fix chat completions call_

fix tool calling again
move
2026-02-06 18:44:34 +00:00 · 2026-02-06 18:26:11 +00:00 · 2026-02-06 17:36:53 +00:00 · 2026-02-06 17:31:55 +00:00 · 2026-02-06 17:17:36 +00:00
140 changed files with 1768 additions and 7709 deletions
@@ -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"
@@ -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 }}
@@ -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:
@@ -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: ...
@@ -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.
@@ -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"
@@ -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).
@@ -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:
@@ -1,628 +0,0 @@
-// !$*UTF8*$!
-{
-	archiveVersion = 1;
-	classes = {
-	};
-	objectVersion = 77;
-	objects = {
-
-/* Begin PBXBuildFile section */
-		E09D17522F44F359009C51A3 /* MLXLLM in Frameworks */ = {isa = PBXBuildFile; productRef = E09D17512F44F359009C51A3 /* MLXLLM */; };
-		E09D17542F44F359009C51A3 /* MLXLMCommon in Frameworks */ = {isa = PBXBuildFile; productRef = E09D17532F44F359009C51A3 /* MLXLMCommon */; };
-/* End PBXBuildFile section */
-
-/* Begin PBXContainerItemProxy section */
-		E09D167D2F44CA20009C51A3 /* PBXContainerItemProxy */ = {
-			isa = PBXContainerItemProxy;
-			containerