvailability>;
-    launchedAt?: number;
   };
 
   let {
@@ -49,13 +46,11 @@
     isFavorite,
     selectedModelId,
     canModelFit,
-    getModelFitStatus,
     onToggleExpand,
     onSelectModel,
     onToggleFavorite,
     onShowInfo,
     downloadStatusMap,
-    launchedAt,
   }: ModelPickerGroupProps = $props();
 
   // Group-level download status: show if any variant is downloaded
@@ -77,45 +72,10 @@
     return `${mb}MB`;
   }
 
-  function timeAgo(ts: number): string {
-    const seconds = Math.floor((Date.now() - ts) / 1000);
-    if (seconds < 60) return "just now";
-    const minutes = Math.floor(seconds / 60);
-    if (minutes < 60) return `${minutes}m ago`;
-    const hours = Math.floor(minutes / 60);
-    if (hours < 24) return `${hours}h ago`;
-    const days = Math.floor(hours / 24);
-    return `${days}d ago`;
-  }
-
   // Check if any variant can fit
   const anyVariantFits = $derived(
     group.variants.some((v) => canModelFit(v.id)),
   );
-  const groupFitStatus = $derived.by((): ModelFitStatus => {
-    let hasClusterCapacityOnly = false;
-    for (const variant of group.variants) {
-      const fitStatus = getModelFitStatus(variant.id);
-      if (fitStatus === "fits_now") {
-        return "fits_now";
-      }
-      if (fitStatus === "fits_cluster_capacity") {
-        hasClusterCapacityOnly = true;
-      }
-    }
-    return hasClusterCapacityOnly ? "fits_cluster_capacity" : "too_large";
-  });
-
-  function getSizeClassForFitStatus(fitStatus: ModelFitStatus): string {
-    switch (fitStatus) {
-      case "fits_now":
-        return "text-white/40";
-      case "fits_cluster_capacity":
-        return "text-orange-400/80";
-      case "too_large":
-        return "text-red-400/70";
-    }
-  }
 
   // Check if this group's model is currently selected (for single-variant groups)
   const isMainSelected = $derived(
@@ -240,42 +200,9 @@
               stroke-width="1.5"
               title="Supports image generation"
             >
-              <rect
-                x="3"
-                y="3"
-                width="18"
-                height="18"
-                rx="2"
-                ry="2"
-                stroke-linecap="round"
-                stroke-linejoin="round"
-              />
+              <rect x="3" y="3" width="18" height="18" rx="2" ry="2" />
               <circle cx="8.5" cy="8.5" r="1.5" />
-              <path
-                d="M21 15l-5-5L5 21"
-                stroke-linecap="round"
-                stroke-linejoin="round"
-              />
-            </svg>
-          {:else if cap === "image_edit"}
-            <svg
-              class="w-3.5 h-3.5 text-white/40 flex-shrink-0"
-              viewBox="0 0 24 24"
-              fill="none"
-              stroke="currentColor"
-              stroke-width="1.5"
-              title="Supports image editing"
-            >
-              <path
-                d="M11 4H4a2 2 0 0 0-2 2v14a2 2 0 0 0 2 2h14a2 2 0 0 0 2-2v-7"
-                stroke-linecap="round"
-                stroke-linejoin="round"
-              />
-              <path
-                d="M18.5 2.5a2.121 2.121 0 0 1 3 3L12 15l-4 1 1-4 9.5-9.5z"
-                stroke-linecap="round"
-                stroke-linejoin="round"
-              />
+              <path d="M21 15l-5-5L5 21" />
             </svg>
           {/if}
         {/each}
@@ -284,14 +211,7 @@
 
     <!-- Size indicator (smallest variant) -->
     {#if !group.hasMultipleVariants && group.smallestVariant?.storage_size_megabytes}
-      {@const singleVariantFitStatus = getModelFitStatus(
-        group.smallestVariant.id,
-      )}
-      <span
-        class="text-xs font-mono flex-shrink-0 {getSizeClassForFitStatus(
-          singleVariantFitStatus,
-        )}"
-      >
+      <span class="text-xs font-mono text-white/30 flex-shrink-0">
         {formatSize(group.smallestVariant.storage_size_megabytes)}
       </span>
     {/if}
@@ -302,24 +222,13 @@
         .map((v) => v.storage_size_megabytes || 0)
         .filter((s) => s > 0)
         .sort((a, b) => a - b)}
-      <span
-        class="text-xs font-mono flex-shrink-0 {getSizeClassForFitStatus(
-          groupFitStatus,
-        )}"
-      >
+      <span class="text-xs font-mono text-white/30 flex-shrink-0">
         {group.variants.length} variants{#if sizes.length >= 2}{" "}({formatSize(
             sizes[0],
           )}-{formatSize(sizes[sizes.length - 1])}){/if}
       </span>
     {/if}
 
-    <!-- Time ago (for recent models) -->
-    {#if launchedAt}
-      <span class="text-xs font-mono text-white/20 flex-shrink-0">
-        {timeAgo(launchedAt)}
-      </span>
-    {/if}
-
     <!-- Download availability indicator -->
     {#if groupDownloadStatus && groupDownloadStatus.nodeIds.length > 0}
       <span
@@ -418,7 +327,6 @@
   {#if isExpanded && group.hasMultipleVariants}
     <div class="bg-black/20 border-t border-white/5">
       {#each group.variants as variant}
-        {@const fitStatus = getModelFitStatus(variant.id)}
         {@const modelCanFit = canModelFit(variant.id)}
         {@const isSelected = selectedModelId === variant.id}
         <button
@@ -443,11 +351,7 @@
           </span>
 
           <!-- Size -->
-          <span
-            class="text-xs font-mono flex-1 {getSizeClassForFitStatus(
-              fitStatus,
-            )}"
-          >
+          <span class="text-xs font-mono text-white/40 flex-1">
             {formatSize(variant.storage_size_megabytes)}
           </span>
 

dashboard/src/lib/components/ModelPickerModal.svelte

@@ -6,7 +6,6 @@
   import ModelFilterPopover from "./ModelFilterPopover.svelte";
   import HuggingFaceResultItem from "./HuggingFaceResultItem.svelte";
   import { getNodesWithModelDownloaded } from "$lib/utils/downloads";
-  import { getRecentEntries } from "$lib/stores/recents.svelte";
 
   interface ModelInfo {
     id: string;
@@ -47,18 +46,13 @@
     tags: string[];
   }
 
-  type ModelFitStatus = "fits_now" | "fits_cluster_capacity" | "too_large";
-
   type ModelPickerModalProps = {
     isOpen: boolean;
     models: ModelInfo[];
     selectedModelId: string | null;
     favorites: Set<string>;
-    recentModelIds?: string[];
-    hasRecents?: boolean;
     existingModelIds: Set<string>;
     canModelFit: (modelId: string) => boolean;
-    getModelFitStatus: (modelId: string) => ModelFitStatus;
     onSelect: (modelId: string) => void;
     onClose: () => void;
     onToggleFavorite: (baseModelId: string) => void;
@@ -82,11 +76,8 @@
     models,
     selectedModelId,
     favorites,
-    recentModelIds = [],
-    hasRecents: hasRecentsTab = false,
     existingModelIds,
     canModelFit,
-    getModelFitStatus,
     onSelect,
     onClose,
     onToggleFavorite,
@@ -372,8 +363,6 @@
       "deepseek",
       "gpt-oss",
       "llama",
-      "flux",
-      "qwen-image",
     ];
     return Array.from(families).sort((a, b) => {
       const aIdx = familyOrder.indexOf(a);
@@ -392,11 +381,7 @@
     // Filter by family
     if (selectedFamily === "favorites") {
       result = result.filter((g) => favorites.has(g.id));
-    } else if (
-      selectedFamily &&
-      selectedFamily !== "huggingface" &&
-      selectedFamily !== "recents"
-    ) {
+    } else if (selectedFamily && selectedFamily !== "huggingface") {
       result = result.filter((g) => g.family === selectedFamily);
     }
 
@@ -440,23 +425,13 @@
       );
     }
 
-    // Sort: fits-now first, then fits-cluster-capacity, then too-large
+    // Sort: models that fit first, then by size (largest first)
     result.sort((a, b) => {
-      const getGroupFitRank = (group: ModelGroup): number => {
-        let hasClusterCapacityOnly = false;
-        for (const variant of group.variants) {
-          const fitStatus = getModelFitStatus(variant.id);
-          if (fitStatus === "fits_now") return 0;
-          if (fitStatus === "fits_cluster_capacity") {
-            hasClusterCapacityOnly = true;
-          }
-        }
-        return hasClusterCapacityOnly ? 1 : 2;
-      };
+      const aFits = a.variants.some((v) => canModelFit(v.id));
+      const bFits = b.variants.some((v) => canModelFit(v.id));
 
-      const aRank = getGroupFitRank(a);
-      const bRank = getGroupFitRank(b);
-      if (aRank !== bRank) return aRank - bRank;
+      if (aFits && !bFits) return -1;
+      if (!aFits && bFits) return 1;
 
       return (
         (b.smallestVariant.storage_size_megabytes || 0) -
@@ -470,48 +445,6 @@
   // Check if any favorites exist
   const hasFavorites = $derived(favorites.size > 0);
 
-  // Timestamp lookup for recent models
-  const recentTimestamps = $derived(
-    new Map(getRecentEntries().map((e) => [e.modelId, e.launchedAt])),
-  );
-
-  // Recent models: single-variant ModelGroups in launch order
-  const recentGroups = $derived.by((): ModelGroup[] => {
-    if (!recentModelIds || recentModelIds.length === 0) return [];
-    const result: ModelGroup[] = [];
-    for (const id of recentModelIds) {
-      const model = models.find((m) => m.id === id);
-      if (model) {
-        result.push({
-          id: model.base_model || model.id,
-          name: model.name || model.id,
-          capabilities: model.capabilities || ["text"],
-          family: model.family || "",
-          variants: [model],
-          smallestVariant: model,
-          hasMultipleVariants: false,
-        });
-      }
-    }
-    return result;
-  });
-
-  // Filtered recent groups (apply search query)
-  const filteredRecentGroups = $derived.by((): ModelGroup[] => {
-    if (!searchQuery.trim()) return recentGroups;
-    const query = searchQuery.toLowerCase().trim();
-    return recentGroups.filter(
-      (g) =>
-        g.name.toLowerCase().includes(query) ||
-        g.variants.some(
-          (v) =>
-            v.id.toLowerCase().includes(query) ||
-            (v.name || "").toLowerCase().includes(query) ||
-            (v.quantization || "").toLowerCase().includes(query),
-        ),
-    );
-  });
-
   function toggleGroupExpanded(groupId: string) {
     const next = new Set(expandedGroups);
     if (next.has(groupId)) {
@@ -669,12 +602,11 @@
         families={uniqueFamilies}
         {selectedFamily}
         {hasFavorites}
-        hasRecents={hasRecentsTab}
         onSelect={(family) => (selectedFamily = family)}
       />
 
       <!-- Model list -->
-      <div class="flex-1 overflow-y-auto scrollbar-hide flex flex-col">
+      <div class="flex-1 overflow-y-auto flex flex-col">
         {#if selectedFamily === "huggingface"}
           <!-- HuggingFace Hub view -->
           <div class="flex-1 flex flex-col min-h-0">
@@ -692,7 +624,7 @@
             </div>
 
             <!-- Results list -->
-            <div class="flex-1 overflow-y-auto scrollbar-hide">
+            <div class="flex-1 overflow-y-auto">
               {#if hfIsLoadingTrending && hfTrendingModels.length === 0}
                 <div
                   class="flex items-center justify-center py-12 text-white/40"
@@ -777,45 +709,6 @@
               </div>
             </div>
           </div>
-        {:else if selectedFamily === "recents"}
-          <!-- Recent models view -->
-          {#if filteredRecentGroups.length === 0}
-            <div
-              class="flex flex-col items-center justify-center h-full text-white/40 p-8"
-            >
-              <svg
-                class="w-12 h-12 mb-3"
-                viewBox="0 0 24 24"
-                fill="currentColor"
-              >
-                <path
-                  d="M13 3a9 9 0 0 0-9 9H1l3.89 3.89.07.14L9 12H6c0-3.87 3.13-7 7-7s7 3.13 7 7-3.13 7-7 7c-1.93 0-3.68-.79-4.94-2.06l-1.42 1.42A8.954 8.954 0 0 0 13 21a9 9 0 0 0 0-18zm-1 5v5l4.28 2.54.72-1.21-3.5-2.08V8H12z"
-                />
-              </svg>
-              <p class="font-mono text-sm">
-                {searchQuery
-                  ? "No matching recent models"
-                  : "No recently launched models"}
-              </p>
-            </div>
-          {:else}
-            {#each filteredRecentGroups as group}
-              <ModelPickerGroup
-                {group}
-                isExpanded={expandedGroups.has(group.id)}
-                isFavorite={favorites.has(group.id)}
-                {selectedModelId}
-                {canModelFit}
-                {getModelFitStatus}
-                onToggleExpand={() => toggleGroupExpanded(group.id)}
-                onSelectModel={handleSelect}
-                {onToggleFavorite}
-                onShowInfo={(g) => (infoGroup = g)}
-                downloadStatusMap={getVariantDownloadMap(group)}
-                launchedAt={recentTimestamps.get(group.variants[0]?.id ?? "")}
-              />
-            {/each}
-          {/if}
         {:else if filteredGroups.length === 0}
           <div
             class="flex flex-col items-center justify-center h-full text-white/40 p-8"
@@ -847,7 +740,6 @@
               isFavorite={favorites.has(group.id)}
               {selectedModelId}
               {canModelFit}
-              {getModelFitStatus}
               onToggleExpand={() => toggleGroupExpanded(group.id)}
               onSelectModel={handleSelect}
               {onToggleFavorite}

dashboard/src/lib/components/TopologyGraph.svelte

@@ -6,8 +6,6 @@
     isTopologyMinimized,
     debugMode,
     nodeThunderboltBridge,
-    nodeRdmaCtl,
-    nodeIdentities,
     type NodeInfo,
   } from "$lib/stores/app.svelte";
 
@@ -33,8 +31,6 @@
   const data = $derived(topologyData());
   const debugEnabled = $derived(debugMode());
   const tbBridgeData = $derived(nodeThunderboltBridge());
-  const rdmaCtlData = $derived(nodeRdmaCtl());
-  const identitiesData = $derived(nodeIdentities());
 
   function getNodeLabel(nodeId: string): string {
     const node = data?.nodes?.[nodeId];
@@ -337,27 +333,14 @@
       if (edge.source === a) entry.aToB = true;
       else entry.bToA = true;
 
-      let ip: string;
-      let ifaceLabel: string;
-      let missingIface: boolean;
-
-      if (edge.sourceRdmaIface || edge.sinkRdmaIface) {
-        ip = "RDMA";
-        ifaceLabel = `${edge.sourceRdmaIface || "?"} \u2192 ${edge.sinkRdmaIface || "?"}`;
-        missingIface = false;
-      } else {
-        ip = edge.sendBackIp || "?";
-        const ifaceInfo = getInterfaceLabel(edge.source, ip);
-        ifaceLabel = ifaceInfo.label;
-        missingIface = ifaceInfo.missing;
-      }
-
+      const ip = edge.sendBackIp || "?";
+      const ifaceInfo = getInterfaceLabel(edge.source, ip);
       entry.connections.push({
         from: edge.source,
         to: edge.target,
         ip,
-        ifaceLabel,
-        missingIface,
+        ifaceLabel: ifaceInfo.label,
+        missingIface: ifaceInfo.missing,
       });
       pairMap.set(key, entry);
     });
@@ -1137,17 +1120,15 @@
           .text(` (${ramUsagePercent.toFixed(0)}%)`);
       }
 
-      // Debug mode: Show TB bridge and RDMA status
+      // Debug mode: Show TB bridge status
       if (debugEnabled) {
-        let debugLabelY =
-          nodeInfo.y +
-          iconBaseHeight / 2 +
-          (showFullLabels ? 32 : showCompactLabels ? 26 : 22);
-        const debugFontSize = showFullLabels ? 9 : 7;
-        const debugLineHeight = showFullLabels ? 11 : 9;
-
         const tbStatus = tbBridgeData[nodeInfo.id];
         if (tbStatus) {
+          const tbY =
+            nodeInfo.y +
+            iconBaseHeight / 2 +
+            (showFullLabels ? 32 : showCompactLabels ? 26 : 22);
+          const tbFontSize = showFullLabels ? 9 : 7;
           const tbColor = tbStatus.enabled
             ? "rgba(234,179,8,0.9)"
             : "rgba(100,100,100,0.7)";
@@ -1155,46 +1136,12 @@
           nodeG
             .append("text")
             .attr("x", nodeInfo.x)
-            .attr("y", debugLabelY)
+            .attr("y", tbY)
             .attr("text-anchor", "middle")
             .attr("fill", tbColor)
-            .attr("font-size", debugFontSize)
+            .attr("font-size", tbFontSize)
             .attr("font-family", "SF Mono, Monaco, monospace")
             .text(tbText);
-          debugLabelY += debugLineHeight;
-        }
-
-        const rdmaStatus = rdmaCtlData[nodeInfo.id];
-        if (rdmaStatus !== undefined) {
-          const rdmaColor = rdmaStatus.enabled
-            ? "rgba(74,222,128,0.9)"
-            : "rgba(100,100,100,0.7)";
-          const rdmaText = rdmaStatus.enabled ? "RDMA:ON" : "RDMA:OFF";
-          nodeG
-            .append("text")
-            .attr("x", nodeInfo.x)
-            .attr("y", debugLabelY)
-            .attr("text-anchor", "middle")
-            .attr("fill", rdmaColor)
-            .attr("font-size", debugFontSize)
-            .attr("font-family", "SF Mono, Monaco, monospace")
-            .text(rdmaText);
-          debugLabelY += debugLineHeight;
-        }
-
-        const identity = identitiesData[nodeInfo.id];
-        if (identity?.osVersion) {
-          nodeG
-            .append("text")
-            .attr("x", nodeInfo.x)
-            .attr("y", debugLabelY)
-            .attr("text-anchor", "middle")
-            .attr("fill", "rgba(179,179,179,0.7)")
-            .attr("font-size", debugFontSize)
-            .attr("font-family", "SF Mono, Monaco, monospace")
-            .text(
-              `macOS ${identity.osVersion}${identity.osBuildVersion ? ` (${identity.osBuildVersion})` : ""}`,
-            );
         }
       }
     });

dashboard/src/lib/stores/app.svelte.ts

@@ -49,7 +49,6 @@ export interface NodeInfo {
   };
   last_macmon_update: number;
   friendly_name?: string;
-  os_version?: string;
 }
 
 export interface TopologyEdge {
@@ -57,8 +56,6 @@ export interface TopologyEdge {
   target: string;
   sendBackIp?: string;
   sendBackInterface?: string;
-  sourceRdmaIface?: string;
-  sinkRdmaIface?: string;
 }
 
 export interface TopologyData {
@@ -79,8 +76,6 @@ interface RawNodeIdentity {
   modelId?: string;
   chipId?: string;
   friendlyName?: string;
-  osVersion?: string;
-  osBuildVersion?: string;
 }
 
 interface RawMemoryUsage {
@@ -230,19 +225,6 @@ interface RawStateResponse {
   nodeMemory?: Record<string, RawMemoryUsage>;
   nodeSystem?: Record<string, RawSystemPerformanceProfile>;
   nodeNetwork?: Record<string, RawNodeNetworkInfo>;
-  // Thunderbolt identifiers per node
-  nodeThunderbolt?: Record<
-    string,
-    {
-      interfaces: Array<{
-        rdmaInterface: string;
-        domainUuid: string;
-        linkSpeed: string;
-      }>;
-    }
-  >;
-  // RDMA ctl status per node
-  nodeRdmaCtl?: Record<string, { enabled: boolean }>;
   // Thunderbolt bridge status per node
   nodeThunderboltBridge?: Record<
     string,
@@ -296,7 +278,6 @@ export interface Conversation {
   modelId: string | null;
   sharding: string | null;
   instanceType: string | null;
-  enableThinking: boolean | null;
 }
 
 const STORAGE_KEY = "exo-conversations";
@@ -444,7 +425,6 @@ function transformTopology(
       },
       last_macmon_update: Date.now() / 1000,
       friendly_name: identity?.friendlyName,
-      os_version: identity?.osVersion,
     };
   }
 
@@ -457,8 +437,6 @@ function transformTopology(
         if (!Array.isArray(edgeList)) continue;
         for (const edge of edgeList) {
           let sendBackIp: string | undefined;
-          let sourceRdmaIface: string | undefined;
-          let sinkRdmaIface: string | undefined;
           if (edge && typeof edge === "object" && "sinkMultiaddr" in edge) {
             const multiaddr = edge.sinkMultiaddr;
             if (multiaddr) {
@@ -466,23 +444,10 @@ function transformTopology(
                 multiaddr.ip_address ||
                 extractIpFromMultiaddr(multiaddr.address);
             }
-          } else if (
-            edge &&
-            typeof edge === "object" &&
-            "sourceRdmaIface" in edge
-          ) {
-            sourceRdmaIface = edge.sourceRdmaIface;
-            sinkRdmaIface = edge.sinkRdmaIface;
           }
 
           if (nodes[source] && nodes[sink] && source !== sink) {
-            edges.push({
-              source,
-              target: sink,
-              sendBackIp,
-              sourceRdmaIface,
-              sinkRdmaIface,
-            });
+            edges.push({ source, target: sink, sendBackIp });
           }
         }
       }
@@ -525,32 +490,12 @@ class AppStore {
   instances = $state<Record<string, unknown>>({});
   runners = $state<Record<string, unknown>>({});
   downloads = $state<Record<string, unknown[]>>({});
-  nodeDisk = $state<
-    Record<
-      string,
-      { total: { inBytes: number }; available: { inBytes: number } }
-    >
-  >({});
   placementPreviews = $state<PlacementPreview[]>([]);
   selectedPreviewModelId = $state<string | null>(null);
   isLoadingPreviews = $state(false);
   previewNodeFilter = $state<Set<string>>(new Set());
   lastUpdate = $state<number | null>(null);
-  nodeIdentities = $state<Record<string, RawNodeIdentity>>({});
   thunderboltBridgeCycles = $state<string[][]>([]);
-  nodeThunderbolt = $state<
-    Record<
-      string,
-      {
-        interfaces: Array<{
-          rdmaInterface: string;
-          domainUuid: string;
-          linkSpeed: string;
-        }>;
-      }
-    >
-  >({});
-  nodeRdmaCtl = $state<Record<string, { enabled: boolean }>>({});
   nodeThunderboltBridge = $state<
     Record<
       string,
@@ -606,7 +551,6 @@ class AppStore {
           modelId: conversation.modelId ?? null,
           sharding: conversation.sharding ?? null,
           instanceType: conversation.instanceType ?? null,
-          enableThinking: conversation.enableThinking ?? null,
         }));
       }
     } catch (error) {
@@ -796,7 +740,6 @@ class AppStore {
       modelId: derivedModelId,
       sharding: derivedSharding,
       instanceType: derivedInstanceType,
-      enableThinking: null,
     };
 
     this.conversations.unshift(conversation);
@@ -822,7 +765,6 @@ class AppStore {
     this.hasStartedChat = true;
     this.isTopologyMinimized = true;
     this.isSidebarOpen = true; // Auto-open sidebar when chatting
-    this.thinkingEnabled = conversation.enableThinking ?? true;
     this.refreshConversationModelFromInstances();
 
     return true;
@@ -1264,15 +1206,6 @@ class AppStore {
       if (data.downloads) {
         this.downloads = data.downloads;
       }
-      if (data.nodeDisk) {
-        this.nodeDisk = data.nodeDisk;
-      }
-      // Node identities (for OS version mismatch detection)
-      this.nodeIdentities = data.nodeIdentities ?? {};
-      // Thunderbolt identifiers per node
-      this.nodeThunderbolt = data.nodeThunderbolt ?? {};
-      // RDMA ctl status per node
-      this.nodeRdmaCtl = data.nodeRdmaCtl ?? {};
       // Thunderbolt bridge cycles
       this.thunderboltBridgeCycles = data.thunderboltBridgeCycles ?? [];
       // Thunderbolt bridge status per node
@@ -1936,11 +1869,6 @@ class AppStore {
     }
   }
 
-  /**
-   * Whether thinking is enabled for the current conversation
-   */
-  thinkingEnabled = $state(true);
-
   /**
    * Selected model for chat (can be set by the UI)
    */
@@ -2119,7 +2047,6 @@ class AppStore {
       textContent?: string;
       preview?: string;
     }[],
-    enableThinking?: boolean | null,
   ): Promise<void> {
     if ((!content.trim() && (!files || files.length === 0)) || this.isLoading)
       return;
@@ -2267,9 +2194,6 @@ class AppStore {
           stream: true,
           logprobs: true,
           top_logprobs: 5,
-          ...(enableThinking != null && {
-            enable_thinking: enableThinking,
-          }),
         }),
       });
 
@@ -2928,18 +2852,6 @@ class AppStore {
     );
   }
 
-  /**
-   * Update the thinking preference for the active conversation
-   */
-  setConversationThinking(enabled: boolean) {
-    this.thinkingEnabled = enabled;
-    const conv = this.getActiveConversation();
-    if (conv) {
-      conv.enableThinking = enabled;
-      this.saveConversationsToStorage();
-    }
-  }
-
   /**
    * Start a download on a specific node
    */
@@ -3046,14 +2958,12 @@ export const topologyData = () => appStore.topologyData;
 export const instances = () => appStore.instances;
 export const runners = () => appStore.runners;
 export const downloads = () => appStore.downloads;
-export const nodeDisk = () => appStore.nodeDisk;
 export const placementPreviews = () => appStore.placementPreviews;
 export const selectedPreviewModelId = () => appStore.selectedPreviewModelId;
 export const isLoadingPreviews = () => appStore.isLoadingPreviews;
 export const lastUpdate = () => appStore.lastUpdate;
 export const isTopologyMinimized = () => appStore.isTopologyMinimized;
 export const selectedChatModel = () => appStore.selectedChatModel;
-export const thinkingEnabled = () => appStore.thinkingEnabled;
 export const debugMode = () => appStore.getDebugMode();
 export const topologyOnlyMode = () => appStore.getTopologyOnlyMode();
 export const chatSidebarVisible = () => appStore.getChatSidebarVisible();
@@ -3069,8 +2979,7 @@ export const sendMessage = (
     textContent?: string;
     preview?: string;
   }[],
-  enableThinking?: boolean | null,
-) => appStore.sendMessage(content, files, enableThinking);
+) => appStore.sendMessage(content, files);
 export const generateImage = (prompt: string, modelId?: string) =>
   appStore.generateImage(prompt, modelId);
 export const editImage = (
@@ -3113,8 +3022,6 @@ export const deleteAllConversations = () => appStore.deleteAllConversations();
 export const renameConversation = (id: string, name: string) =>
   appStore.renameConversation(id, name);
 export const getActiveConversation = () => appStore.getActiveConversation();
-export const setConversationThinking = (enabled: boolean) =>
-  appStore.setConversationThinking(enabled);
 
 // Sidebar actions
 export const isSidebarOpen = () => appStore.isSidebarOpen;
@@ -3131,12 +3038,7 @@ export const setChatSidebarVisible = (visible: boolean) =>
   appStore.setChatSidebarVisible(visible);
 export const refreshState = () => appStore.fetchState();
 
-// Node identities (for OS version mismatch detection)
-export const nodeIdentities = () => appStore.nodeIdentities;
-
-// Thunderbolt & RDMA status
-export const nodeThunderbolt = () => appStore.nodeThunderbolt;
-export const nodeRdmaCtl = () => appStore.nodeRdmaCtl;
+// Thunderbolt bridge status
 export const thunderboltBridgeCycles = () => appStore.thunderboltBridgeCycles;
 export const nodeThunderboltBridge = () => appStore.nodeThunderboltBridge;
 

dashboard/src/lib/stores/recents.svelte.ts

@@ -1,75 +0,0 @@
-/**
- * RecentsStore - Manages recently launched models with localStorage persistence
- */
-
-import { browser } from "$app/environment";
-
-const RECENTS_KEY = "exo-recent-models";
-const MAX_RECENT_MODELS = 20;
-
-interface RecentEntry {
-  modelId: string;
-  launchedAt: number;
-}
-
-class RecentsStore {
-  recents = $state<RecentEntry[]>([]);
-
-  constructor() {
-    if (browser) {
-      this.loadFromStorage();
-    }
-  }
-
-  private loadFromStorage() {
-    try {
-      const stored = localStorage.getItem(RECENTS_KEY);
-      if (stored) {
-        const parsed = JSON.parse(stored) as RecentEntry[];
-        this.recents = parsed;
-      }
-    } catch (error) {
-      console.error("Failed to load recent models:", error);
-    }
-  }
-
-  private saveToStorage() {
-    try {
-      localStorage.setItem(RECENTS_KEY, JSON.stringify(this.recents));
-    } catch (error) {
-      console.error("Failed to save recent models:", error);
-    }
-  }
-
-  recordLaunch(modelId: string) {
-    // Remove existing entry for this model (if any) to move it to top
-    const filtered = this.recents.filter((r) => r.modelId !== modelId);
-    // Prepend new entry
-    const next = [{ modelId, launchedAt: Date.now() }, ...filtered];
-    // Cap at max
-    this.recents = next.slice(0, MAX_RECENT_MODELS);
-    this.saveToStorage();
-  }
-
-  getRecentModelIds(): string[] {
-    return this.recents.map((r) => r.modelId);
-  }
-
-  hasAny(): boolean {
-    return this.recents.length > 0;
-  }
-
-  clearAll() {
-    this.recents = [];
-    this.saveToStorage();
-  }
-}
-
-export const recentsStore = new RecentsStore();
-
-export const hasRecents = () => recentsStore.hasAny();
-export const getRecentModelIds = () => recentsStore.getRecentModelIds();
-export const getRecentEntries = () => recentsStore.recents;
-export const recordRecentLaunch = (modelId: string) =>
-  recentsStore.recordLaunch(modelId);
-export const clearRecents = () => recentsStore.clearAll();

dashboard/src/routes/+page.svelte

@@ -12,11 +12,6 @@
     toggleFavorite,
     getFavoritesSet,
   } from "$lib/stores/favorites.svelte";
-  import {
-    hasRecents,
-    getRecentModelIds,
-    recordRecentLaunch,
-  } from "$lib/stores/recents.svelte";
   import {
     hasStartedChat,
     isTopologyMinimized,
@@ -42,11 +37,8 @@
     toggleTopologyOnlyMode,
     chatSidebarVisible,
     toggleChatSidebarVisible,
-    nodeThunderbolt,
-    nodeRdmaCtl,
     thunderboltBridgeCycles,
     nodeThunderboltBridge,
-    nodeIdentities,
     type DownloadProgress,
     type PlacementPreview,
   } from "$lib/stores/app.svelte";
@@ -70,50 +62,8 @@
   const sidebarVisible = $derived(chatSidebarVisible());
   const tbBridgeCycles = $derived(thunderboltBridgeCycles());
   const tbBridgeData = $derived(nodeThunderboltBridge());
-  const identitiesData = $derived(nodeIdentities());
-  const tbIdentifiers = $derived(nodeThunderbolt());
-  const rdmaCtlData = $derived(nodeRdmaCtl());
   const nodeFilter = $derived(previewNodeFilter());
 
-  // Detect macOS version mismatches across cluster nodes
-  const macosVersionMismatch = $derived.by(() => {
-    if (!identitiesData) return null;
-    const entries = Object.entries(identitiesData);
-    // Filter to macOS nodes (version starts with a digit, e.g. "15.3")
-    const macosNodes = entries.filter(([_, id]) => {
-      const v = id.osVersion;
-      return v && v !== "Unknown" && /^\d/.test(v);
-    });
-    if (macosNodes.length < 2) return null;
-    // Compare on buildVersion for precise mismatch detection
-    const buildVersions = new Set(
-      macosNodes.map(([_, id]) => id.osBuildVersion ?? id.osVersion),
-    );
-    if (buildVersions.size <= 1) return null;
-    return macosNodes.map(([nodeId, id]) => ({
-      nodeId,
-      friendlyName: getNodeName(nodeId),
-      version: id.osVersion!,
-      buildVersion: id.osBuildVersion ?? "Unknown",
-    }));
-  });
-
-  // Detect TB5 nodes where RDMA is not enabled
-  const tb5WithoutRdma = $derived.by(() => {
-    const rdmaCtl = rdmaCtlData;
-    if (!rdmaCtl) return false;
-    const ids = tbIdentifiers;
-    if (!ids) return false;
-    // Find nodes with TB5 hardware (any TB interface)
-    const tb5NodeIds = Object.entries(ids)
-      .filter(([_, node]) => node.interfaces.length > 0)
-      .map(([id]) => id);
-    if (tb5NodeIds.length < 2) return false;
-    // At least one TB5 node has RDMA disabled
-    return tb5NodeIds.some((id) => rdmaCtl[id]?.enabled !== true);
-  });
-  let tb5InfoDismissed = $state(false);
-
   // Helper to get friendly node name from node ID
   function getNodeName(nodeId: string): string {
     const node = data?.nodes?.[nodeId];
@@ -146,12 +96,6 @@
     }
   }
 
-  // Warning icon SVG path (reused across warning snippets)
-  const warningIconPath =
-    "M12 9v2m0 4h.01m-6.938 4h13.856c1.54 0 2.502-1.667 1.732-3L13.732 4c-.77-1.333-2.694-1.333-3.464 0L3.34 16c-.77 1.333.192 3 1.732 3z";
-  const infoIconPath =
-    "M13 16h-1v-4h-1m1-4h.01M21 12a9 9 0 11-18 0 9 9 0 0118 0z";
-
   let mounted = $state(false);
 
   // Instance launch state
@@ -169,10 +113,6 @@
       capabilities?: string[];
     }>
   >([]);
-  type ModelMemoryFitStatus =
-    | "fits_now"
-    | "fits_cluster_capacity"
-    | "too_large";
 
   // Model tasks lookup for ChatForm - maps both short IDs and full HuggingFace IDs
   const modelTasks = $derived(() => {
@@ -190,19 +130,6 @@
     return tasks;
   });
 
-  const modelCapabilities = $derived(() => {
-    const caps: Record<string, string[]> = {};
-    for (const model of models) {
-      if (model.capabilities && model.capabilities.length > 0) {
-        caps[model.id] = model.capabilities;
-        if (model.hugging_face_id) {
-          caps[model.hugging_face_id] = model.capabilities;
-        }
-      }
-    }
-    return caps;
-  });
-
   // Helper to check if a model supports image generation
   function modelSupportsImageGeneration(modelId: string): boolean {
     const model = models.find(
@@ -301,10 +228,6 @@
   // Favorites state (reactive)
   const favoritesSet = $derived(getFavoritesSet());
 
-  // Recent models state (reactive)
-  const recentModelIds = $derived(getRecentModelIds());
-  const showRecentsTab = $derived(hasRecents());
-
   // Slider dragging state
   let isDraggingSlider = $state(false);
   let sliderTrackElement: HTMLDivElement | null = $state(null);
@@ -527,41 +450,14 @@
     );
   });
 
-  // Calculate total memory in the cluster (in GB)
-  const clusterTotalMemoryGB = $derived(() => {
-    if (!data) return 0;
-    return (
-      Object.values(data.nodes).reduce((acc, n) => {
-        const total =
-          n.macmon_info?.memory?.ram_total ?? n.system_info?.memory ?? 0;
-        return acc + total;
-      }, 0) /
-      (1024 * 1024 * 1024)
-    );
-  });
-
-  function getModelMemoryFitStatus(model: {
-    id: string;
-    name?: string;
-    storage_size_megabytes?: number;
-  }): ModelMemoryFitStatus {
-    const modelSizeGB = getModelSizeGB(model);
-    if (modelSizeGB <= availableMemoryGB()) {
-      return "fits_now";
-    }
-    if (modelSizeGB <= clusterTotalMemoryGB()) {
-      return "fits_cluster_capacity";
-    }
-    return "too_large";
-  }
-
   // Check if a model has enough memory to run
   function hasEnoughMemory(model: {
     id: string;
     name?: string;
     storage_size_megabytes?: number;
   }): boolean {
-    return getModelMemoryFitStatus(model) === "fits_now";
+    const modelSizeGB = getModelSizeGB(model);
+    return modelSizeGB <= availableMemoryGB();
   }
 
   // Sorted models for dropdown - biggest first, unrunnable at the end
@@ -734,9 +630,6 @@
         // Always auto-select the newly launched model so the user chats to what they just launched
         setSelectedChatModel(modelId);
 
-        // Record the launch in recent models history
-        recordRecentLaunch(modelId);
-
         // Scroll to the bottom of instances container to show the new instance
         // Use multiple attempts to ensure DOM has updated with the new instance
         const scrollToBottom = () => {
@@ -1764,249 +1657,6 @@
   });
 </script>
 
-{#snippet clusterWarnings()}
-  {#if tbBridgeCycles.length > 0 || macosVersionMismatch || (tb5WithoutRdma && !tb5InfoDismissed)}
-    <div class="absolute top-4 left-4 flex flex-col gap-2 z-40">
-      {#if tbBridgeCycles.length > 0}
-        {@const cycle = tbBridgeCycles[0]}
-        {@const serviceName = getTbBridgeServiceName(cycle)}
-        {@const disableCmd = `sudo networksetup -setnetworkserviceenabled "${serviceName}" off`}
-        <div class="group relative" role="alert">
-          <div
-            class="flex items-center gap-2 px-3 py-2 rounded border border-yellow-500/50 bg-yellow-500/10 backdrop-blur-sm cursor-help"
-          >
-            <svg
-              class="w-5 h-5 text-yellow-400 flex-shrink-0"
-              fill="none"
-              viewBox="0 0 24 24"
-              stroke="currentColor"
-              stroke-width="2"
-            >
-              <path
-                stroke-linecap="round"
-                stroke-linejoin="round"
-                d={warningIconPath}
-              />
-            </svg>
-            <span class="text-sm font-mono text-yellow-200">
-              THUNDERBOLT BRIDGE CYCLE DETECTED
-            </span>
-          </div>
-
-          <!-- Tooltip on hover -->
-          <div
-            class="absolute top-full left-0 mt-2 w-80 p-3 rounded border border-yellow-500/30 bg-exo-dark-gray/95 backdrop-blur-sm opacity-0 invisible group-hover:opacity-100 group-hover:visible transition-all duration-200 z-50 shadow-lg"
-          >
-            <p class="text-xs text-white/80 mb-2">
-              A network routing cycle was detected between nodes connected via
-              Thunderbolt Bridge. This can cause connectivity issues.
-            </p>
-            <p class="text-xs text-white/60 mb-2">
-              <span class="text-yellow-300">Affected nodes:</span>
-              {cycle.map(getNodeName).join(" → ")}
-            </p>
-            <p class="text-xs text-white/60 mb-1">
-              <span class="text-yellow-300">To fix:</span> Disable the Thunderbolt
-              Bridge on one of the affected nodes:
-            </p>
-            <button
-              type="button"
-              onclick={() => copyToClipboard(disableCmd)}
-              class="w-full flex items-center gap-2 text-[10px] font-mono bg-exo-black/60 px-2 py-1.5 rounded text-exo-yellow break-all text-left hover:bg-exo-black/80 transition-colors cursor-pointer group/copy"
-              title="Click to copy"
-            >
-              <span class="flex-1">{disableCmd}</span>
-              <svg
-                class="w-3.5 h-3.5 flex-shrink-0 text-white/40 group-hover/copy:text-exo-yellow transition-colors"
-                fill="none"
-                viewBox="0 0 24 24"
-                stroke="currentColor"
-                stroke-width="2"
-              >
-                {#if copiedCommand}
-                  <path
-                    stroke-linecap="round"
-                    stroke-linejoin="round"
-                    d="M5 13l4 4L19 7"
-                  />
-                {:else}
-                  <path
-                    stroke-linecap="round"
-                    stroke-linejoin="round"
-                    d="M8 16H6a2 2 0 01-2-2V6a2 2 0 012-2h8a2 2 0 012 2v2m-6 12h8a2 2 0 002-2v-8a2 2 0 00-2-2h-8a2 2 0 00-2 2v8a2 2 0 002 2z"
-                  />
-                {/if}
-              </svg>
-            </button>
-          </div>
-        </div>
-      {/if}
-
-      {#if macosVersionMismatch}
-        <div class="group relative" role="alert">
-          <div
-            class="flex items-center gap-2 px-3 py-2 rounded border border-yellow-500/50 bg-yellow-500/10 backdrop-blur-sm cursor-help"
-          >
-            <svg
-              class="w-5 h-5 text-yellow-400 flex-shrink-0"
-              fill="none"
-              viewBox="0 0 24 24"
-              stroke="currentColor"
-              stroke-width="2"
-            >
-              <path
-                stroke-linecap="round"
-                stroke-linejoin="round"
-                d={warningIconPath}
-              />
-            </svg>
-            <span class="text-sm font-mono text-yellow-200">
-              INCOMPATIBLE macOS VERSIONS
-            </span>
-          </div>
-
-          <!-- Tooltip on hover -->
-          <div
-            class="absolute top-full left-0 mt-2 w-80 p-3 rounded border border-yellow-500/30 bg-exo-dark-gray/95 backdrop-blur-sm opacity-0 invisible group-hover:opacity-100 group-hover:visible transition-all duration-200 z-50 shadow-lg"
-          >
-            <p class="text-xs text-white/80 mb-2">
-              Nodes in this cluster are running different macOS versions. This
-              may cause inference compatibility issues.
-            </p>
-            <div class="text-xs text-white/60 mb-2">
-              <span class="text-yellow-300">Node versions:</span>
-              {#each macosVersionMismatch as node}
-                <div class="ml-2">
-                  {node.friendlyName} — macOS {node.version} ({node.buildVersion})
-                </div>
-              {/each}
-            </div>
-            <p class="text-xs text-white/60">
-              <span class="text-yellow-300">Suggested action:</span> Update all nodes
-              to the same macOS version for best compatibility.
-            </p>
-          </div>
-        </div>
-      {/if}
-
-      {#if tb5WithoutRdma && !tb5InfoDismissed}
-        <div
-          class="flex items-center gap-2 px-3 py-2 rounded border border-blue-400/50 bg-blue-400/10 backdrop-blur-sm"
-          role="status"
-        >
-          <svg
-            class="w-5 h-5 text-blue-400 flex-shrink-0"
-            fill="none"
-            viewBox="0 0 24 24"
-            stroke="currentColor"
-            stroke-width="2"
-          >
-            <path
-              stroke-linecap="round"
-              stroke-linejoin="round"
-              d={infoIconPath}
-            />
-          </svg>
-          <span class="text-sm font-mono text-blue-200"> RDMA AVAILABLE </span>
-          <button
-            type="button"
-            onclick={() => (tb5InfoDismissed = true)}
-            class="ml-1 text-blue-300/60 hover:text-blue-200 transition-colors cursor-pointer"
-            title="Dismiss"
-          >
-            <svg
-              class="w-4 h-4"
-              fill="none"
-              viewBox="0 0 24 24"
-              stroke="currentColor"
-              stroke-width="2"
-            >
-              <path
-                stroke-linecap="round"
-                stroke-linejoin="round"
-                d="M6 18L18 6M6 6l12 12"
-              />
-            </svg>
-          </button>
-        </div>
-      {/if}
-    </div>
-  {/if}
-{/snippet}
-
-{#snippet clusterWarningsCompact()}
-  {#if tbBridgeCycles.length > 0 || macosVersionMismatch || (tb5WithoutRdma && !tb5InfoDismissed)}
-    <div class="absolute top-2 left-2 flex flex-col gap-1">
-      {#if tbBridgeCycles.length > 0}
-        <div
-          class="flex items-center gap-1.5 px-2 py-1 rounded border border-yellow-500/50 bg-yellow-500/10 backdrop-blur-sm"
-          title="Thunderbolt Bridge cycle detected"
-        >
-          <svg
-            class="w-3.5 h-3.5 text-yellow-400"
-            fill="none"
-            viewBox="0 0 24 24"
-            stroke="currentColor"
-            stroke-width="2"
-          >
-            <path
-              stroke-linecap="round"
-              stroke-linejoin="round"
-              d={warningIconPath}
-            />
-          </svg>
-          <span class="text-[10px] font-mono text-yellow-200">TB CYCLE</span>
-        </div>
-      {/if}
-      {#if macosVersionMismatch}
-        <div
-          class="flex items-center gap-1.5 px-2 py-1 rounded border border-yellow-500/50 bg-yellow-500/10 backdrop-blur-sm"
-          title="Incompatible macOS versions detected"
-        >
-          <svg
-            class="w-3.5 h-3.5 text-yellow-400"
-            fill="none"
-            viewBox="0 0 24 24"
-            stroke="currentColor"
-            stroke-width="2"
-          >
-            <path
-              stroke-linecap="round"
-              stroke-linejoin="round"
-              d={warningIconPath}
-            />
-          </svg>
-          <span class="text-[10px] font-mono text-yellow-200"
-            >macOS MISMATCH</span
-          >
-        </div>
-      {/if}
-      {#if tb5WithoutRdma && !tb5InfoDismissed}
-        <div
-          class="flex items-center gap-1.5 px-2 py-1 rounded border border-blue-400/50 bg-blue-400/10 backdrop-blur-sm"
-          title="Thunderbolt 5 detected — RDMA can be enabled for better performance"
-        >
-          <svg
-            class="w-3.5 h-3.5 text-blue-400"
-            fill="none"
-            viewBox="0 0 24 24"
-            stroke="currentColor"
-            stroke-width="2"
-          >
-            <path
-              stroke-linecap="round"
-              stroke-linejoin="round"
-              d={infoIconPath}
-            />
-          </svg>
-          <span class="text-[10px] font-mono text-blue-200">RDMA AVAILABLE</span
-          >
-        </div>
-      {/if}
-    </div>
-  {/if}
-{/snippet}
-
 <!-- Global event listeners for slider dragging -->
 <svelte:window
   onmousemove={handleSliderMouseMove}
@@ -2074,40 +1724,17 @@
             onNodeClick={togglePreviewNodeFilter}
           />
 
-          {@render clusterWarnings()}
-
-          <!-- TB5 RDMA Available Info -->
-          {#if tb5WithoutRdma && !tb5InfoDismissed}
-            <div
-              class="absolute left-4 flex items-center gap-2 px-3 py-2 rounded border border-blue-400/50 bg-blue-400/10 backdrop-blur-sm"
-              class:top-16={tbBridgeCycles.length > 0}
-              class:top-4={tbBridgeCycles.length === 0}
-              role="status"
-            >
-              <svg
-                class="w-5 h-5 text-blue-400 flex-shrink-0"
-                fill="none"
-                viewBox="0 0 24 24"
-                stroke="currentColor"
-                stroke-width="2"
-              >
-                <path
-                  stroke-linecap="round"
-                  stroke-linejoin="round"
-                  d="M13 16h-1v-4h-1m1-4h.01M21 12a9 9 0 11-18 0 9 9 0 0118 0z"
-                />
-              </svg>
-              <span class="text-sm font-mono text-blue-200">
-                RDMA AVAILABLE
-              </span>
-              <button
-                type="button"
-                onclick={() => (tb5InfoDismissed = true)}
-                class="ml-1 text-blue-300/60 hover:text-blue-200 transition-colors cursor-pointer"
-                title="Dismiss"
+          <!-- Thunderbolt Bridge Cycle Warning -->
+          {#if tbBridgeCycles.length > 0}
+            {@const cycle = tbBridgeCycles[0]}
+            {@const serviceName = getTbBridgeServiceName(cycle)}
+            {@const disableCmd = `sudo networksetup -setnetworkserviceenabled "${serviceName}" off`}
+            <div class="absolute top-4 left-4 group" role="alert">
+              <div
+                class="flex items-center gap-2 px-3 py-2 rounded border border-yellow-500/50 bg-yellow-500/10 backdrop-blur-sm cursor-help"
               >
                 <svg
-                  class="w-4 h-4"
+                  class="w-5 h-5 text-yellow-400 flex-shrink-0"
                   fill="none"
                   viewBox="0 0 24 24"
                   stroke="currentColor"
@@ -2116,10 +1743,60 @@
                   <path
                     stroke-linecap="round"
                     stroke-linejoin="round"
-                    d="M6 18L18 6M6 6l12 12"
+                    d="M12 9v2m0 4h.01m-6.938 4h13.856c1.54 0 2.502-1.667 1.732-3L13.732 4c-.77-1.333-2.694-1.333-3.464 0L3.34 16c-.77 1.333.192 3 1.732 3z"
                   />
                 </svg>
-              </button>
+                <span class="text-sm font-mono text-yellow-200">
+                  THUNDERBOLT BRIDGE CYCLE DETECTED
+                </span>
+              </div>
+
+              <!-- Tooltip on hover -->
+              <div
+                class="absolute top-full left-0 mt-2 w-80 p-3 rounded border border-yellow-500/30 bg-exo-dark-gray/95 backdrop-blur-sm opacity-0 invisible group-hover:opacity-100 group-hover:visible transition-all duration-200 z-50 shadow-lg"
+              >
+                <p class="text-xs text-white/80 mb-2">
+                  A network routing cycle was detected between nodes connected
+                  via Thunderbolt Bridge. This can cause connectivity issues.
+                </p>
+                <p class="text-xs text-white/60 mb-2">
+                  <span class="text-yellow-300">Affected nodes:</span>
+                  {cycle.map(getNodeName).join(" → ")}
+                </p>
+                <p class="text-xs text-white/60 mb-1">
+                  <span class="text-yellow-300">To fix:</span> Disable the Thunderbolt
+                  Bridge on one of the affected nodes:
+                </p>
+                <button
+                  type="button"
+                  onclick={() => copyToClipboard(disableCmd)}
+                  class="w-full flex items-center gap-2 text-[10px] font-mono bg-exo-black/60 px-2 py-1.5 rounded text-exo-yellow break-all text-left hover:bg-exo-black/80 transition-colors cursor-pointer group/copy"
+                  title="Click to copy"
+                >
+                  <span class="flex-1">{disableCmd}</span>
+                  <svg
+                    class="w-3.5 h-3.5 flex-shrink-0 text-white/40 group-hover/copy:text-exo-yellow transition-colors"
+                    fill="none"
+                    viewBox="0 0 24 24"
+                    stroke="currentColor"
+                    stroke-width="2"
+                  >
+                    {#if copiedCommand}
+                      <path
+                        stroke-linecap="round"
+                        stroke-linejoin="round"
+                        d="M5 13l4 4L19 7"
+                      />
+                    {:else}
+                      <path
+                        stroke-linecap="round"
+                        stroke-linejoin="round"
+                        d="M8 16H6a2 2 0 01-2-2V6a2 2 0 012-2h8a2 2 0 012 2v2m-6 12h8a2 2 0 002-2v-8a2 2 0 00-2-2h-8a2 2 0 00-2 2v8a2 2 0 002 2z"
+                      />
+                    {/if}
+                  </svg>
+                </button>
+              </div>
             </div>
           {/if}
 
@@ -2166,21 +1843,17 @@
               onNodeClick={togglePreviewNodeFilter}
             />
 
-            {@render clusterWarnings()}
-
-            <!-- TB5 RDMA Available Info -->
-            {#if tb5WithoutRdma && !tb5InfoDismissed}
-              <div
-                class="absolute left-4 group"
-                class:top-16={tbBridgeCycles.length > 0}
-                class:top-4={tbBridgeCycles.length === 0}
-                role="status"
-              >
+            <!-- Thunderbolt Bridge Cycle Warning -->
+            {#if tbBridgeCycles.length > 0}
+              {@const cycle = tbBridgeCycles[0]}
+              {@const serviceName = getTbBridgeServiceName(cycle)}
+              {@const disableCmd = `sudo networksetup -setnetworkserviceenabled "${serviceName}" off`}
+              <div class="absolute top-4 left-4 group" role="alert">
                 <div
-                  class="flex items-center gap-2 px-3 py-2 rounded border border-blue-400/50 bg-blue-400/10 backdrop-blur-sm"
+                  class="flex items-center gap-2 px-3 py-2 rounded border border-yellow-500/50 bg-yellow-500/10 backdrop-blur-sm cursor-help"
                 >
                   <svg
-                    class="w-5 h-5 text-blue-400 flex-shrink-0"
+                    class="w-5 h-5 text-yellow-400 flex-shrink-0"
                     fill="none"
                     viewBox="0 0 24 24"
                     stroke="currentColor"
@@ -2189,62 +1862,60 @@
                     <path
                       stroke-linecap="round"
                       stroke-linejoin="round"
-                      d="M13 16h-1v-4h-1m1-4h.01M21 12a9 9 0 11-18 0 9 9 0 0118 0z"
+                      d="M12 9v2m0 4h.01m-6.938 4h13.856c1.54 0 2.502-1.667 1.732-3L13.732 4c-.77-1.333-2.694-1.333-3.464 0L3.34 16c-.77 1.333.192 3 1.732 3z"
                     />
                   </svg>
-                  <span class="text-sm font-mono text-blue-200">
-                    RDMA AVAILABLE
+                  <span class="text-sm font-mono text-yellow-200">
+                    THUNDERBOLT BRIDGE CYCLE DETECTED
                   </span>
+                </div>
+
+                <!-- Tooltip on hover -->
+                <div
+                  class="absolute top-full left-0 mt-2 w-80 p-3 rounded border border-yellow-500/30 bg-exo-dark-gray/95 backdrop-blur-sm opacity-0 invisible group-hover:opacity-100 group-hover:visible transition-all duration-200 z-50 shadow-lg"
+                >
+                  <p class="text-xs text-white/80 mb-2">
+                    A network routing cycle was detected between nodes connected
+                    via Thunderbolt Bridge. This can cause connectivity issues.
+                  </p>
+                  <p class="text-xs text-white/60 mb-2">
+                    <span class="text-yellow-300">Affected nodes:</span>
+                    {cycle.map(getNodeName).join(" → ")}
+                  </p>
+                  <p class="text-xs text-white/60 mb-1">
+                    <span class="text-yellow-300">To fix:</span> Disable the Thunderbolt
+                    Bridge on one of the affected nodes:
+                  </p>
                   <button
                     type="button"
-                    onclick={() => (tb5InfoDismissed = true)}
-                    class="ml-1 text-blue-300/60 hover:text-blue-200 transition-colors cursor-pointer"
-                    title="Dismiss"
+                    onclick={() => copyToClipboard(disableCmd)}
+                    class="w-full flex items-center gap-2 text-[10px] font-mono bg-exo-black/60 px-2 py-1.5 rounded text-exo-yellow break-all text-left hover:bg-exo-black/80 transition-colors cursor-pointer group/copy"
+                    title="Click to copy"
                   >
+                    <span class="flex-1">{disableCmd}</span>
                     <svg
-                      class="w-4 h-4"
+                      class="w-3.5 h-3.5 flex-shrink-0 text-white/40 group-hover/copy:text-exo-yellow transition-colors"
                       fill="none"
                       viewBox="0 0 24 24"
                       stroke="currentColor"
                       stroke-width="2"
                     >
-                      <path
-                        stroke-linecap="round"
-                        stroke-linejoin="round"
-                        d="M6 18L18 6M6 6l12 12"
-                      />
+                      {#if copiedCommand}
+                        <path
+                          stroke-linecap="round"
+                          stroke-linejoin="round"
+                          d="M5 13l4 4L19 7"
+                        />
+                      {:else}
+                        <path
+                          stroke-linecap="round"
+                          stroke-linejoin="round"
+                          d="M8 16H6a2 2 0 01-2-2V6a2 2 0 012-2h8a2 2 0 012 2v2m-6 12h8a2 2 0 002-2v-8a2 2 0 00-2-2h-8a2 2 0 00-2 2v8a2 2 0 002 2z"
+                        />
+                      {/if}
                     </svg>
                   </button>
                 </div>
-
-                <!-- Tooltip on hover -->
-                <div
-                  class="absolute top-full left-0 mt-2 w-80 p-3 rounded border border-blue-400/30 bg-exo-dark-gray/95 backdrop-blur-sm opacity-0 invisible group-hover:opacity-100 group-hover:visible transition-all duration-200 z-50 shadow-lg"
-                >
-                  <p class="text-xs text-white/80 mb-2">
-                    Thunderbolt 5 hardware detected on multiple nodes. Enable
-                    RDMA for significantly faster inter-node communication.
-                  </p>
-                  <p class="text-xs text-white/60 mb-1.5">
-                    <span class="text-blue-300">To enable:</span>
-                  </p>
-                  <ol
-                    class="text-xs text-white/60 list-decimal list-inside space-y-0.5 mb-1.5"
-                  >
-                    <li>Connect nodes with TB5 cables</li>
-                    <li>Boot to Recovery (hold power 10s → Options)</li>
-                    <li>
-                      Run
-                      <code class="text-blue-300 bg-blue-400/10 px-1 rounded"
-                        >rdma_ctl enable</code
-                      >
-                    </li>
-                    <li>Reboot</li>
-                  </ol>
-                  <p class="text-xs text-white/40">
-                    Requires macOS 26.2+, TB5 cables, and matching OS versions.
-                  </p>
-                </div>
               </div>
             {/if}
 
@@ -2283,7 +1954,6 @@
                 showHelperText={false}
                 showModelSelector={true}
                 modelTasks={modelTasks()}
-                modelCapabilities={modelCapabilities()}
               />
             </div>
           </div>
@@ -3063,7 +2733,6 @@
                 placeholder="Ask anything"
                 showModelSelector={true}
                 modelTasks={modelTasks()}
-                modelCapabilities={modelCapabilities()}
               />
             </div>
           </div>
@@ -3104,7 +2773,30 @@
                   onNodeClick={togglePreviewNodeFilter}
                 />
 
-                {@render clusterWarningsCompact()}
+                <!-- Thunderbolt Bridge Cycle Warning (compact) -->
+                {#if tbBridgeCycles.length > 0}
+                  <div
+                    class="absolute top-2 left-2 flex items-center gap-1.5 px-2 py-1 rounded border border-yellow-500/50 bg-yellow-500/10 backdrop-blur-sm"
+                    title="Thunderbolt Bridge cycle detected - click to view details"
+                  >
+                    <svg
+                      class="w-3.5 h-3.5 text-yellow-400"
+                      fill="none"
+                      viewBox="0 0 24 24"
+                      stroke="currentColor"
+                      stroke-width="2"
+                    >
+                      <path
+                        stroke-linecap="round"
+                        stroke-linejoin="round"
+                        d="M12 9v2m0 4h.01m-6.938 4h13.856c1.54 0 2.502-1.667 1.732-3L13.732 4c-.77-1.333-2.694-1.333-3.464 0L3.34 16c-.77 1.333.192 3 1.732 3z"
+                      />
+                    </svg>
+                    <span class="text-[10px] font-mono text-yellow-200"
+                      >TB CYCLE</span
+                    >
+                  </div>
+                {/if}
               </div>
             </button>
 
@@ -3560,17 +3252,11 @@
   {models}
   {selectedModelId}
   favorites={favoritesSet}
-  {recentModelIds}
-  hasRecents={showRecentsTab}
   existingModelIds={new Set(models.map((m) => m.id))}
   canModelFit={(modelId) => {
     const model = models.find((m) => m.id === modelId);
     return model ? hasEnoughMemory(model) : false;
   }}
-  getModelFitStatus={(modelId): ModelMemoryFitStatus => {
-    const model = models.find((m) => m.id === modelId);
-    return model ? getModelMemoryFitStatus(model) : "too_large";
-  }}
   onSelect={handleModelPickerSelect}
   onClose={() => (isModelPickerOpen = false)}
   onToggleFavorite={toggleFavorite}

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

@@ -3,7 +3,6 @@
   import {
     topologyData,
     downloads,
-    nodeDisk,
     type DownloadProgress,
     refreshState,
     lastUpdate as lastUpdateStore,
@@ -38,13 +37,10 @@
     nodeId: string;
     nodeName: string;
     models: ModelEntry[];
-    diskAvailable?: number;
-    diskTotal?: number;
   };
 
   const data = $derived(topologyData());
   const downloadsData = $derived(downloads());
-  const nodeDiskData = $derived(nodeDisk());
 
   function getNodeLabel(nodeId: string): string {
     const node = data?.nodes?.[nodeId];
@@ -331,17 +327,10 @@
           ];
         }
 
-        // Get disk info for this node
-        const diskInfo = nodeDiskData?.[nodeId];
-        const diskAvailable = diskInfo?.available?.inBytes;
-        const diskTotal = diskInfo?.total?.inBytes;
-
         built.push({
           nodeId,
           nodeName: getNodeLabel(nodeId),
           models,
-          diskAvailable,
-          diskTotal,
         });
       }
 
@@ -428,14 +417,6 @@
                 <div class="text-xs text-exo-light-gray font-mono truncate">
                   {node.nodeId}
                 </div>
-                <div class="text-xs text-exo-light-gray font-mono mt-1">
-                  {formatBytes(
-                    node.models
-                      .filter((m) => m.status === "completed")
-                      .reduce((sum, m) => sum + m.totalBytes, 0),
-                  )} models{#if node.diskAvailable != null}
-                    - {formatBytes(node.diskAvailable)} free{/if}
-                </div>
               </div>
               <div
                 class="text-xs font-mono uppercase tracking-wider whitespace-nowrap shrink-0 text-right"
@@ -448,6 +429,13 @@
                     / {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>
 

e2e/Dockerfile

@@ -1,58 +0,0 @@
-# Stage 1: Build the dashboard
-FROM node:22-slim AS dashboard
-WORKDIR /app/dashboard
-COPY dashboard/package.json dashboard/package-lock.json ./
-RUN npm ci
-COPY dashboard/ .
-RUN npm run build
-
-# Stage 2: Build and run exo
-FROM python:3.13-slim
-
-# Install system dependencies
-# libblas-dev/liblapack-dev/liblapacke-dev are required by MLX CPU backend on Linux
-RUN apt-get update && apt-get install -y \
-    build-essential \
-    pkg-config \
-    libssl-dev \
-    libblas-dev \
-    liblapack-dev \
-    liblapacke-dev \
-    curl \
-    protobuf-compiler \
-    iptables \
-    && rm -rf /var/lib/apt/lists/*
-
-# Install Rust nightly
-RUN curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y --default-toolchain nightly
-ENV PATH="/root/.cargo/bin:${PATH}"
-
-# Wrap g++ with -fpermissive to fix MLX CPU JIT compilation with GCC 14
-# (GCC 14 treats _Float128/_Float32/_Float64 as built-in types, conflicting with MLX-generated code)
-# Must be done BEFORE uv sync so any source builds also get the fix
-RUN mv /usr/bin/g++ /usr/bin/g++.real && \
-    printf '#!/bin/sh\nexec /usr/bin/g++.real -fpermissive "$@"\n' > /usr/bin/g++ && \
-    chmod +x /usr/bin/g++
-
-# Install uv
-COPY --from=ghcr.io/astral-sh/uv:latest /uv /usr/local/bin/uv
-
-WORKDIR /app
-
-# Copy dependency files first for better layer caching
-COPY pyproject.toml Cargo.toml uv.lock README.md ./
-COPY rust/ ./rust/
-COPY bench/pyproject.toml ./bench/pyproject.toml
-
-# Copy source and resources
-COPY src/ ./src/
-COPY resources/ ./resources/
-
-# Copy built dashboard from stage 1
-COPY --from=dashboard /app/dashboard/build ./dashboard/build/
-
-# Install Python deps and build Rust bindings, then clean up build artifacts
-# to keep the layer small (Rust target/ and cargo registry can be 1-2 GB)
-RUN uv sync && rm -rf /app/rust/target /root/.cargo/registry /root/.cargo/git
-
-CMD [".venv/bin/exo", "-v"]

e2e/conftest.py

@@ -1,195 +0,0 @@
-"""Shared E2E test infrastructure for exo cluster tests."""
-
-import asyncio
-import json
-import os
-import sys
-from pathlib import Path
-from urllib.error import URLError
-from urllib.request import Request, urlopen
-
-E2E_DIR = Path(__file__).parent.resolve()
-TIMEOUT = int(os.environ.get("E2E_TIMEOUT", "120"))
-
-
-class Cluster:
-    """Async wrapper around a docker compose exo cluster."""
-
-    def __init__(self, name: str, overrides: list[str] | None = None):
-        self.name = name
-        self.project = f"e2e-{name}"
-        compose_files = [str(E2E_DIR / "docker-compose.yml")]
-        for path in overrides or []:
-            compose_files.append(str(E2E_DIR / path))
-        self._compose_base = [
-            "docker",
-            "compose",
-            "-p",
-            self.project,
-            *[arg for f in compose_files for arg in ("-f", f)],
-        ]
-
-    async def __aenter__(self):
-        return self
-
-    async def __aexit__(self, *exc):
-        await self.stop()
-
-    async def _run(self, *args: str, check: bool = True) -> str:
-        proc = await asyncio.create_subprocess_exec(
-            *self._compose_base,
-            *args,
-            stdout=asyncio.subprocess.PIPE,
-            stderr=asyncio.subprocess.STDOUT,
-        )
-        stdout, _ = await proc.communicate()
-        output = stdout.decode()
-        if check and proc.returncode != 0:
-            print(output, file=sys.stderr)
-            raise RuntimeError(
-                f"docker compose {' '.join(args)} failed (rc={proc.returncode})"
-            )
-        return output
-
-    async def build(self):
-        # Skip build if the image was pre-built (e.g. in CI with buildx cache)
-        proc = await asyncio.create_subprocess_exec(
-            "docker",
-            "image",
-            "inspect",
-            "exo-e2e:latest",
-            stdout=asyncio.subprocess.DEVNULL,
-            stderr=asyncio.subprocess.DEVNULL,
-        )
-        await proc.wait()
-        if proc.returncode == 0:
-            print("  Using pre-built image (exo-e2e:latest)")
-            return
-        print("  Building images...")
-        await self._run("build", "--quiet")
-
-    async def start(self):
-        print("  Starting cluster...")
-        await self._run("up", "-d")
-
-    async def stop(self):
-        print("  Cleaning up...")
-        await self._run("down", "--timeout", "5", check=False)
-
-    async def logs(self) -> str:
-        return await self._run("logs", check=False)
-
-    async def exec(
-        self, service: str, *cmd: str, check: bool = True
-    ) -> tuple[int, str]:
-        """Run a command inside a running container. Returns (returncode, output)."""
-        proc = await asyncio.create_subprocess_exec(
-            *self._compose_base,
-            "exec",
-            "-T",
-            service,
-            *cmd,
-            stdout=asyncio.subprocess.PIPE,
-            stderr=asyncio.subprocess.STDOUT,
-        )
-        stdout, _ = await proc.communicate()
-        output = stdout.decode()
-        if check and proc.returncode != 0:
-            raise RuntimeError(
-                f"exec {' '.join(cmd)} in {service} failed (rc={proc.returncode})"
-            )
-        return proc.returncode, output
-
-    async def wait_for(self, description: str, check_fn, timeout: int = TIMEOUT):
-        """Poll check_fn every 2s until it returns True or timeout expires."""
-        print(f"  Waiting for {description}...")
-        deadline = asyncio.get_event_loop().time() + timeout
-        while asyncio.get_event_loop().time() < deadline:
-            if await check_fn():
-                print(f"  {description}")
-                return
-            await asyncio.sleep(2)
-        output = await self.logs()
-        print(f"--- cluster logs ---\n{output}\n---", file=sys.stderr)
-        raise TimeoutError(f"Timed out waiting for {description}")
-
-    async def assert_healthy(self):
-        """Verify the cluster formed correctly: nodes started, discovered each other, elected a master, API responds."""
-
-        async def both_nodes_started():
-            log = await self.logs()
-            return log.count("Starting node") >= 2
-
-        async def nodes_discovered():
-            log = await self.logs()
-            return log.count("ConnectionMessageType.Connected") >= 2
-
-        async def master_elected():
-            log = await self.logs()
-            return "demoting self" in log
-
-        async def api_responding():
-            try:
-                with urlopen("http://localhost:52415/v1/models", timeout=3) as resp:
-                    return resp.status == 200
-            except (URLError, OSError):
-                return False
-
-        await self.wait_for("Both nodes started", both_nodes_started)
-        await self.wait_for("Nodes discovered each other", nodes_discovered)
-        await self.wait_for("Master election resolved", master_elected)
-        await self.wait_for("API responding", api_responding)
-
-    async def _api(
-        self, method: str, path: str, body: dict | None = None, timeout: int = 30
-    ) -> dict:
-        """Make an API request to the cluster. Returns parsed JSON."""
-        url = f"http://localhost:52415{path}"
-        data = json.dumps(body).encode() if body else None
-        req = Request(
-            url, data=data, headers={"Content-Type": "application/json"}, method=method
-        )
-        loop = asyncio.get_event_loop()
-        resp_bytes = await loop.run_in_executor(
-            None, lambda: urlopen(req, timeout=timeout).read()
-        )
-        return json.loads(resp_bytes)
-
-    async def place_model(self, model: str, timeout: int = 600):
-        """Place a model instance on the cluster (triggers download) and wait until it's ready."""
-        await self._api("POST", "/place_instance", {"model_id": model})
-
-        async def model_ready():
-            try:
-                resp = await self._api("GET", "/v1/models")
-                return any(m.get("id") == model for m in resp.get("data", []))
-            except Exception:
-                return False
-
-        await self.wait_for(f"Model {model} ready", model_ready, timeout=timeout)
-
-    async def chat(
-        self, model: str, messages: list[dict], timeout: int = 600, **kwargs
-    ) -> dict:
-        """Send a chat completion request. Retries until model is downloaded and inference completes."""
-        body = json.dumps({"model": model, "messages": messages, **kwargs}).encode()
-        deadline = asyncio.get_event_loop().time() + timeout
-        last_error = None
-
-        while asyncio.get_event_loop().time() < deadline:
-            try:
-                req = Request(
-                    "http://localhost:52415/v1/chat/completions",
-                    data=body,
-                    headers={"Content-Type": "application/json"},
-                )
-                loop = asyncio.get_event_loop()
-                resp_bytes = await loop.run_in_executor(
-                    None, lambda r=req: urlopen(r, timeout=300).read()
-                )
-                return json.loads(resp_bytes)
-            except Exception as e:
-                last_error = e
-                await asyncio.sleep(5)
-
-        raise TimeoutError(f"Chat request failed after {timeout}s: {last_error}")

e2e/docker-compose.yml

@@ -1,20 +0,0 @@
-services:
-  exo-node-1:
-    image: exo-e2e:latest
-    build:
-      context: ..
-      dockerfile: e2e/Dockerfile
-    environment:
-      - EXO_LIBP2P_NAMESPACE=docker-e2e
-    command: [".venv/bin/exo", "-v"]
-    ports:
-      - "52415:52415"
-
-  exo-node-2:
-    image: exo-e2e:latest
-    build:
-      context: ..
-      dockerfile: e2e/Dockerfile
-    environment:
-      - EXO_LIBP2P_NAMESPACE=docker-e2e
-    command: [".venv/bin/exo", "-v"]

e2e/run_all.py

@@ -1,83 +0,0 @@
-#!/usr/bin/env python3
-"""Discovers and runs all E2E tests in e2e/test_*.py.
-
-Tests with '# slow' on the first line of their docstring are skipped
-unless --slow is passed or E2E_SLOW=1 is set.
-"""
-
-import os
-import subprocess
-import sys
-from pathlib import Path
-
-E2E_DIR = Path(__file__).parent.resolve()
-
-
-def is_slow(test_file: Path) -> bool:
-    """Check if the test file is marked as slow (has '# slow' in first 3 lines)."""
-    with open(test_file) as f:
-        for line in f:
-            if line.strip().startswith("#"):
-                continue
-            if line.strip().startswith('"""') or line.strip().startswith("'''"):
-                # Read into the docstring
-                for doc_line in f:
-                    if "slow" in doc_line.lower() and doc_line.strip().startswith(
-                        "slow"
-                    ):
-                        return True
-                    if '"""' in doc_line or "'''" in doc_line:
-                        break
-            break
-    return False
-
-
-def main():
-    run_slow = "--slow" in sys.argv or os.environ.get("E2E_SLOW") == "1"
-    if "--update-snapshots" in sys.argv:
-        os.environ["UPDATE_SNAPSHOTS"] = "1"
-    test_files = sorted(E2E_DIR.glob("test_*.py"))
-    if not test_files:
-        print("No test files found")
-        sys.exit(1)
-
-    passed = 0
-    failed = 0
-    skipped = 0
-    failures = []
-
-    for test_file in test_files:
-        name = test_file.stem
-        if is_slow(test_file) and not run_slow:
-            print(f"=== {name} === SKIPPED (slow, use --slow to run)")
-            skipped += 1
-            continue
-
-        print(f"=== {name} ===")
-        result = subprocess.run([sys.executable, str(test_file)])
-        if result.returncode == 0:
-            passed += 1
-        else:
-            # Retry once — Docker networking (mDNS) can be slow on first boot
-            print(f"\n=== {name} === RETRYING (attempt 2/2)")
-            result = subprocess.run([sys.executable, str(test_file)])
-            if result.returncode == 0:
-                passed += 1
-            else:
-                failed += 1
-                failures.append(name)
-        print()
-
-    total = passed + failed + skipped
-    print("================================")
-    print(
-        f"{passed}/{total} tests passed" + (f", {skipped} skipped" if skipped else "")
-    )
-
-    if failed:
-        print(f"Failed: {' '.join(failures)}")
-        sys.exit(1)
-
-
-if __name__ == "__main__":
-    main()

e2e/snapshot.py

@@ -1,78 +0,0 @@
-"""Snapshot testing infrastructure for E2E tests.
-
-Provides deterministic regression testing by comparing inference output
-against committed baseline snapshots. Tests FAIL if no baseline exists —
-baselines must be explicitly generated and committed.
-
-Generate baselines: UPDATE_SNAPSHOTS=1 python3 e2e/run_all.py --slow
-Update after intentional changes: UPDATE_SNAPSHOTS=1 python3 e2e/run_all.py --slow
-
-Snapshots are stored per-architecture (e.g. snapshots/x86_64/, snapshots/arm64/)
-since floating-point results differ between CPU architectures.
-"""
-
-import difflib
-import json
-import os
-import platform
-from pathlib import Path
-
-ARCH = platform.machine()
-SNAPSHOTS_DIR = Path(__file__).parent / "snapshots" / ARCH
-
-
-def assert_snapshot(
-    name: str,
-    content: str,
-    metadata: dict,
-) -> None:
-    """Compare content against a saved snapshot, or create one if missing.
-
-    Args:
-        name: Snapshot identifier (used as filename: snapshots/{arch}/{name}.json).
-        content: The actual inference output to compare.
-        metadata: Additional context stored alongside content (model, seed, etc.).
-                  Not used for comparison -- purely documentary.
-
-    Raises:
-        AssertionError: If content doesn't match the saved snapshot.
-
-    Environment:
-        UPDATE_SNAPSHOTS=1: Overwrite existing snapshot with actual content.
-    """
-    snapshot_file = SNAPSHOTS_DIR / f"{name}.json"
-    update = os.environ.get("UPDATE_SNAPSHOTS") == "1"
-
-    if update:
-        # Explicitly regenerate snapshot
-        SNAPSHOTS_DIR.mkdir(parents=True, exist_ok=True)
-        snapshot_data = {**metadata, "arch": ARCH, "content": content}
-        snapshot_file.write_text(json.dumps(snapshot_data, indent=2) + "\n")
-        print(f"  Updated snapshot: {ARCH}/{snapshot_file.name}")
-    elif not snapshot_file.exists():
-        raise AssertionError(
-            f"No baseline snapshot for '{name}' on {ARCH}.\n"
-            f"Expected file: {snapshot_file}\n\n"
-            f"Generate baselines with: UPDATE_SNAPSHOTS=1 python3 e2e/run_all.py --slow"
-        )
-    else:
-        snapshot = json.loads(snapshot_file.read_text())
-        expected = snapshot["content"]
-        if content != expected:
-            diff = "\n".join(
-                difflib.unified_diff(
-                    expected.splitlines(),
-                    content.splitlines(),
-                    fromfile=f"expected ({snapshot_file.relative_to(SNAPSHOTS_DIR.parent.parent)})",
-                    tofile="actual",
-                    lineterm="",
-                )
-            )
-            raise AssertionError(
-                f"Snapshot mismatch for '{name}' on {ARCH}!\n\n"
-                f"{diff}\n\n"
-                f"Expected: {expected!r}\n"
-                f"Actual:   {content!r}\n\n"
-                f"To update: UPDATE_SNAPSHOTS=1 python3 e2e/run_all.py --slow"
-            )
-        print(f"  Output matches snapshot ({ARCH}/{snapshot_file.name})")

e2e/test_cluster_formation.py

@@ -1,22 +0,0 @@
-"""Test: Basic cluster formation.
-
-Verifies two nodes discover each other, elect a master, and the API responds.
-"""
-
-import asyncio
-import sys
-
-sys.path.insert(0, str(__import__("pathlib").Path(__file__).parent))
-from conftest import Cluster
-
-
-async def main():
-    async with Cluster("cluster_formation") as cluster:
-        await cluster.build()
-        await cluster.start()
-        await cluster.assert_healthy()
-        print("PASSED: cluster_formation")
-
-
-if __name__ == "__main__":
-    asyncio.run(main())

e2e/test_inference_snapshot.py

@@ -1,61 +0,0 @@
-"""Test: Deterministic inference output (snapshot test).
-
-Sends a chat completion request with a fixed seed,
-then verifies the output matches a known-good snapshot. This ensures
-inference produces consistent results across runs.
-
-Uses MLX CPU backend in Docker on x86 Linux.
-"""
-
-import asyncio
-import sys
-from pathlib import Path
-
-sys.path.insert(0, str(Path(__file__).parent))
-from snapshot import assert_snapshot
-
-from conftest import Cluster
-
-MODEL = "mlx-community/Qwen3-0.6B-4bit"
-SEED = 42
-PROMPT = "What is 2+2? Reply with just the number."
-MAX_TOKENS = 32
-
-
-async def main():
-    async with Cluster("inference_snapshot") as cluster:
-        await cluster.build()
-        await cluster.start()
-        await cluster.assert_healthy()
-
-        print(f"  Launching model {MODEL}...")
-        await cluster.place_model(MODEL)
-
-        print(f"  Sending chat completion (seed={SEED})...")
-        resp = await cluster.chat(
-            model=MODEL,
-            messages=[{"role": "user", "content": PROMPT}],
-            seed=SEED,
-            temperature=0,
-            max_tokens=MAX_TOKENS,
-        )
-
-        content = resp["choices"][0]["message"]["content"]
-        print(f"  Response: {content!r}")
-
-        assert_snapshot(
-            name="inference_snapshot",
-            content=content,
-            metadata={
-                "model": MODEL,
-                "seed": SEED,
-                "prompt": PROMPT,
-                "max_tokens": MAX_TOKENS,
-            },
-        )
-
-        print("PASSED: inference_snapshot")
-
-
-if __name__ == "__main__":
-    asyncio.run(main())

e2e/test_no_internet.py

@@ -1,47 +0,0 @@
-"""Test: Cluster works without internet access.
-
-Verifies exo functions correctly when containers can talk to each other
-but cannot reach the internet. Uses iptables to block all outbound traffic
-except private subnets and multicast (for mDNS discovery).
-"""
-
-import asyncio
-import sys
-
-sys.path.insert(0, str(__import__("pathlib").Path(__file__).parent))
-from conftest import Cluster
-
-
-async def main():
-    async with Cluster(
-        "no_internet",
-        overrides=["tests/no_internet/docker-compose.override.yml"],
-    ) as cluster:
-        await cluster.build()
-        await cluster.start()
-        await cluster.assert_healthy()
-
-        # Verify internet is actually blocked from inside the containers
-        for node in ["exo-node-1", "exo-node-2"]:
-            rc, _ = await cluster.exec(
-                node,
-                "curl",
-                "-sf",
-                "--max-time",
-                "3",
-                "https://huggingface.co",
-                check=False,
-            )
-            assert rc != 0, f"{node} should not be able to reach the internet"
-            print(f"  {node}: internet correctly blocked")
-
-        # Verify exo detected no internet connectivity
-        log = await cluster.logs()
-        assert "Internet connectivity: False" in log, "exo should detect no internet"
-        print("  exo correctly detected no internet connectivity")
-
-        print("PASSED: no_internet")
-
-
-if __name__ == "__main__":
-    asyncio.run(main())

e2e/test_runner_chaos.py

@@ -1,65 +0,0 @@
-"""Test: Runner chaos — abrupt runner death detection.
-slow
-
-Sends a chat completion with the EXO_RUNNER_MUST_DIE trigger, which causes
-the runner process to call os._exit(1) (simulating an OOM kill). Verifies that
-the RunnerSupervisor health check detects the death and the system doesn't hang.
-
-Requires a machine that can run MLX inference at reasonable speed (Apple Silicon).
-Run with: python3 e2e/run_all.py --slow  or  E2E_SLOW=1 python3 e2e/run_all.py
-"""
-
-import asyncio
-import contextlib
-import sys
-from pathlib import Path
-
-sys.path.insert(0, str(Path(__file__).parent))
-from conftest import Cluster
-
-MODEL = "mlx-community/Qwen3-0.6B-4bit"
-
-
-async def main():
-    async with Cluster("runner_chaos") as cluster:
-        await cluster.build()
-        await cluster.start()
-        await cluster.assert_healthy()
-
-        # Place the model so a runner is loaded and ready
-        print(f"  Launching model {MODEL}...")
-        await cluster.place_model(MODEL)
-
-        # Send a chat request with the die trigger.
-        # The runner will call os._exit(1) mid-inference, simulating OOM kill.
-        # The chat request itself will fail — that's expected.
-        print("  Sending EXO_RUNNER_MUST_DIE trigger...")
-        with contextlib.suppress(Exception):
-            await cluster.chat(
-                model=MODEL,
-                messages=[{"role": "user", "content": "EXO RUNNER MUST DIE"}],
-                timeout=60,
-            )
-
-        # Wait for the health check to detect the death and emit RunnerFailed
-        async def health_check_detected():
-            log = await cluster.logs()
-            return "runner process died unexpectedly" in log
-
-        await cluster.wait_for(
-            "Health check detected runner death",
-            health_check_detected,
-            timeout=30,
-        )
-
-        # Verify RunnerFailed was emitted (visible in logs)
-        log = await cluster.logs()
-        assert "runner process died unexpectedly" in log, (
-            f"Expected health check to detect runner death but it didn't.\nLogs:\n{log}"
-        )
-
-        print("PASSED: runner_chaos")
-
-
-if __name__ == "__main__":
-    asyncio.run(main())

e2e/test_snapshot_code_gen.py

@@ -1,60 +0,0 @@
-"""Test: Code generation snapshot.
-slow
-
-Verifies deterministic output for a code generation prompt.
-"""
-
-import asyncio
-import sys
-from pathlib import Path
-
-sys.path.insert(0, str(Path(__file__).parent))
-from snapshot import assert_snapshot
-
-from conftest import Cluster
-
-MODEL = "mlx-community/Qwen3-0.6B-4bit"
-SEED = 42
-PROMPT = (
-    "Write a Python function to reverse a string. Only output the code, no explanation."
-)
-MAX_TOKENS = 64
-
-
-async def main():
-    async with Cluster("snapshot_code_gen") as cluster:
-        await cluster.build()
-        await cluster.start()
-        await cluster.assert_healthy()
-
-        print(f"  Launching model {MODEL}...")
-        await cluster.place_model(MODEL)
-
-        print(f"  Sending chat completion (seed={SEED})...")
-        resp = await cluster.chat(
-            model=MODEL,
-            messages=[{"role": "user", "content": PROMPT}],
-            seed=SEED,
-            temperature=0,
-            max_tokens=MAX_TOKENS,
-        )
-
-        content = resp["choices"][0]["message"]["content"]
-        print(f"  Response: {content!r}")
-
-        assert_snapshot(
-            name="snapshot_code_gen",
-            content=content,
-            metadata={
-                "model": MODEL,
-                "seed": SEED,
-                "prompt": PROMPT,
-                "max_tokens": MAX_TOKENS,
-            },
-        )
-
-        print("PASSED: snapshot_code_gen")
-
-
-if __name__ == "__main__":
-    asyncio.run(main())

e2e/test_snapshot_edge.py

@@ -1,65 +0,0 @@
-"""Test: Edge case snapshots.
-slow
-
-Verifies deterministic output for edge-case prompts: single word input,
-special characters, and unicode.
-"""
-
-import asyncio
-import sys
-from pathlib import Path
-
-sys.path.insert(0, str(Path(__file__).parent))
-from snapshot import assert_snapshot
-
-from conftest import Cluster
-
-MODEL = "mlx-community/Qwen3-0.6B-4bit"
-SEED = 42
-MAX_TOKENS = 32
-
-CASES = [
-    ("edge_single_word", "Hi"),
-    ("edge_special_chars", "What does 2 * (3 + 4) / 7 - 1 equal? Use <math> tags."),
-    ("edge_unicode", "Translate 'hello' to Japanese, Chinese, and Korean."),
-]
-
-
-async def main():
-    async with Cluster("snapshot_edge") as cluster:
-        await cluster.build()
-        await cluster.start()
-        await cluster.assert_healthy()
-
-        print(f"  Launching model {MODEL}...")
-        await cluster.place_model(MODEL)
-
-        for snapshot_name, prompt in CASES:
-            print(f"  [{snapshot_name}] Sending: {prompt!r}")
-            resp = await cluster.chat(
-                model=MODEL,
-                messages=[{"role": "user", "content": prompt}],
-                seed=SEED,
-                temperature=0,
-                max_tokens=MAX_TOKENS,
-            )
-
-            content = resp["choices"][0]["message"]["content"]
-            print(f"  [{snapshot_name}] Response: {content!r}")
-
-            assert_snapshot(
-                name=snapshot_name,
-                content=content,
-                metadata={
-                    "model": MODEL,
-                    "seed": SEED,
-                    "prompt": prompt,
-                    "max_tokens": MAX_TOKENS,
-                },
-            )
-
-        print("PASSED: snapshot_edge")
-
-
-if __name__ == "__main__":
-    asyncio.run(main())

e2e/test_snapshot_long_output.py

@@ -1,58 +0,0 @@
-"""Test: Longer output snapshot.
-slow
-
-Verifies deterministic output with a higher max_tokens (128).
-"""
-
-import asyncio
-import sys
-from pathlib import Path
-
-sys.path.insert(0, str(Path(__file__).parent))
-from snapshot import assert_snapshot
-
-from conftest import Cluster
-
-MODEL = "mlx-community/Qwen3-0.6B-4bit"
-SEED = 42
-PROMPT = "Explain how a binary search algorithm works."
-MAX_TOKENS = 128
-
-
-async def main():
-    async with Cluster("snapshot_long_output") as cluster:
-        await cluster.build()
-        await cluster.start()
-        await cluster.assert_healthy()
-
-        print(f"  Launching model {MODEL}...")
-        await cluster.place_model(MODEL)
-
-        print(f"  Sending chat completion (seed={SEED}, max_tokens={MAX_TOKENS})...")
-        resp = await cluster.chat(
-            model=MODEL,
-            messages=[{"role": "user", "content": PROMPT}],
-            seed=SEED,
-            temperature=0,
-            max_tokens=MAX_TOKENS,
-        )
-
-        content = resp["choices"][0]["message"]["content"]
-        print(f"  Response: {content!r}")
-
-        assert_snapshot(
-            name="snapshot_long_output",
-            content=content,
-            metadata={
-                "model": MODEL,
-                "seed": SEED,
-                "prompt": PROMPT,
-                "max_tokens": MAX_TOKENS,
-            },
-        )
-
-        print("PASSED: snapshot_long_output")
-
-
-if __name__ == "__main__":
-    asyncio.run(main())

e2e/test_snapshot_multi_model.py

@@ -1,73 +0,0 @@
-"""Test: Multi-model snapshot tests.
-slow
-
-Verifies deterministic output across different model architectures to catch
-model-specific regressions. Each model uses its own snapshot file.
-Run with: python3 e2e/run_all.py --slow  or  E2E_SLOW=1 python3 e2e/run_all.py
-"""
-
-import asyncio
-import sys
-from pathlib import Path
-
-sys.path.insert(0, str(Path(__file__).parent))
-from snapshot import assert_snapshot
-
-from conftest import Cluster
-
-SEED = 42
-PROMPT = "What is the capital of France?"
-MAX_TOKENS = 32
-
-MODELS = [
-    "mlx-community/SmolLM2-135M-Instruct",
-    "mlx-community/Llama-3.2-1B-Instruct-4bit",
-    "mlx-community/gemma-2-2b-it-4bit",
-]
-
-
-async def main():
-    async with Cluster("snapshot_multi_model") as cluster:
-        await cluster.build()
-        await cluster.start()
-        await cluster.assert_healthy()
-
-        for model in MODELS:
-            short_name = (
-                model.split("/")[-1].lower().replace("-", "_").replace(".", "_")
-            )
-            snapshot_name = f"snapshot_multi_{short_name}"
-
-            print(f"  Launching model {model}...")
-            await cluster.place_model(model)
-
-            print(f"  Sending chat completion (seed={SEED})...")
-            resp = await cluster.chat(
-                model=model,
-                messages=[{"role": "user", "content": PROMPT}],
-                seed=SEED,
-                temperature=0,
-                max_tokens=MAX_TOKENS,
-            )
-
-            content = resp["choices"][0]["message"]["content"]
-            print(f"  [{short_name}] Response: {content!r}")
-
-            assert_snapshot(
-                name=snapshot_name,
-                content=content,
-                metadata={
-                    "model": model,
-                    "seed": SEED,
-                    "prompt": PROMPT,
-                    "max_tokens": MAX_TOKENS,
-                },
-            )
-
-            print(f"  [{short_name}] PASSED")
-
-        print("PASSED: snapshot_multi_model")
-
-
-if __name__ == "__main__":
-    asyncio.run(main())

e2e/test_snapshot_reasoning.py

@@ -1,58 +0,0 @@
-"""Test: Reasoning/math snapshot.
-slow
-
-Verifies deterministic output for a simple reasoning prompt.
-"""
-
-import asyncio
-import sys
-from pathlib import Path
-
-sys.path.insert(0, str(Path(__file__).parent))
-from snapshot import assert_snapshot
-
-from conftest import Cluster
-
-MODEL = "mlx-community/Qwen3-0.6B-4bit"
-SEED = 42
-PROMPT = "If I have 3 apples and give away 1, how many do I have? Think step by step."
-MAX_TOKENS = 64
-
-
-async def main():
-    async with Cluster("snapshot_reasoning") as cluster:
-        await cluster.build()
-        await cluster.start()
-        await cluster.assert_healthy()
-
-        print(f"  Launching model {MODEL}...")
-        await cluster.place_model(MODEL)
-
-        print(f"  Sending chat completion (seed={SEED})...")
-        resp = await cluster.chat(
-            model=MODEL,
-            messages=[{"role": "user", "content": PROMPT}],
-            seed=SEED,
-            temperature=0,
-            max_tokens=MAX_TOKENS,
-        )
-
-        content = resp["choices"][0]["message"]["content"]
-        print(f"  Response: {content!r}")
-
-        assert_snapshot(
-            name="snapshot_reasoning",
-            content=content,
-            metadata={
-                "model": MODEL,
-                "seed": SEED,
-                "prompt": PROMPT,
-                "max_tokens": MAX_TOKENS,
-            },
-        )
-
-        print("PASSED: snapshot_reasoning")
-
-
-if __name__ == "__main__":
-    asyncio.run(main())

e2e/tests/no_internet/docker-compose.override.yml

@@ -1,32 +0,0 @@
-# Block all outbound internet traffic using iptables while preserving:
-#   - Multicast (224.0.0.0/4) for mDNS peer discovery
-#   - Private subnets (10/8, 172.16/12, 192.168/16) for inter-container communication
-#   - Loopback (127/8)
-# Requires NET_ADMIN capability for iptables.
-services:
-  exo-node-1:
-    cap_add:
-      - NET_ADMIN
-    entrypoint: ["/bin/sh", "-c"]
-    command:
-      - |
-        iptables -A OUTPUT -d 127.0.0.0/8 -j ACCEPT
-        iptables -A OUTPUT -d 10.0.0.0/8 -j ACCEPT
-        iptables -A OUTPUT -d 172.16.0.0/12 -j ACCEPT
-        iptables -A OUTPUT -d 192.168.0.0/16 -j ACCEPT
-        iptables -A OUTPUT -d 224.0.0.0/4 -j ACCEPT
-        iptables -A OUTPUT -j REJECT
-        exec .venv/bin/exo -v
-  exo-node-2:
-    cap_add:
-      - NET_ADMIN
-    entrypoint: ["/bin/sh", "-c"]
-    command:
-      - |
-        iptables -A OUTPUT -d 127.0.0.0/8 -j ACCEPT
-        iptables -A OUTPUT -d 10.0.0.0/8 -j ACCEPT
-        iptables -A OUTPUT -d 172.16.0.0/12 -j ACCEPT
-        iptables -A OUTPUT -d 192.168.0.0/16 -j ACCEPT
-        iptables -A OUTPUT -d 224.0.0.0/4 -j ACCEPT
-        iptables -A OUTPUT -j REJECT
-        exec .venv/bin/exo -v

flake.nix

@@ -83,9 +83,6 @@
           _module.args.pkgs = import inputs.nixpkgs {
             inherit system;
             config.allowUnfreePredicate = pkg: (pkg.pname or "") == "metal-toolchain";
-            overlays = [
-              (import ./nix/apple-sdk-overlay.nix)
-            ];
           };
           treefmt = {
             projectRootFile = "flake.nix";

nix/apple-sdk-overlay.nix

@@ -1,18 +0,0 @@
-# Overlay that builds apple-sdk with a custom versions.json (for SDK 26.2).
-# The upstream nixpkgs package reads versions.json at eval time via a relative
-# path, so we can't override it through callPackage args. Instead, we copy
-# the upstream source and patch the one file.
-final: _prev:
-let
-  upstreamSrc = final.path + "/pkgs/by-name/ap/apple-sdk";
-  patchedSrc = final.runCommandLocal "apple-sdk-src-patched" { } ''
-    cp -r ${upstreamSrc} $out
-    chmod -R u+w $out
-    cp ${./apple-sdk/metadata/versions.json} $out/metadata/versions.json
-  '';
-in
-{
-  apple-sdk_26 = final.callPackage (patchedSrc + "/package.nix") {
-    darwinSdkMajorVersion = "26";
-  };
-}

nix/apple-sdk/metadata/versions.json

@@ -1,26 +0,0 @@
-{
-  "14": {
-    "urls": [
-      "https://swcdn.apple.com/content/downloads/14/48/052-59890-A_I0F5YGAY0Y/p9n40hio7892gou31o1v031ng6fnm9sb3c/CLTools_macOSNMOS_SDK.pkg",
-      "https://web.archive.org/web/20250211001355/https://swcdn.apple.com/content/downloads/14/48/052-59890-A_I0F5YGAY0Y/p9n40hio7892gou31o1v031ng6fnm9sb3c/CLTools_macOSNMOS_SDK.pkg"
-    ],
-    "version": "14.4",
-    "hash": "sha256-QozDiwY0Czc0g45vPD7G4v4Ra+3DujCJbSads3fJjjM="
-  },
-  "15": {
-    "urls": [
-      "https://swcdn.apple.com/content/downloads/52/01/082-41241-A_0747ZN8FHV/dectd075r63pppkkzsb75qk61s0lfee22j/CLTools_macOSNMOS_SDK.pkg",
-      "https://web.archive.org/web/20250530132510/https://swcdn.apple.com/content/downloads/52/01/082-41241-A_0747ZN8FHV/dectd075r63pppkkzsb75qk61s0lfee22j/CLTools_macOSNMOS_SDK.pkg"
-    ],
-    "version": "15.5",
-    "hash": "sha256-HBiSJuw1XBUK5R/8Sj65c3rftSEvQl/O9ZZVp/g1Amo="
-  },
-  "26": {
-    "urls": [
-      "https://swcdn.apple.com/content/downloads/60/22/089-71960-A_W8BL1RUJJ6/5zkyplomhk1cm7z6xja2ktgapnhhti6wwd/CLTools_macOSNMOS_SDK.pkg",
-      "https://web.archive.org/web/20250915230423/https://swcdn.apple.com/content/downloads/60/22/089-71960-A_W8BL1RUJJ6/5zkyplomhk1cm7z6xja2ktgapnhhti6wwd/CLTools_macOSNMOS_SDK.pkg"
-    ],
-    "version": "26.2",
-    "hash": "sha256-hXRlMieVv0smna5uiWRwq87IWOaPWtAjAldbi+wQXcw="
-  }
-}

nix/mlx.nix

@@ -41,7 +41,7 @@ let
 
   mlx = stdenv.mkDerivation rec {
     pname = "mlx";
-    version = let v = "0.30.6"; in
+    version = let v = "0.30.5"; in
       assert v == uvLockMlxVersion || throw "MLX version mismatch: nix/mlx.nix has ${v} but uv.lock has ${uvLockMlxVersion}. Update both the version and hash in nix/mlx.nix.";
       v;
     pyproject = true;
@@ -50,7 +50,7 @@ let
       owner = "ml-explore";
       repo = "mlx";
       tag = "v${version}";
-      hash = "sha256-avD5EGhwgmPdXLAyQSqTO6AXk/W3ziH+f6AetjK3Sdo=";
+      hash = "sha256-OJk6jPlbaSlsUdk3ADz3tWcRzTWXRof3/q8Soe1AO6w=";
     };
 
     patches = [
@@ -85,7 +85,6 @@ let
         (lib.cmakeOptionType "filepath" "FETCHCONTENT_SOURCE_DIR_JSON" "${nlohmann_json.src}")
         (lib.cmakeOptionType "filepath" "FETCHCONTENT_SOURCE_DIR_NANOBIND" "${nanobind}")
         (lib.cmakeBool "FETCHCONTENT_FULLY_DISCONNECTED" true)
-        (lib.cmakeBool "MLX_BUILD_CPU" true)
         (lib.cmakeBool "MLX_BUILD_METAL" true)
         (lib.cmakeOptionType "filepath" "FETCHCONTENT_SOURCE_DIR_METAL_CPP" "${metal_cpp}")
         (lib.cmakeOptionType "string" "CMAKE_OSX_DEPLOYMENT_TARGET" "${apple-sdk_26.version}")

pyproject.toml

@@ -17,8 +17,8 @@ dependencies = [
     "loguru>=0.7.3",
     "exo_pyo3_bindings", # rust bindings
     "anyio==4.11.0",
-    "mlx==0.30.6; sys_platform == 'darwin'",
-    "mlx[cpu]==0.30.6; sys_platform == 'linux'",
+    "mlx==0.30.5; sys_platform == 'darwin'",
+    "mlx[cpu]==0.30.5; sys_platform == 'linux'",
     "mlx-lm==0.30.6",
     "tiktoken>=0.12.0", # required for kimi k2 tokenizer
     "hypercorn>=0.18.0",
@@ -28,8 +28,6 @@ dependencies = [
     "pillow>=11.0,<12.0", # compatibility with mflux
     "mflux==0.15.5",
     "python-multipart>=0.0.21",
-    "msgspec>=0.19.0",
-    "zstandard>=0.23.0",
 ]
 
 [project.scripts]
@@ -59,7 +57,6 @@ dev = [
 [tool.uv.workspace]
 members = [
     "rust/exo_pyo3_bindings",
-    "bench",
 ]
 
 [tool.uv.sources]

python/parts.nix

@@ -14,9 +14,7 @@
 
       # Override overlay to inject Nix-built components
       exoOverlay = final: prev: {
-        # Replace workspace exo_pyo3_bindings with Nix-built wheel.
-        # Preserve passthru so mkVirtualEnv can resolve dependency groups.
-        # Copy .pyi stub + py.typed marker so basedpyright can find the types.
+        # Replace workspace exo_pyo3_bindings with Nix-built wheel
         exo-pyo3-bindings = pkgs.stdenv.mkDerivation {
           pname = "exo-pyo3-bindings";
           version = "0.1.0";
@@ -24,12 +22,6 @@
           # Install from pre-built wheel
           nativeBuildInputs = [ final.pyprojectWheelHook ];
           dontStrip = true;
-          passthru = prev.exo-pyo3-bindings.passthru or { };
-          postInstall = ''
-            local siteDir=$out/${final.python.sitePackages}/exo_pyo3_bindings
-            cp ${inputs.self}/rust/exo_pyo3_bindings/exo_pyo3_bindings.pyi $siteDir/
-            touch $siteDir/py.typed
-          '';
         };
       };
 
@@ -37,32 +29,17 @@
 
       # Overlay to provide build systems and custom packages
       buildSystemsOverlay = final: prev: {
+        # Use our pure Nix-built MLX with Metal support
+        mlx = self'.packages.mlx;
+
         # mlx-lm is a git dependency that needs setuptools
         mlx-lm = prev.mlx-lm.overrideAttrs (old: {
           nativeBuildInputs = (old.nativeBuildInputs or [ ]) ++ [
             final.setuptools
           ];
         });
-      } // lib.optionalAttrs pkgs.stdenv.hostPlatform.isDarwin {
-        # Use our pure Nix-built MLX with Metal support (macOS only)
-        mlx = self'.packages.mlx;
       };
 
-      # Additional overlay for Linux-specific fixes (type checking env).
-      # Native wheels have shared lib dependencies we don't need at type-check time.
-      linuxOverlay = final: prev:
-        let
-          ignoreMissing = drv: drv.overrideAttrs { autoPatchelfIgnoreMissingDeps = [ "*" ]; };
-          nvidiaPackages = lib.filterAttrs (name: _: lib.hasPrefix "nvidia-" name) prev;
-        in
-        lib.optionalAttrs pkgs.stdenv.hostPlatform.isLinux (
-          (lib.mapAttrs (_: ignoreMissing) nvidiaPackages) // {
-            mlx = ignoreMissing prev.mlx;
-            torch = ignoreMissing prev.torch;
-            triton = ignoreMissing prev.triton;
-          }
-        );
-
       pythonSet = (pkgs.callPackage inputs.pyproject-nix.build.packages {
         inherit python;
       }).overrideScope (
@@ -71,7 +48,6 @@
           overlay
           exoOverlay
           buildSystemsOverlay
-          linuxOverlay
         ]
       );
       exoVenv = pythonSet.mkVirtualEnv "exo-env" workspace.deps.default;
@@ -93,16 +69,6 @@
         text = ''exec python ${path} "$@"'';
       };
 
-      benchVenv = pythonSet.mkVirtualEnv "exo-bench-env" {
-        exo-bench = [ ];
-      };
-
-      mkBenchScript = name: path: pkgs.writeShellApplication {
-        inherit name;
-        runtimeInputs = [ benchVenv ];
-        text = ''exec python ${path} "$@"'';
-      };
-
       mkSimplePythonScript = name: path: pkgs.writeShellApplication {
         inherit name;
         runtimeInputs = [ pkgs.python313 ];
@@ -130,8 +96,8 @@
           exo = exoPackage;
           # Test environment for running pytest outside of Nix sandbox (needs GPU access)
           exo-test-env = testVenv;
+          exo-bench = mkPythonScript "exo-bench" (inputs.self + /bench/exo_bench.py);
         } // {
-        exo-bench = mkBenchScript "exo-bench" (inputs.self + /bench/exo_bench.py);
         exo-get-all-models-on-cluster = mkSimplePythonScript "exo-get-all-models-on-cluster" (inputs.self + /tests/get_all_models_on_cluster.py);
       };
 
@@ -142,21 +108,6 @@
           ${pkgs.ruff}/bin/ruff check ${inputs.self}
           touch $out
         '';
-
-        # Hermetic basedpyright type checking
-        typecheck = pkgs.runCommand "typecheck"
-          {
-            nativeBuildInputs = [
-              testVenv
-              pkgs.basedpyright
-            ];
-          }
-          ''
-            cd ${inputs.self}
-            export HOME=$TMPDIR
-            basedpyright --pythonpath ${testVenv}/bin/python
-            touch $out
-          '';
       };
     };
 }

resources/image_model_cards/exolabs--FLUX.1-Kontext-dev-4bit.toml

@@ -3,10 +3,6 @@ n_layers = 57
 hidden_size = 1
 supports_tensor = false
 tasks = ["ImageToImage"]
-family = "flux"
-quantization = "4bit"
-base_model = "FLUX.1 Kontext"
-capabilities = ["image_edit"]
 
 [storage_size]
 in_bytes = 15475325472

resources/image_model_cards/exolabs--FLUX.1-Kontext-dev-8bit.toml

@@ -3,10 +3,6 @@ n_layers = 57
 hidden_size = 1
 supports_tensor = false
 tasks = ["ImageToImage"]
-family = "flux"
-quantization = "8bit"
-base_model = "FLUX.1 Kontext"
-capabilities = ["image_edit"]
 
 [storage_size]
 in_bytes = 21426029632

resources/image_model_cards/exolabs--FLUX.1-Kontext-dev.toml

@@ -3,10 +3,6 @@ n_layers = 57
 hidden_size = 1
 supports_tensor = false
 tasks = ["ImageToImage"]
-family = "flux"
-quantization = ""
-base_model = "FLUX.1 Kontext"
-capabilities = ["image_edit"]
 
 [storage_size]
 in_bytes = 33327437952

resources/image_model_cards/exolabs--FLUX.1-Krea-dev-4bit.toml

@@ -3,10 +3,6 @@ n_layers = 57
 hidden_size = 1
 supports_tensor = false
 tasks = ["TextToImage"]
-family = "flux"
-quantization = "4bit"
-base_model = "FLUX.1 Krea"
-capabilities = ["image_gen"]
 
 [storage_size]
 in_bytes = 15475325472

resources/image_model_cards/exolabs--FLUX.1-Krea-dev-8bit.toml

@@ -3,10 +3,6 @@ n_layers = 57
 hidden_size = 1
 supports_tensor = false
 tasks = ["TextToImage"]
-family = "flux"
-quantization = "8bit"
-base_model = "FLUX.1 Krea"
-capabilities = ["image_gen"]
 
 [storage_size]
 in_bytes = 21426029632

resources/image_model_cards/exolabs--FLUX.1-Krea-dev.toml

@@ -3,10 +3,6 @@ n_layers = 57
 hidden_size = 1
 supports_tensor = false
 tasks = ["TextToImage"]
-family = "flux"
-quantization = ""
-base_model = "FLUX.1 Krea"
-capabilities = ["image_gen"]
 
 [storage_size]
 in_bytes = 33327437952

resources/image_model_cards/exolabs--FLUX.1-dev-4bit.toml

@@ -3,10 +3,6 @@ n_layers = 57
 hidden_size = 1
 supports_tensor = false
 tasks = ["TextToImage"]
-family = "flux"
-quantization = "4bit"
-base_model = "FLUX.1 Dev"
-capabilities = ["image_gen"]
 
 [storage_size]
 in_bytes = 15475325472

resources/image_model_cards/exolabs--FLUX.1-dev-8bit.toml

@@ -3,10 +3,6 @@ n_layers = 57
 hidden_size = 1
 supports_tensor = false
 tasks = ["TextToImage"]
-family = "flux"
-quantization = "8bit"
-base_model = "FLUX.1 Dev"
-capabilities = ["image_gen"]
 
 [storage_size]
 in_bytes = 21426029632

resources/image_model_cards/exolabs--FLUX.1-dev.toml

@@ -3,10 +3,6 @@ n_layers = 57
 hidden_size = 1
 supports_tensor = false
 tasks = ["TextToImage"]
-family = "flux"
-quantization = ""
-base_model = "FLUX.1 Dev"
-capabilities = ["image_gen"]
 
 [storage_size]
 in_bytes = 33327437952

resources/image_model_cards/exolabs--FLUX.1-schnell-4bit.toml

@@ -3,10 +3,6 @@ n_layers = 57
 hidden_size = 1
 supports_tensor = false
 tasks = ["TextToImage"]
-family = "flux"
-quantization = "4bit"
-base_model = "FLUX.1 Schnell"
-capabilities = ["image_gen"]
 
 [storage_size]
 in_bytes = 15470210592

resources/image_model_cards/exolabs--FLUX.1-schnell-8bit.toml

@@ -3,10 +3,6 @@ n_layers = 57
 hidden_size = 1
 supports_tensor = false
 tasks = ["TextToImage"]
-family = "flux"
-quantization = "8bit"
-base_model = "FLUX.1 Schnell"
-capabilities = ["image_gen"]
 
 [storage_size]
 in_bytes = 21415799872

resources/image_model_cards/exolabs--FLUX.1-schnell.toml

@@ -3,10 +3,6 @@ n_layers = 57
 hidden_size = 1
 supports_tensor = false
 tasks = ["TextToImage"]
-family = "flux"
-quantization = ""
-base_model = "FLUX.1 Schnell"
-capabilities = ["image_gen"]
 
 [storage_size]
 in_bytes = 33306978432

resources/image_model_cards/exolabs--Qwen-Image-4bit.toml

@@ -4,10 +4,6 @@ hidden_size = 1
 supports_tensor = false
 tasks = ["TextToImage"]
 uses_cfg = true
-family = "qwen-image"
-quantization = "4bit"
-base_model = "Qwen Image"
-capabilities = ["image_gen"]
 
 [storage_size]
 in_bytes = 26799533856

resources/image_model_cards/exolabs--Qwen-Image-8bit.toml

@@ -4,10 +4,6 @@ hidden_size = 1
 supports_tensor = false
 tasks = ["TextToImage"]
 uses_cfg = true
-family = "qwen-image"
-quantization = "8bit"
-base_model = "Qwen Image"
-capabilities = ["image_gen"]
 
 [storage_size]
 in_bytes = 37014734400

resources/image_model_cards/exolabs--Qwen-Image-Edit-2509-4bit.toml

@@ -4,10 +4,6 @@ hidden_size = 1
 supports_tensor = false
 tasks = ["ImageToImage"]
 uses_cfg = true
-family = "qwen-image"
-quantization = "4bit"
-base_model = "Qwen Image Edit"
-capabilities = ["image_edit"]
 
 [storage_size]
 in_bytes = 26799533856

resources/image_model_cards/exolabs--Qwen-Image-Edit-2509-8bit.toml

@@ -4,10 +4,6 @@ hidden_size = 1
 supports_tensor = false
 tasks = ["ImageToImage"]
 uses_cfg = true
-family = "qwen-image"
-quantization = "8bit"
-base_model = "Qwen Image Edit"
-capabilities = ["image_edit"]
 
 [storage_size]
 in_bytes = 37014734400

resources/image_model_cards/exolabs--Qwen-Image-Edit-2509.toml

@@ -4,10 +4,6 @@ hidden_size = 1
 supports_tensor = false
 tasks = ["ImageToImage"]
 uses_cfg = true
-family = "qwen-image"
-quantization = ""
-base_model = "Qwen Image Edit"
-capabilities = ["image_edit"]
 
 [storage_size]
 in_bytes = 57445135488

resources/image_model_cards/exolabs--Qwen-Image.toml

@@ -4,10 +4,6 @@ hidden_size = 1
 supports_tensor = false
 tasks = ["TextToImage"]
 uses_cfg = true
-family = "qwen-image"
-quantization = ""
-base_model = "Qwen Image"
-capabilities = ["image_gen"]
 
 [storage_size]
 in_bytes = 57445135488

resources/inference_model_cards/mlx-community--SmolLM2-135M-Instruct.toml

@@ -1,12 +0,0 @@
-model_id = "mlx-community/SmolLM2-135M-Instruct"
-n_layers = 30
-hidden_size = 576
-supports_tensor = true
-tasks = ["TextGeneration"]
-family = "llama"
-quantization = "bf16"
-base_model = "SmolLM2 135M"
-capabilities = ["text"]
-
-[storage_size]
-in_bytes = 269060381

resources/inference_model_cards/mlx-community--Step-3.5-Flash-4bit.toml

@@ -1,12 +0,0 @@
-model_id = "mlx-community/Step-3.5-Flash-4bit"
-n_layers = 45
-hidden_size = 4096
-supports_tensor = true
-tasks = ["TextGeneration"]
-family = "step"
-quantization = "4bit"
-base_model = "Step 3.5 Flash"
-capabilities = ["text", "thinking"]
-
-[storage_size]
-in_bytes = 114572190076

resources/inference_model_cards/mlx-community--Step-3.5-Flash-6bit.toml

@@ -1,12 +0,0 @@
-model_id = "mlx-community/Step-3.5-Flash-6bit"
-n_layers = 45
-hidden_size = 4096
-supports_tensor = true
-tasks = ["TextGeneration"]
-family = "step"
-quantization = "6bit"
-base_model = "Step 3.5 Flash"
-capabilities = ["text", "thinking"]
-
-[storage_size]
-in_bytes = 159039627774

resources/inference_model_cards/mlx-community--Step-3.5-Flash-8Bit.toml

@@ -1,12 +0,0 @@
-model_id = "mlx-community/Step-3.5-Flash-8Bit"
-n_layers = 45
-hidden_size = 4096
-supports_tensor = true
-tasks = ["TextGeneration"]
-family = "step"
-quantization = "8bit"
-base_model = "Step 3.5 Flash"
-capabilities = ["text", "thinking"]
-
-[storage_size]
-in_bytes = 209082699847

resources/inference_model_cards/mlx-community--gemma-2-2b-it-4bit.toml

@@ -1,12 +0,0 @@
-model_id = "mlx-community/gemma-2-2b-it-4bit"
-n_layers = 26
-hidden_size = 2304
-supports_tensor = false
-tasks = ["TextGeneration"]
-family = "gemma2"
-quantization = "4bit"
-base_model = "Gemma 2 2B"
-capabilities = ["text"]
-
-[storage_size]
-in_bytes = 1492755242

rust/exo_pyo3_bindings/src/networking.rs

@@ -22,6 +22,7 @@ use pyo3::{Bound, Py, PyErr, PyResult, PyTraverseError, PyVisit, Python, pymetho
 use pyo3_stub_gen::derive::{gen_stub_pyclass, gen_stub_pyclass_enum, gen_stub_pymethods};
 use std::net::IpAddr;
 use tokio::sync::{Mutex, mpsc, oneshot};
+use util::ext::VecExt as _;
 
 mod exception {
     use pyo3::types::PyTuple;
@@ -531,9 +532,7 @@ impl PyNetworkingHandle {
             .recv_many_py(limit)
             .allow_threads_py() // allow-threads-aware async call
             .await?
-            .into_iter()
-            .map(|(t, d)| (t, d.pybytes()))
-            .collect())
+            .map(|(t, d)| (t, d.pybytes())))
     }
 
     // TODO: rn this blocks main thread if anything else is awaiting the channel (bc its a mutex)

rust/networking/src/swarm.rs

@@ -106,6 +106,7 @@ mod behaviour {
     use crate::{alias, discovery};
     use libp2p::swarm::NetworkBehaviour;
     use libp2p::{gossipsub, identity};
+    use std::time::Duration;
 
     /// Behavior of the Swarm which composes all desired behaviors:
     /// Right now its just [`discovery::Behaviour`] and [`gossipsub::Behaviour`].
@@ -133,6 +134,7 @@ mod behaviour {
         gossipsub::Behaviour::new(
             MessageAuthenticity::Signed(keypair.clone()),
             ConfigBuilder::default()
+                .publish_queue_duration(Duration::from_secs(15))
                 .max_transmit_size(1024 * 1024)
                 .validation_mode(ValidationMode::Strict)
                 .build()

rust/util/Cargo.toml

@@ -13,3 +13,13 @@ path = "src/lib.rs"
 workspace = true
 
 [dependencies]
+# macro dependencies
+extend = { workspace = true }
+
+# utility dependencies
+thiserror = { workspace = true }
+once_cell = { workspace = true }
+internment = { workspace = true }
+derive_more = { workspace = true }
+bon = { workspace = true }
+recursion = { workspace = true }

rust/util/src/lib.rs

@@ -1 +1,53 @@
+//! TODO: crate documentation
+//!
+//! this is here as a placeholder documentation
+//!
+//!
+
+// enable Rust-unstable features for convenience
+#![feature(trait_alias)]
+#![feature(stmt_expr_attributes)]
+#![feature(type_alias_impl_trait)]
+#![feature(specialization)]
+#![feature(unboxed_closures)]
+#![feature(const_trait_impl)]
+#![feature(fn_traits)]
+
+pub mod nonempty;
 pub mod wakerdeque;
+
+pub(crate) mod private {
+    // sealed traits support
+    pub trait Sealed {}
+    impl<T: ?Sized> Sealed for T {}
+}
+
+/// Namespace for all the type/trait aliases used by this crate.
+pub(crate) mod alias {}
+
+/// Namespace for crate-wide extension traits/methods
+pub mod ext {
+    use extend::ext;
+
+    #[ext(pub, name = BoxedSliceExt)]
+    impl<T> Box<[T]> {
+        #[inline]
+        fn map<B, F>(self, f: F) -> Box<[B]>
+        where
+            F: FnMut(T) -> B,
+        {
+            self.into_iter().map(f).collect()
+        }
+    }
+
+    #[ext(pub, name = VecExt)]
+    impl<T> Vec<T> {
+        #[inline]
+        fn map<B, F>(self, f: F) -> Vec<B>
+        where
+            F: FnMut(T) -> B,
+        {
+            self.into_iter().map(f).collect()
+        }
+    }
+}

rust/util/src/nonempty.rs

@@ -0,0 +1,138 @@
+use std::slice::SliceIndex;
+use std::{ops, slice};
+use thiserror::Error;
+
+#[derive(Error, Debug)]
+#[error("Cannot create to `NonemptyArray` because the supplied slice is empty")]
+pub struct EmptySliceError;
+
+/// A pointer to a non-empty fixed-size slice allocated on the heap.
+#[derive(Clone, Debug, PartialEq, Eq, Hash, PartialOrd, Ord)]
+#[repr(transparent)]
+pub struct NonemptyArray<T>(Box<[T]>);
+
+#[allow(clippy::arbitrary_source_item_ordering)]
+impl<T> NonemptyArray<T> {
+    #[inline]
+    pub fn singleton(value: T) -> Self {
+        Self(Box::new([value]))
+    }
+
+    #[allow(clippy::missing_errors_doc)]
+    #[inline]
+    pub fn try_from_boxed_slice<S: Into<Box<[T]>>>(
+        boxed_slice: S,
+    ) -> Result<Self, EmptySliceError> {
+        let boxed_slice = boxed_slice.into();
+        if boxed_slice.is_empty() {
+            Err(EmptySliceError)
+        } else {
+            Ok(Self(boxed_slice))
+        }
+    }
+
+    #[must_use]
+    #[inline]
+    pub fn into_boxed_slice(self) -> Box<[T]> {
+        self.0
+    }
+
+    #[must_use]
+    #[inline]
+    pub fn to_vec(&self) -> Vec<T>
+    where
+        T: Clone,
+    {
+        self.0.to_vec()
+    }
+
+    #[must_use]
+    #[inline]
+    pub const fn as_slice(&self) -> &[T] {
+        &self.0
+    }
+
+    #[allow(clippy::indexing_slicing)]
+    #[must_use]
+    #[inline]
+    pub fn first(&self) -> &T {
+        &self.0[0]
+    }
+
+    #[allow(clippy::indexing_slicing, clippy::arithmetic_side_effects)]
+    #[must_use]
+    #[inline]
+    pub fn last(&self) -> &T {
+        &self.0[self.0.len() - 1]
+    }
+
+    #[must_use]
+    #[inline]
+    pub fn get<I>(&self, index: I) -> Option<&I::Output>
+    where
+        I: SliceIndex<[T]>,
+    {
+        self.0.get(index)
+    }
+
+    #[allow(clippy::len_without_is_empty)]
+    #[must_use]
+    #[inline]
+    pub const fn len(&self) -> usize {
+        self.0.len()
+    }
+
+    #[allow(clippy::iter_without_into_iter)]
+    #[inline]
+    pub fn iter(&self) -> slice::Iter<'_, T> {
+        self.0.iter()
+    }
+
+    #[allow(clippy::iter_without_into_iter)]
+    #[inline]
+    pub fn iter_mut(&mut self) -> slice::IterMut<'_, T> {
+        self.0.iter_mut()
+    }
+
+    #[inline]
+    #[must_use]
+    pub fn map<U, F: FnMut(T) -> U>(self, f: F) -> NonemptyArray<U> {
+        NonemptyArray(self.0.into_iter().map(f).collect())
+    }
+}
+
+impl<T> From<NonemptyArray<T>> for Box<[T]> {
+    #[inline]
+    fn from(value: NonemptyArray<T>) -> Self {
+        value.into_boxed_slice()
+    }
+}
+
+impl<T> ops::Index<usize> for NonemptyArray<T> {
+    type Output = T;
+
+    #[inline]
+    fn index(&self, index: usize) -> &Self::Output {
+        self.0.index(index)
+    }
+}
+
+impl<T> IntoIterator for NonemptyArray<T> {
+    type Item = T;
+    type IntoIter = std::vec::IntoIter<T>;
+
+    #[inline]
+    fn into_iter(self) -> Self::IntoIter {
+        self.into_boxed_slice().into_vec().into_iter()
+    }
+}
+
+impl<'a, T> IntoIterator for &'a NonemptyArray<T> {
+    type Item = &'a T;
+    type IntoIter = slice::Iter<'a, T>;
+
+    #[inline]
+    fn into_iter(self) -> Self::IntoIter {
+        self.iter()
+    }
+}

src/exo/download/coordinator.py

@@ -56,49 +56,8 @@ class DownloadCoordinator:
     event_receiver: Receiver[Event] = field(init=False)
     _tg: TaskGroup = field(init=False, default_factory=anyio.create_task_group)
 
-    # Per-model throttle for download progress events
-    _last_progress_time: dict[ModelId, float] = field(default_factory=dict)
-
     def __post_init__(self) -> None:
         self.event_sender, self.event_receiver = channel[Event]()
-        self.shard_downloader.on_progress(self._download_progress_callback)
-
-    async def _download_progress_callback(
-        self, callback_shard: ShardMetadata, progress: RepoDownloadProgress
-    ) -> None:
-        model_id = callback_shard.model_card.model_id
-        throttle_interval_secs = 1.0
-
-        if progress.status == "complete":
-            completed = DownloadCompleted(
-                shard_metadata=callback_shard,
-                node_id=self.node_id,
-                total_bytes=progress.total_bytes,
-            )
-            self.download_status[model_id] = completed
-            await self.event_sender.send(
-                NodeDownloadProgress(download_progress=completed)
-            )
-            if model_id in self.active_downloads:
-                del self.active_downloads[model_id]
-            self._last_progress_time.pop(model_id, None)
-        elif (
-            progress.status == "in_progress"
-            and current_time() - self._last_progress_time.get(model_id, 0.0)
-            > throttle_interval_secs
-        ):
-            ongoing = DownloadOngoing(
-                node_id=self.node_id,
-                shard_metadata=callback_shard,
-                download_progress=map_repo_download_progress_to_download_progress_data(
-                    progress
-                ),
-            )
-            self.download_status[model_id] = ongoing
-            await self.event_sender.send(
-                NodeDownloadProgress(download_progress=ongoing)
-            )
-            self._last_progress_time[model_id] = current_time()
 
     async def run(self) -> None:
         logger.info("Starting DownloadCoordinator")
@@ -160,12 +119,12 @@ class DownloadCoordinator:
     async def _start_download(self, shard: ShardMetadata) -> None:
         model_id = shard.model_card.model_id
 
-        # Check if already downloading, complete, or recently failed
+        # Check if already downloading or complete
         if model_id in self.download_status:
             status = self.download_status[model_id]
-            if isinstance(status, (DownloadOngoing, DownloadCompleted, DownloadFailed)):
+            if isinstance(status, (DownloadOngoing, DownloadCompleted)):
                 logger.debug(
-                    f"Download for {model_id} already in progress, complete, or failed, skipping"
+                    f"Download for {model_id} already in progress or complete, skipping"
                 )
                 return
 
@@ -210,6 +169,46 @@ class DownloadCoordinator:
         self.download_status[model_id] = status
         self.event_sender.send_nowait(NodeDownloadProgress(download_progress=status))
 
+        last_progress_time = 0.0
+        throttle_interval_secs = 1.0
+
+        async def download_progress_callback(
+            callback_shard: ShardMetadata, progress: RepoDownloadProgress
+        ) -> None:
+            nonlocal last_progress_time
+
+            if progress.status == "complete":
+                completed = DownloadCompleted(
+                    shard_metadata=callback_shard,
+                    node_id=self.node_id,
+                    total_bytes=progress.total_bytes,
+                )
+                self.download_status[callback_shard.model_card.model_id] = completed
+                await self.event_sender.send(
+                    NodeDownloadProgress(download_progress=completed)
+                )
+                # Clean up active download tracking
+                if callback_shard.model_card.model_id in self.active_downloads:
+                    del self.active_downloads[callback_shard.model_card.model_id]
+            elif (
+                progress.status == "in_progress"
+                and current_time() - last_progress_time > throttle_interval_secs
+            ):
+                ongoing = DownloadOngoing(
+                    node_id=self.node_id,
+                    shard_metadata=callback_shard,
+                    download_progress=map_repo_download_progress_to_download_progress_data(
+                        progress
+                    ),
+                )
+                self.download_status[callback_shard.model_card.model_id] = ongoing
+                await self.event_sender.send(
+                    NodeDownloadProgress(download_progress=ongoing)
+                )
+                last_progress_time = current_time()
+
+        self.shard_downloader.on_progress(download_progress_callback)
+
         async def download_wrapper() -> None:
             try:
                 await self.shard_downloader.ensure_shard(shard)
@@ -284,12 +283,6 @@ class DownloadCoordinator:
                     _,
                     progress,
                 ) in self.shard_downloader.get_shard_download_status():
-                    model_id = progress.shard.model_card.model_id
-
-                    # Active downloads emit progress via the callback — don't overwrite
-                    if model_id in self.active_downloads:
-                        continue
-
                     if progress.status == "complete":
                         status: DownloadProgress = DownloadCompleted(
                             node_id=self.node_id,

src/exo/download/download_utils.py

@@ -457,8 +457,6 @@ async def download_file_with_retry(
             )
         except HuggingFaceAuthenticationError:
             raise
-        except FileNotFoundError:
-            raise
         except HuggingFaceRateLimitError as e:
             if attempt == n_attempts - 1:
                 raise e

src/exo/main.py

@@ -251,8 +251,7 @@ class Node:
 def main():
     args = Args.parse()
     soft, hard = resource.getrlimit(resource.RLIMIT_NOFILE)
-    target = min(max(soft, 65535), hard)
-    resource.setrlimit(resource.RLIMIT_NOFILE, (target, hard))
+    resource.setrlimit(resource.RLIMIT_NOFILE, (max(soft, 65535), hard))
 
     mp.set_start_method("spawn")
     # TODO: Refactor the current verbosity system

src/exo/master/adapters/chat_completions.py

@@ -17,7 +17,6 @@ from exo.shared.types.api import (
     LogprobsContentItem,
     StreamingChoiceResponse,
     ToolCall,
-    Usage,
 )
 from exo.shared.types.chunks import ErrorChunk, TokenChunk, ToolCallChunk
 from exo.shared.types.common import CommandId
@@ -80,7 +79,6 @@ def chat_request_to_text_generation(
         seed=request.seed,
         stream=request.stream,
         tools=request.tools,
-        enable_thinking=request.enable_thinking,
         chat_template_messages=chat_template_messages
         if chat_template_messages
         else None,
@@ -126,8 +124,6 @@ async def generate_chat_stream(
     chunk_stream: AsyncGenerator[ErrorChunk | ToolCallChunk | TokenChunk, None],
 ) -> AsyncGenerator[str, None]:
     """Generate Chat Completions API streaming events from chunks."""
-    last_usage: Usage | None = None
-
     async for chunk in chunk_stream:
         if isinstance(chunk, ErrorChunk):
             error_response = ErrorResponse(
@@ -141,8 +137,6 @@ async def generate_chat_stream(
             yield "data: [DONE]\n\n"
             return
 
-        last_usage = chunk.usage or last_usage
-
         if isinstance(chunk, ToolCallChunk):
             tool_call_deltas = [
                 ToolCall(
@@ -166,15 +160,12 @@ async def generate_chat_stream(
                         finish_reason="tool_calls",
                     )
                 ],
-                usage=last_usage,
             )
             yield f"data: {tool_response.model_dump_json()}\n\n"
             yield "data: [DONE]\n\n"
             return
 
         chunk_response = chunk_to_response(chunk, command_id)
-        if chunk.finish_reason is not None:
-            chunk_response = chunk_response.model_copy(update={"usage": last_usage})
         yield f"data: {chunk_response.model_dump_json()}\n\n"
 
         if chunk.finish_reason is not None:
@@ -184,9 +175,7 @@ async def generate_chat_stream(
 async def collect_chat_response(
     command_id: CommandId,
     chunk_stream: AsyncGenerator[ErrorChunk | ToolCallChunk | TokenChunk, None],
-) -> AsyncGenerator[str]:
-    # This is an AsyncGenerator[str] rather than returning a ChatCompletionReponse because
-    # FastAPI handles the cancellation better but wouldn't auto-serialize for some reason
+) -> ChatCompletionResponse:
     """Collect all token chunks and return a single ChatCompletionResponse."""
     text_parts: list[str] = []
     tool_calls: list[ToolCall] = []
@@ -194,7 +183,6 @@ async def collect_chat_response(
     model: str | None = None
     finish_reason: FinishReason | None = None
     error_message: str | None = None
-    last_usage: Usage | None = None
 
     async for chunk in chunk_stream:
         if isinstance(chunk, ErrorChunk):
@@ -204,8 +192,6 @@ async def collect_chat_response(
         if model is None:
             model = chunk.model
 
-        last_usage = chunk.usage or last_usage
-
         if isinstance(chunk, TokenChunk):
             text_parts.append(chunk.text)
             if chunk.logprob is not None:
@@ -236,7 +222,7 @@ async def collect_chat_response(
     combined_text = "".join(text_parts)
     assert model is not None
 
-    yield ChatCompletionResponse(
+    return ChatCompletionResponse(
         id=command_id,
         created=int(time.time()),
         model=model,
@@ -254,6 +240,4 @@ async def collect_chat_response(
                 finish_reason=finish_reason,
             )
         ],
-        usage=last_usage,
-    ).model_dump_json()
-    return
+    )

src/exo/master/adapters/claude.py

@@ -4,7 +4,7 @@ import json
 from collections.abc import AsyncGenerator
 from typing import Any
 
-from exo.shared.types.api import FinishReason, Usage
+from exo.shared.types.api import FinishReason
 from exo.shared.types.chunks import ErrorChunk, TokenChunk, ToolCallChunk
 from exo.shared.types.claude_api import (
     ClaudeContentBlock,
@@ -161,14 +161,12 @@ async def collect_claude_response(
     command_id: CommandId,
     model: str,
     chunk_stream: AsyncGenerator[ErrorChunk | ToolCallChunk | TokenChunk, None],
-) -> AsyncGenerator[str]:
-    # This is an AsyncGenerator[str] rather than returning a ChatCompletionReponse because
-    # FastAPI handles the cancellation better but wouldn't auto-serialize for some reason
+) -> ClaudeMessagesResponse:
     """Collect all token chunks and return a single ClaudeMessagesResponse."""
     text_parts: list[str] = []
     tool_use_blocks: list[ClaudeToolUseBlock] = []
     stop_reason: ClaudeStopReason | None = None
-    last_usage: Usage | None = None
+    last_stats = None
     error_message: str | None = None
 
     async for chunk in chunk_stream:
@@ -176,8 +174,6 @@ async def collect_claude_response(
             error_message = chunk.error_message or "Internal server error"
             break
 
-        last_usage = chunk.usage or last_usage
-
         if isinstance(chunk, ToolCallChunk):
             for tool in chunk.tool_calls:
                 tool_use_blocks.append(
@@ -187,10 +183,12 @@ async def collect_claude_response(
                         input=json.loads(tool.arguments),  # pyright: ignore[reportAny]
                     )
                 )
+            last_stats = chunk.stats or last_stats
             stop_reason = "tool_use"
             continue
 
         text_parts.append(chunk.text)
+        last_stats = chunk.stats or last_stats
 
         if chunk.finish_reason is not None:
             stop_reason = finish_reason_to_claude_stop_reason(chunk.finish_reason)
@@ -210,11 +208,11 @@ async def collect_claude_response(
     if not content:
         content.append(ClaudeTextBlock(text=""))
 
-    # Use actual usage data if available
-    input_tokens = last_usage.prompt_tokens if last_usage else 0
-    output_tokens = last_usage.completion_tokens if last_usage else 0
+    # Use actual usage data from stats if available
+    input_tokens = last_stats.prompt_tokens if last_stats else 0
+    output_tokens = last_stats.generation_tokens if last_stats else 0
 
-    yield ClaudeMessagesResponse(
+    return ClaudeMessagesResponse(
         id=f"msg_{command_id}",
         model=model,
         content=content,
@@ -223,8 +221,7 @@ async def collect_claude_response(
             input_tokens=input_tokens,
             output_tokens=output_tokens,
         ),
-    ).model_dump_json()
-    return
+    )
 
 
 async def generate_claude_stream(
@@ -252,7 +249,7 @@ async def generate_claude_stream(
 
     output_tokens = 0
     stop_reason: ClaudeStopReason | None = None
-    last_usage: Usage | None = None
+    last_stats = None
     next_block_index = 1  # text block is 0, tool blocks start at 1
 
     async for chunk in chunk_stream:
@@ -260,9 +257,8 @@ async def generate_claude_stream(
             # Close text block and bail
             break
 
-        last_usage = chunk.usage or last_usage
-
         if isinstance(chunk, ToolCallChunk):
+            last_stats = chunk.stats or last_stats
             stop_reason = "tool_use"
 
             # Emit tool_use content blocks
@@ -294,6 +290,7 @@ async def generate_claude_stream(
             continue
 
         output_tokens += 1  # Count each chunk as one token
+        last_stats = chunk.stats or last_stats
 
         # content_block_delta
         delta_event = ClaudeContentBlockDeltaEvent(
@@ -305,9 +302,9 @@ async def generate_claude_stream(
         if chunk.finish_reason is not None:
             stop_reason = finish_reason_to_claude_stop_reason(chunk.finish_reason)
 
-    # Use actual token count from usage if available
-    if last_usage is not None:
-        output_tokens = last_usage.completion_tokens
+    # Use actual token count from stats if available
+    if last_stats is not None:
+        output_tokens = last_stats.generation_tokens
 
     # content_block_stop for text block
     block_stop = ClaudeContentBlockStopEvent(index=0)

src/exo/master/adapters/responses.py

@@ -4,7 +4,6 @@ from collections.abc import AsyncGenerator
 from itertools import count
 from typing import Any
 
-from exo.shared.types.api import Usage
 from exo.shared.types.chunks import ErrorChunk, TokenChunk, ToolCallChunk
 from exo.shared.types.common import CommandId
 from exo.shared.types.openai_responses import (
@@ -122,15 +121,13 @@ async def collect_responses_response(
     command_id: CommandId,
     model: str,
     chunk_stream: AsyncGenerator[ErrorChunk | ToolCallChunk | TokenChunk, None],
-) -> AsyncGenerator[str]:
-    # This is an AsyncGenerator[str] rather than returning a ChatCompletionReponse because
-    # FastAPI handles the cancellation better but wouldn't auto-serialize for some reason
+) -> ResponsesResponse:
     """Collect all token chunks and return a single ResponsesResponse."""
     response_id = f"resp_{command_id}"
     item_id = f"item_{command_id}"
     accumulated_text = ""
     function_call_items: list[ResponseFunctionCallItem] = []
-    last_usage: Usage | None = None
+    last_stats = None
     error_message: str | None = None
 
     async for chunk in chunk_stream:
@@ -138,8 +135,6 @@ async def collect_responses_response(
             error_message = chunk.error_message or "Internal server error"
             break
 
-        last_usage = chunk.usage or last_usage
-
         if isinstance(chunk, ToolCallChunk):
             for tool in chunk.tool_calls:
                 function_call_items.append(
@@ -150,20 +145,22 @@ async def collect_responses_response(
                         arguments=tool.arguments,
                     )
                 )
+            last_stats = chunk.stats or last_stats
             continue
 
         accumulated_text += chunk.text
+        last_stats = chunk.stats or last_stats
 
     if error_message is not None:
         raise ValueError(error_message)
 
-    # Create usage from usage data if available
+    # Create usage from stats if available
     usage = None
-    if last_usage is not None:
+    if last_stats is not None:
         usage = ResponseUsage(
-            input_tokens=last_usage.prompt_tokens,
-            output_tokens=last_usage.completion_tokens,
-            total_tokens=last_usage.total_tokens,
+            input_tokens=last_stats.prompt_tokens,
+            output_tokens=last_stats.generation_tokens,
+            total_tokens=last_stats.prompt_tokens + last_stats.generation_tokens,
         )
 
     output: list[ResponseItem] = [
@@ -175,15 +172,14 @@ async def collect_responses_response(
     ]
     output.extend(function_call_items)
 
-    yield ResponsesResponse(
+    return ResponsesResponse(
         id=response_id,
         model=model,
         status="completed",
         output=output,
         output_text=accumulated_text,
         usage=usage,
-    ).model_dump_json()
-    return
+    )
 
 
 async def generate_responses_stream(
@@ -239,16 +235,15 @@ async def generate_responses_stream(
 
     accumulated_text = ""
     function_call_items: list[ResponseFunctionCallItem] = []
-    last_usage: Usage | None = None
+    last_stats = None
     next_output_index = 1  # message item is at 0
 
     async for chunk in chunk_stream:
         if isinstance(chunk, ErrorChunk):
             break
 
-        last_usage = chunk.usage or last_usage
-
         if isinstance(chunk, ToolCallChunk):
+            last_stats = chunk.stats or last_stats
             for tool in chunk.tool_calls:
                 fc_id = f"fc_{tool.id}"
                 call_id = f"call_{tool.id}"
@@ -307,6 +302,7 @@ async def generate_responses_stream(
             continue
 
         accumulated_text += chunk.text
+        last_stats = chunk.stats or last_stats
 
         # response.output_text.delta
         delta_event = ResponseTextDeltaEvent(
@@ -350,13 +346,13 @@ async def generate_responses_stream(
     )
     yield f"event: response.output_item.done\ndata: {item_done.model_dump_json()}\n\n"
 
-    # Create usage from usage data if available
+    # Create usage from stats if available
     usage = None
-    if last_usage is not None:
+    if last_stats is not None:
         usage = ResponseUsage(
-            input_tokens=last_usage.prompt_tokens,
-            output_tokens=last_usage.completion_tokens,
-            total_tokens=last_usage.total_tokens,
+            input_tokens=last_stats.prompt_tokens,
+            output_tokens=last_stats.generation_tokens,
+            total_tokens=last_stats.prompt_tokens + last_stats.generation_tokens,
         )
 
     # response.completed

src/exo/master/api.py

@@ -3,7 +3,7 @@ import contextlib
 import json
 import random
 import time
-from collections.abc import AsyncGenerator, Awaitable, Callable, Iterator
+from collections.abc import AsyncGenerator, Awaitable, Callable
 from datetime import datetime, timezone
 from http import HTTPStatus
 from pathlib import Path
@@ -37,13 +37,11 @@ from exo.master.adapters.responses import (
     generate_responses_stream,
     responses_request_to_text_generation,
 )
-from exo.master.event_log import DiskEventLog
 from exo.master.image_store import ImageStore
 from exo.master.placement import place_instance as get_instance_placements
 from exo.shared.apply import apply
 from exo.shared.constants import (
     DASHBOARD_DIR,
-    EXO_EVENT_LOG_DIR,
     EXO_IMAGE_CACHE_DIR,
     EXO_MAX_CHUNK_SIZE,
     EXO_TRACING_CACHE_DIR,
@@ -125,7 +123,6 @@ from exo.shared.types.commands import (
     PlaceInstance,
     SendInputChunk,
     StartDownload,
-    TaskCancelled,
     TaskFinished,
     TextGeneration,
 )
@@ -149,8 +146,6 @@ from exo.utils.banner import print_startup_banner
 from exo.utils.channels import Receiver, Sender, channel
 from exo.utils.event_buffer import OrderedBuffer
 
-_API_EVENT_LOG_DIR = EXO_EVENT_LOG_DIR / "api"
-
 
 def _format_to_content_type(image_format: Literal["png", "jpeg", "webp"] | None) -> str:
     return f"image/{image_format or 'png'}"
@@ -180,7 +175,7 @@ class API:
         election_receiver: Receiver[ElectionMessage],
     ) -> None:
         self.state = State()
-        self._event_log = DiskEventLog(_API_EVENT_LOG_DIR)
+        self._event_log: list[Event] = []
         self.command_sender = command_sender
         self.download_command_sender = download_command_sender
         self.global_event_receiver = global_event_receiver
@@ -228,8 +223,6 @@ class API:
 
     def reset(self, new_session_id: SessionId, result_clock: int):
         logger.info("Resetting API State")
-        self._event_log.close()
-        self._event_log = DiskEventLog(_API_EVENT_LOG_DIR)
         self.state = State()
         self.session_id = new_session_id
         self.event_buffer = OrderedBuffer[Event]()
@@ -296,7 +289,7 @@ class API:
         self.app.post("/v1/messages", response_model=None)(self.claude_messages)
         self.app.post("/v1/responses", response_model=None)(self.openai_responses)
         self.app.get("/state")(lambda: self.state)
-        self.app.get("/events")(self.stream_events)
+        self.app.get("/events")(lambda: self._event_log)
         self.app.post("/download/start")(self.start_download)
         self.app.delete("/download/{node_id}/{model_id:path}")(self.delete_download)
         self.app.get("/v1/traces")(self.list_traces)
@@ -393,12 +386,7 @@ class API:
         if len(list(self.state.topology.list_nodes())) == 0:
             return PlacementPreviewResponse(previews=[])
 
-        try:
-            model_card = await ModelCard.load(model_id)
-        except Exception as exc:
-            raise HTTPException(
-                status_code=400, detail=f"Failed to load model card: {exc}"
-            ) from exc
+        model_card = await ModelCard.load(model_id)
         instance_combinations: list[tuple[Sharding, InstanceMeta, int]] = []
         for sharding in (Sharding.Pipeline, Sharding.Tensor):
             for instance_meta in (InstanceMeta.MlxRing, InstanceMeta.MlxJaccl):
@@ -541,14 +529,16 @@ class API:
                         break
 
         except anyio.get_cancelled_exc_class():
-            command = TaskCancelled(cancelled_command_id=command_id)
-            with anyio.CancelScope(shield=True):
-                await self.command_sender.send(
-                    ForwarderCommand(origin=self.node_id, command=command)
-                )
+            # TODO: TaskCancelled
+            """
+            self.command_sender.send_nowait(
+                ForwarderCommand(origin=self.node_id, command=command)
+            )
+            """
             raise
         finally:
-            await self._send(TaskFinished(finished_command_id=command_id))
+            command = TaskFinished(finished_command_id=command_id)
+            await self._send(command)
             if command_id in self._text_generation_queues:
                 del self._text_generation_queues[command_id]
 
@@ -643,14 +633,11 @@ class API:
                     "X-Accel-Buffering": "no",
                 },
             )
-        else:
-            return StreamingResponse(
-                collect_chat_response(
-                    command.command_id,
-                    self._token_chunk_stream(command.command_id),
-                ),
-                media_type="application/json",
-            )
+
+        return await collect_chat_response(
+            command.command_id,
+            self._token_chunk_stream(command.command_id),
+        )
 
     async def bench_chat_completions(
         self, payload: BenchChatCompletionRequest
@@ -666,7 +653,8 @@ class API:
         command = TextGeneration(task_params=task_params)
         await self._send(command)
 
-        return await self._collect_text_generation_with_stats(command.command_id)
+        response = await self._collect_text_generation_with_stats(command.command_id)
+        return response
 
     async def _resolve_and_validate_text_model(self, model_id: ModelId) -> ModelId:
         """Validate a text model exists and return the resolved model ID.
@@ -701,22 +689,6 @@ class API:
             )
         return resolved_model
 
-    def stream_events(self) -> StreamingResponse:
-        def _generate_json_array(events: Iterator[Event]) -> Iterator[str]:
-            yield "["
-            first = True
-            for event in events:
-                if not first:
-                    yield ","
-                first = False
-                yield event.model_dump_json()
-            yield "]"
-
-        return StreamingResponse(
-            _generate_json_array(self._event_log.read_all()),
-            media_type="application/json",
-        )
-
     async def get_image(self, image_id: str) -> FileResponse:
         stored = self._image_store.get(Id(image_id))
         if stored is None:
@@ -884,11 +856,6 @@ class API:
                         del image_metadata[key]
 
         except anyio.get_cancelled_exc_class():
-            command = TaskCancelled(cancelled_command_id=command_id)
-            with anyio.CancelScope(shield=True):
-                await self.command_sender.send(
-                    ForwarderCommand(origin=self.node_id, command=command)
-                )
             raise
         finally:
             await self._send(TaskFinished(finished_command_id=command_id))
@@ -970,11 +937,6 @@ class API:
 
             return (images, stats if capture_stats else None)
         except anyio.get_cancelled_exc_class():
-            command = TaskCancelled(cancelled_command_id=command_id)
-            with anyio.CancelScope(shield=True):
-                await self.command_sender.send(
-                    ForwarderCommand(origin=self.node_id, command=command)
-                )
             raise
         finally:
             await self._send(TaskFinished(finished_command_id=command_id))
@@ -1232,15 +1194,12 @@ class API:
                     "X-Accel-Buffering": "no",
                 },
             )
-        else:
-            return StreamingResponse(
-                collect_claude_response(
-                    command.command_id,
-                    payload.model,
-                    self._token_chunk_stream(command.command_id),
-                ),
-                media_type="application/json",
-            )
+
+        return await collect_claude_response(
+            command.command_id,
+            payload.model,
+            self._token_chunk_stream(command.command_id),
+        )
 
     async def openai_responses(
         self, payload: ResponsesRequest
@@ -1268,15 +1227,11 @@ class API:
                 },
             )
 
-        else:
-            return StreamingResponse(
-                collect_responses_response(
-                    command.command_id,
-                    payload.model,
-                    self._token_chunk_stream(command.command_id),
-                ),
-                media_type="application/json",
-            )
+        return await collect_responses_response(
+            command.command_id,
+            payload.model,
+            self._token_chunk_stream(command.command_id),
+        )
 
     def _calculate_total_available_memory(self) -> Memory:
         """Calculate total available memory across all nodes in bytes."""
@@ -1382,7 +1337,6 @@ class API:
                     with anyio.CancelScope(shield=True):
                         shutdown_ev.set()
         finally:
-            self._event_log.close()
             self.command_sender.close()
             self.global_event_receiver.close()
 

src/exo/master/event_log.py

@@ -1,187 +0,0 @@
-import contextlib
-import json
-from collections import OrderedDict
-from collections.abc import Iterator
-from datetime import datetime, timezone
-from io import BufferedRandom, BufferedReader
-from pathlib import Path
-
-import msgspec
-import zstandard
-from loguru import logger
-from pydantic import TypeAdapter
-
-from exo.shared.types.events import Event
-
-_EVENT_ADAPTER: TypeAdapter[Event] = TypeAdapter(Event)
-
-_HEADER_SIZE = 4  # uint32 big-endian
-_OFFSET_CACHE_SIZE = 128
-_MAX_ARCHIVES = 5
-
-
-def _serialize_event(event: Event) -> bytes:
-    return msgspec.msgpack.encode(event.model_dump(mode="json"))
-
-
-def _deserialize_event(raw: bytes) -> Event:
-    # Decode msgpack into a Python dict, then re-encode as JSON for Pydantic.
-    # Pydantic's validate_json() uses JSON-mode coercion (e.g. string -> enum)
-    # even under strict=True, whereas validate_python() does not. Going through
-    # JSON is the only way to get correct round-trip deserialization without
-    # disabling strict mode or adding casts everywhere.
-    as_json = json.dumps(msgspec.msgpack.decode(raw, type=dict))
-    return _EVENT_ADAPTER.validate_json(as_json)
-
-
-def _unpack_header(header: bytes) -> int:
-    return int.from_bytes(header, byteorder="big")
-
-
-def _skip_record(f: BufferedReader) -> bool:
-    """Skip one length-prefixed record. Returns False on EOF."""
-    header = f.read(_HEADER_SIZE)
-    if len(header) < _HEADER_SIZE:
-        return False
-    f.seek(_unpack_header(header), 1)
-    return True
-
-
-def _read_record(f: BufferedReader) -> Event | None:
-    """Read one length-prefixed record. Returns None on EOF."""
-    header = f.read(_HEADER_SIZE)
-    if len(header) < _HEADER_SIZE:
-        return None
-    length = _unpack_header(header)
-    payload = f.read(length)
-    if len(payload) < length:
-        return None
-    return _deserialize_event(payload)
-
-
-class DiskEventLog:
-    """Append-only event log backed by a file on disk.
-
-    On-disk format: sequence of length-prefixed msgpack records.
-    Each record is [4-byte big-endian uint32 length][msgpack payload].
-
-    Uses a bounded LRU cache of event index → byte offset for efficient
-    random access without storing an offset per event.
-    """
-
-    def __init__(self, directory: Path) -> None:
-        self._directory = directory
-        self._directory.mkdir(parents=True, exist_ok=True)
-        self._active_path = directory / "events.bin"
-        self._offset_cache: OrderedDict[int, int] = OrderedDict()
-        self._count: int = 0
-
-        # Rotate stale active file from a previous session/crash
-        if self._active_path.exists():
-            self._rotate(self._active_path, self._directory)
-
-        self._file: BufferedRandom = open(self._active_path, "w+b")  # noqa: SIM115
-
-    def _cache_offset(self, idx: int, offset: int) -> None:
-        self._offset_cache[idx] = offset
-        self._offset_cache.move_to_end(idx)
-        if len(self._offset_cache) > _OFFSET_CACHE_SIZE:
-            self._offset_cache.popitem(last=False)
-
-    def _seek_to(self, f: BufferedReader, target_idx: int) -> None:
-        """Seek f to the byte offset of event target_idx, using cache or scanning forward."""
-        if target_idx in self._offset_cache:
-            self._offset_cache.move_to_end(target_idx)
-            f.seek(self._offset_cache[target_idx])
-            return
-
-        # Find the highest cached index before target_idx
-        scan_from_idx = 0
-        scan_from_offset = 0
-        for cached_idx in self._offset_cache:
-            if cached_idx < target_idx:
-                scan_from_idx = cached_idx
-                scan_from_offset = self._offset_cache[cached_idx]
-
-        # Scan forward, skipping records
-        f.seek(scan_from_offset)
-        for _ in range(scan_from_idx, target_idx):
-            _skip_record(f)
-
-        self._cache_offset(target_idx, f.tell())
-
-    def append(self, event: Event) -> None:
-        packed = _serialize_event(event)
-        self._file.write(len(packed).to_bytes(_HEADER_SIZE, byteorder="big"))
-        self._file.write(packed)
-        self._count += 1
-
-    def read_range(self, start: int, end: int) -> Iterator[Event]:
-        """Yield events from index start (inclusive) to end (exclusive)."""
-        end = min(end, self._count)
-        if start < 0 or end < 0 or start >= end:
-            return
-
-        self._file.flush()
-        with open(self._active_path, "rb") as f:
-            self._seek_to(f, start)
-            for _ in range(end - start):
-                event = _read_record(f)
-                if event is None:
-                    break
-                yield event
-
-            # Cache where we ended up so the next sequential read is a hit
-            if end < self._count:
-                self._cache_offset(end, f.tell())
-
-    def read_all(self) -> Iterator[Event]:
-        """Yield all events from the log one at a time."""
-        if self._count == 0:
-            return
-        self._file.flush()
-        with open(self._active_path, "rb") as f:
-            for _ in range(self._count):
-                event = _read_record(f)
-                if event is None:
-                    break
-                yield event
-
-    def __len__(self) -> int:
-        return self._count
-
-    def close(self) -> None:
-        """Close the file and rotate active file to compressed archive."""
-        if self._file.closed:
-            return
-        self._file.close()
-        if self._active_path.exists() and self._count > 0:
-            self._rotate(self._active_path, self._directory)
-        elif self._active_path.exists():
-            self._active_path.unlink()
-
-    @staticmethod
-    def _rotate(source: Path, directory: Path) -> None:
-        """Compress source into a timestamped archive.
-
-        Keeps at most ``_MAX_ARCHIVES`` compressed copies.  Oldest beyond
-        the limit are deleted.
-        """
-        try:
-            stamp = datetime.now(timezone.utc).strftime("%Y-%m-%d_%H-%M-%S_%f")
-            dest = directory / f"events.{stamp}.bin.zst"
-            compressor = zstandard.ZstdCompressor()
-            with open(source, "rb") as f_in, open(dest, "wb") as f_out:
-                compressor.copy_stream(f_in, f_out)
-            source.unlink()
-            logger.info(f"Rotated event log: {source} -> {dest}")
-
-            # Prune oldest archives beyond the limit
-            archives = sorted(directory.glob("events.*.bin.zst"))
-            for old in archives[:-_MAX_ARCHIVES]:
-                old.unlink()
-        except Exception as e:
-            logger.opt(exception=e).warning(f"Failed to rotate event log {source}")
-            # Clean up the source even if compression fails
-            with contextlib.suppress(OSError):
-                source.unlink()

src/exo/master/main.py

@@ -4,7 +4,6 @@ import anyio
 from anyio.abc import TaskGroup
 from loguru import logger
 
-from exo.master.event_log import DiskEventLog
 from exo.master.placement import (
     add_instance_to_placements,
     cancel_unnecessary_downloads,
@@ -13,7 +12,7 @@ from exo.master.placement import (
     place_instance,
 )
 from exo.shared.apply import apply
-from exo.shared.constants import EXO_EVENT_LOG_DIR, EXO_TRACING_ENABLED
+from exo.shared.constants import EXO_TRACING_ENABLED
 from exo.shared.types.commands import (
     CreateInstance,
     DeleteInstance,
@@ -24,7 +23,6 @@ from exo.shared.types.commands import (
     PlaceInstance,
     RequestEventLog,
     SendInputChunk,
-    TaskCancelled,
     TaskFinished,
     TestCommand,
     TextGeneration,
@@ -40,7 +38,6 @@ from exo.shared.types.events import (
     NodeTimedOut,
     TaskCreated,
     TaskDeleted,
-    TaskStatusUpdated,
     TraceEventData,
     TracesCollected,
     TracesMerged,
@@ -91,7 +88,8 @@ class Master:
             local_event_receiver.clone_sender()
         )
         self._multi_buffer = MultiSourceBuffer[NodeId, Event]()
-        self._event_log = DiskEventLog(EXO_EVENT_LOG_DIR / "master")
+        # TODO: not have this
+        self._event_log: list[Event] = []
         self._pending_traces: dict[TaskId, dict[int, list[TraceEventData]]] = {}
         self._expected_ranks: dict[TaskId, set[int]] = {}
 
@@ -105,7 +103,6 @@ class Master:
                 tg.start_soon(self._loopback_processor)
                 tg.start_soon(self._plan)
         finally:
-            self._event_log.close()
             self.global_event_sender.close()
             self.local_event_receiver.close()
             self.command_receiver.close()
@@ -281,7 +278,7 @@ class Master:
                         case DeleteInstance():
                             placement = delete_instance(command, self.state.instances)
                             transition_events = get_transition_events(
-                                self.state.instances, placement, self.state.tasks
+                                self.state.instances, placement
                             )
                             for cmd in cancel_unnecessary_downloads(
                                 placement, self.state.downloads
@@ -301,7 +298,7 @@ class Master:
                                 self.state.node_network,
                             )
                             transition_events = get_transition_events(
-                                self.state.instances, placement, self.state.tasks
+                                self.state.instances, placement
                             )
                             generated_events.extend(transition_events)
                         case CreateInstance():
@@ -311,7 +308,7 @@ class Master:
                                 self.state.instances,
                             )
                             transition_events = get_transition_events(
-                                self.state.instances, placement, self.state.tasks
+                                self.state.instances, placement
                             )
                             generated_events.extend(transition_events)
                         case SendInputChunk(chunk=chunk):
@@ -321,18 +318,6 @@ class Master:
                                     chunk=chunk,
                                 )
                             )
-                        case TaskCancelled():
-                            if (
-                                task_id := self.command_task_mapping.get(
-                                    command.cancelled_command_id
-                                )
-                            ) is not None:
-                                generated_events.append(
-                                    TaskStatusUpdated(
-                                        task_status=TaskStatus.Cancelled,
-                                        task_id=task_id,
-                                    )
-                                )
                         case TaskFinished():
                             generated_events.append(
                                 TaskDeleted(
@@ -341,18 +326,16 @@ class Master:
                                     ]
                                 )
                             )
-                            self.command_task_mapping.pop(
-                                command.finished_command_id, None
-                            )
+                            if command.finished_command_id in self.command_task_mapping:
+                                del self.command_task_mapping[
+                                    command.finished_command_id
+                                ]
                         case RequestEventLog():
                             # We should just be able to send everything, since other buffers will ignore old messages
-                            # rate limit to 1000 at a time
-                            end = min(command.since_idx + 1000, len(self._event_log))
-                            for i, event in enumerate(
-                                self._event_log.read_range(command.since_idx, end),
-                                start=command.since_idx,
-                            ):
-                                await self._send_event(IndexedEvent(idx=i, event=event))
+                            for i in range(command.since_idx, len(self._event_log)):
+                                await self._send_event(
+                                    IndexedEvent(idx=i, event=self._event_log[i])
+                                )
                     for event in generated_events:
                         await self.event_sender.send(event)
                 except ValueError as e:

src/exo/master/placement.py

@@ -22,15 +22,9 @@ from exo.shared.types.commands import (
     PlaceInstance,
 )
 from exo.shared.types.common import NodeId
-from exo.shared.types.events import (
-    Event,
-    InstanceCreated,
-    InstanceDeleted,
-    TaskStatusUpdated,
-)
+from exo.shared.types.events import Event, InstanceCreated, InstanceDeleted
 from exo.shared.types.memory import Memory
 from exo.shared.types.profiling import MemoryUsage, NodeNetworkInfo
-from exo.shared.types.tasks import Task, TaskId, TaskStatus
 from exo.shared.types.worker.downloads import (
     DownloadOngoing,
     DownloadProgress,
@@ -192,7 +186,6 @@ def delete_instance(
 def get_transition_events(
     current_instances: Mapping[InstanceId, Instance],
     target_instances: Mapping[InstanceId, Instance],
-    tasks: Mapping[TaskId, Task],
 ) -> Sequence[Event]:
     events: list[Event] = []
 
@@ -208,18 +201,6 @@ def get_transition_events(
     # find instances to delete
     for instance_id in current_instances:
         if instance_id not in target_instances:
-            for task in tasks.values():
-                if task.instance_id == instance_id and task.task_status in [
-                    TaskStatus.Pending,
-                    TaskStatus.Running,
-                ]:
-                    events.append(
-                        TaskStatusUpdated(
-                            task_status=TaskStatus.Cancelled,
-                            task_id=task.task_id,
-                        )
-                    )
-
             events.append(
                 InstanceDeleted(
                     instance_id=instance_id,

src/exo/master/tests/test_claude_tool_use.py

@@ -4,11 +4,7 @@ import json
 from collections.abc import AsyncGenerator
 from typing import Any, cast
 
-from exo.master.adapters.claude import (
-    ClaudeMessagesResponse,
-    collect_claude_response,
-    generate_claude_stream,
-)
+from exo.master.adapters.claude import collect_claude_response, generate_claude_stream
 from exo.shared.types.api import ToolCallItem
 from exo.shared.types.chunks import ErrorChunk, TokenChunk, ToolCallChunk
 from exo.shared.types.common import CommandId, ModelId
@@ -21,18 +17,6 @@ async def _chunks_to_stream(
         yield chunk
 
 
-async def _collect_response(
-    command_id: CommandId,
-    model: str,
-    chunk_stream: AsyncGenerator[ErrorChunk | ToolCallChunk | TokenChunk, None],
-) -> ClaudeMessagesResponse:
-    """Helper to consume the async generator and parse the JSON response."""
-    parts: list[str] = []
-    async for part in collect_claude_response(command_id, model, chunk_stream):
-        parts.append(part)
-    return ClaudeMessagesResponse.model_validate_json("".join(parts))
-
-
 MODEL = ModelId("test-model")
 COMMAND_ID = CommandId("cmd_test123")
 
@@ -63,7 +47,7 @@ class TestCollectClaudeResponseToolUse:
                 ],
             ),
         ]
-        response = await _collect_response(
+        response = await collect_claude_response(
             COMMAND_ID, "test-model", _chunks_to_stream(chunks)
         )
 
@@ -93,7 +77,7 @@ class TestCollectClaudeResponseToolUse:
                 ],
             ),
         ]
-        response = await _collect_response(
+        response = await collect_claude_response(
             COMMAND_ID, "test-model", _chunks_to_stream(chunks)
         )
 
@@ -118,7 +102,7 @@ class TestCollectClaudeResponseToolUse:
                 ],
             ),
         ]
-        response = await _collect_response(
+        response = await collect_claude_response(
             COMMAND_ID, "test-model", _chunks_to_stream(chunks)
         )
 
@@ -132,7 +116,7 @@ class TestCollectClaudeResponseToolUse:
 
     async def test_no_content_produces_empty_text_block(self):
         chunks: list[ErrorChunk | ToolCallChunk | TokenChunk] = []
-        response = await _collect_response(
+        response = await collect_claude_response(
             COMMAND_ID, "test-model", _chunks_to_stream(chunks)
         )
         assert len(response.content) == 1

src/exo/master/tests/test_event_log.py

@@ -1,155 +0,0 @@
-from pathlib import Path
-
-import pytest
-
-from exo.master.event_log import DiskEventLog
-from exo.shared.types.events import TestEvent
-
-
-@pytest.fixture
-def log_dir(tmp_path: Path) -> Path:
-    return tmp_path / "event_log"
-
-
-def test_append_and_read_back(log_dir: Path):
-    log = DiskEventLog(log_dir)
-    events = [TestEvent() for _ in range(5)]
-    for e in events:
-        log.append(e)
-
-    assert len(log) == 5
-
-    result = list(log.read_all())
-    assert len(result) == 5
-    for original, restored in zip(events, result, strict=True):
-        assert original.event_id == restored.event_id
-
-    log.close()
-
-
-def test_read_range(log_dir: Path):
-    log = DiskEventLog(log_dir)
-    events = [TestEvent() for _ in range(10)]
-    for e in events:
-        log.append(e)
-
-    result = list(log.read_range(3, 7))
-    assert len(result) == 4
-    for i, restored in enumerate(result):
-        assert events[3 + i].event_id == restored.event_id
-
-    log.close()
-
-
-def test_read_range_bounds(log_dir: Path):
-    log = DiskEventLog(log_dir)
-    events = [TestEvent() for _ in range(3)]
-    for e in events:
-        log.append(e)
-
-    # Start beyond count
-    assert list(log.read_range(5, 10)) == []
-    # Negative start
-    assert list(log.read_range(-1, 2)) == []
-    # End beyond count is clamped
-    result = list(log.read_range(1, 100))
-    assert len(result) == 2
-
-    log.close()
-
-
-def test_empty_log(log_dir: Path):
-    log = DiskEventLog(log_dir)
-    assert len(log) == 0
-    assert list(log.read_all()) == []
-    assert list(log.read_range(0, 10)) == []
-    log.close()
-
-
-def _archives(log_dir: Path) -> list[Path]:
-    return sorted(log_dir.glob("events.*.bin.zst"))
-
-
-def test_rotation_on_close(log_dir: Path):
-    log = DiskEventLog(log_dir)
-    log.append(TestEvent())
-    log.close()
-
-    active = log_dir / "events.bin"
-    assert not active.exists()
-
-    archives = _archives(log_dir)
-    assert len(archives) == 1
-    assert archives[0].stat().st_size > 0
-
-
-def test_rotation_on_construction_with_stale_file(log_dir: Path):
-    log_dir.mkdir(parents=True, exist_ok=True)
-    (log_dir / "events.bin").write_bytes(b"stale data")
-
-    log = DiskEventLog(log_dir)
-    archives = _archives(log_dir)
-    assert len(archives) == 1
-    assert archives[0].exists()
-    assert len(log) == 0
-
-    log.close()
-
-
-def test_empty_log_no_archive(log_dir: Path):
-    """Closing an empty log should not leave an archive."""
-    log = DiskEventLog(log_dir)
-    log.close()
-
-    active = log_dir / "events.bin"
-
-    assert not active.exists()
-    assert _archives(log_dir) == []
-
-
-def test_close_is_idempotent(log_dir: Path):
-    log = DiskEventLog(log_dir)
-    log.append(TestEvent())
-    log.close()
-    archive = _archives(log_dir)
-    log.close()  # should not raise
-
-    assert _archives(log_dir) == archive
-
-
-def test_successive_sessions(log_dir: Path):
-    """Simulate two master sessions: both archives should be kept."""
-    log1 = DiskEventLog(log_dir)
-    log1.append(TestEvent())
-    log1.close()
-
-    first_archive = _archives(log_dir)[-1]
-
-    log2 = DiskEventLog(log_dir)
-    log2.append(TestEvent())
-    log2.append(TestEvent())
-    log2.close()
-
-    # Session 1 archive shifted to slot 2, session 2 in slot 1
-    second_archive = _archives(log_dir)[-1]
-    should_be_first_archive = _archives(log_dir)[-2]
-
-    assert first_archive.exists()
-    assert second_archive.exists()
-    assert first_archive != second_archive
-    assert should_be_first_archive == first_archive
-
-
-def test_rotation_keeps_at_most_5_archives(log_dir: Path):
-    """After 7 sessions, only the 5 most recent archives should remain."""
-    all_archives: list[Path] = []
-    for _ in range(7):
-        log = DiskEventLog(log_dir)
-        log.append(TestEvent())
-        log.close()
-        all_archives.append(_archives(log_dir)[-1])
-
-    for old in all_archives[:2]:
-        assert not old.exists()
-    for recent in all_archives[2:]:
-        assert recent.exists()

src/exo/master/tests/test_placement.py

@@ -239,7 +239,7 @@ def test_get_transition_events_no_change(instance: Instance):
     target_instances = {instance_id: instance}
 
     # act
-    events = get_transition_events(current_instances, target_instances, {})
+    events = get_transition_events(current_instances, target_instances)
 
     # assert
     assert len(events) == 0
@@ -252,7 +252,7 @@ def test_get_transition_events_create_instance(instance: Instance):
     target_instances: dict[InstanceId, Instance] = {instance_id: instance}
 
     # act
-    events = get_transition_events(current_instances, target_instances, {})
+    events = get_transition_events(current_instances, target_instances)
 
     # assert
     assert len(events) == 1
@@ -266,7 +266,7 @@ def test_get_transition_events_delete_instance(instance: Instance):
     target_instances: dict[InstanceId, Instance] = {}
 
     # act
-    events = get_transition_events(current_instances, target_instances, {})
+    events = get_transition_events(current_instances, target_instances)
 
     # assert
     assert len(events) == 1

src/exo/routing/router.py

@@ -207,10 +207,10 @@ class Router:
                 try:
                     logger.trace(f"Sending message on {topic} with payload {data}")
                     await self._net.gossipsub_publish(topic, data)
-                except NoPeersSubscribedToTopicError:
+                # As a hack, this also catches AllQueuesFull
+                # Need to fix that ASAP.
+                except (NoPeersSubscribedToTopicError, AllQueuesFullError):
                     pass
-                except AllQueuesFullError:
-                    logger.warning(f"All peer queues full, dropping message on {topic}")
 
 
 def get_node_id_keypair(

src/exo/shared/apply.py

@@ -31,7 +31,6 @@ from exo.shared.types.events import (
 from exo.shared.types.profiling import (
     NodeIdentity,
     NodeNetworkInfo,
-    NodeRdmaCtlStatus,
     NodeThunderboltInfo,
     ThunderboltBridgeStatus,
 )
@@ -48,9 +47,7 @@ from exo.utils.info_gatherer.info_gatherer import (
     MemoryUsage,
     MiscData,
     NodeConfig,
-    NodeDiskUsage,
     NodeNetworkInterfaces,
-    RdmaCtlStatus,
     StaticNodeInformation,
     ThunderboltBridgeInfo,
 )
@@ -226,9 +223,6 @@ def apply_node_timed_out(event: NodeTimedOut, state: State) -> State:
     node_memory = {
         key: value for key, value in state.node_memory.items() if key != event.node_id
     }
-    node_disk = {
-        key: value for key, value in state.node_disk.items() if key != event.node_id
-    }
     node_system = {
         key: value for key, value in state.node_system.items() if key != event.node_id
     }
@@ -245,9 +239,6 @@ def apply_node_timed_out(event: NodeTimedOut, state: State) -> State:
         for key, value in state.node_thunderbolt_bridge.items()
         if key != event.node_id
     }
-    node_rdma_ctl = {
-        key: value for key, value in state.node_rdma_ctl.items() if key != event.node_id
-    }
     # Only recompute cycles if the leaving node had TB bridge enabled
     leaving_node_status = state.node_thunderbolt_bridge.get(event.node_id)
     leaving_node_had_tb_enabled = (
@@ -265,12 +256,10 @@ def apply_node_timed_out(event: NodeTimedOut, state: State) -> State:
             "last_seen": last_seen,
             "node_identities": node_identities,
             "node_memory": node_memory,
-            "node_disk": node_disk,
             "node_system": node_system,
             "node_network": node_network,
             "node_thunderbolt": node_thunderbolt,
             "node_thunderbolt_bridge": node_thunderbolt_bridge,
-            "node_rdma_ctl": node_rdma_ctl,
             "thunderbolt_bridge_cycles": thunderbolt_bridge_cycles,
         }
     )
@@ -299,8 +288,6 @@ def apply_node_gathered_info(event: NodeGatheredInfo, state: State) -> State:
             update["node_memory"] = {**state.node_memory, event.node_id: info.memory}
         case MemoryUsage():
             update["node_memory"] = {**state.node_memory, event.node_id: info}
-        case NodeDiskUsage():
-            update["node_disk"] = {**state.node_disk, event.node_id: info.disk_usage}
         case NodeConfig():
             pass
         case MiscData():
@@ -315,12 +302,7 @@ def apply_node_gathered_info(event: NodeGatheredInfo, state: State) -> State:
         case StaticNodeInformation():
             current_identity = state.node_identities.get(event.node_id, NodeIdentity())
             new_identity = current_identity.model_copy(
-                update={
-                    "model_id": info.model,
-                    "chip_id": info.chip,
-                    "os_version": info.os_version,
-                    "os_build_version": info.os_build_version,
-                }
+                update={"model_id": info.model, "chip_id": info.chip}
             )
             update["node_identities"] = {
                 **state.node_identities,
@@ -372,11 +354,6 @@ def apply_node_gathered_info(event: NodeGatheredInfo, state: State) -> State:
                         new_tb_bridge, state.node_network
                     )
                 )
-        case RdmaCtlStatus():
-            update["node_rdma_ctl"] = {
-                **state.node_rdma_ctl,
-                event.node_id: NodeRdmaCtlStatus(enabled=info.enabled),
-            }
 
     return state.model_copy(update=update)
 

src/exo/shared/constants.py

@@ -43,8 +43,7 @@ DASHBOARD_DIR = (
 )
 
 # Log files (data/logs or cache)
-EXO_LOG_DIR = EXO_CACHE_HOME / "exo_log"
-EXO_LOG = EXO_LOG_DIR / "exo.log"
+EXO_LOG = EXO_CACHE_HOME / "exo.log"
 EXO_TEST_LOG = EXO_CACHE_HOME / "exo_test.log"
 
 # Identity (config)
@@ -61,7 +60,6 @@ EXO_MAX_CHUNK_SIZE = 512 * 1024
 
 EXO_CUSTOM_MODEL_CARDS_DIR = EXO_DATA_HOME / "custom_model_cards"
 
-EXO_EVENT_LOG_DIR = EXO_DATA_HOME / "event_log"
 EXO_IMAGE_CACHE_DIR = EXO_CACHE_HOME / "images"
 EXO_TRACING_CACHE_DIR = EXO_CACHE_HOME / "traces"
 

src/exo/shared/logging.py

@@ -1,30 +1,11 @@
 import logging
 import sys
-from collections.abc import Iterator
 from pathlib import Path
 
-import zstandard
 from hypercorn import Config
 from hypercorn.logging import Logger as HypercornLogger
 from loguru import logger
 
-_MAX_LOG_ARCHIVES = 5
-
-
-def _zstd_compress(filepath: str) -> None:
-    source = Path(filepath)
-    dest = source.with_suffix(source.suffix + ".zst")
-    cctx = zstandard.ZstdCompressor()
-    with open(source, "rb") as f_in, open(dest, "wb") as f_out:
-        cctx.copy_stream(f_in, f_out)
-    source.unlink()
-
-
-def _once_then_never() -> Iterator[bool]:
-    yield True
-    while True:
-        yield False
-
 
 class InterceptLogger(HypercornLogger):
     def __init__(self, config: Config):
@@ -72,16 +53,13 @@ def logger_setup(log_file: Path | None, verbosity: int = 0):
             enqueue=True,
         )
     if log_file:
-        rotate_once = _once_then_never()
         logger.add(
             log_file,
             format="[ {time:YYYY-MM-DD HH:mm:ss.SSS} | {level: <8} | {name}:{function}:{line} ] {message}",
             level="INFO",
             colorize=False,
             enqueue=True,
-            rotation=lambda _, __: next(rotate_once),
-            retention=_MAX_LOG_ARCHIVES,
-            compression=_zstd_compress,
+            rotation="1 week",
         )
 
 

src/exo/shared/models/model_cards.py

@@ -30,11 +30,11 @@ from exo.utils.pydantic_ext import CamelCaseModel
 # kinda ugly...
 # TODO: load search path from config.toml
 _custom_cards_dir = Path(str(EXO_CUSTOM_MODEL_CARDS_DIR))
-CARD_SEARCH_PATH = [
-    Path(RESOURCES_DIR) / "inference_model_cards",
-    Path(RESOURCES_DIR) / "image_model_cards",
-    _custom_cards_dir,
-]
+_csp = [Path(RESOURCES_DIR) / "inference_model_cards", _custom_cards_dir]
+if EXO_ENABLE_IMAGE_MODELS:
+    _csp.append(Path(RESOURCES_DIR) / "image_model_cards")
+
+CARD_SEARCH_PATH = _csp
 
 _card_cache: dict[ModelId, "ModelCard"] = {}
 
@@ -49,16 +49,10 @@ async def _refresh_card_cache():
                 pass
 
 
-def _is_image_card(card: "ModelCard") -> bool:
-    return any(t in (ModelTask.TextToImage, ModelTask.ImageToImage) for t in card.tasks)
-
-
 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)]
+    return list(_card_cache.values())
 
 
 class ModelTask(str, Enum):
@@ -189,7 +183,6 @@ class ConfigData(BaseModel):
             ["MiniMaxM2ForCausalLM"],
             ["LlamaForCausalLM"],
             ["GptOssForCausalLM"],
-            ["Step3p5ForCausalLM"],
         ]
 
     @model_validator(mode="before")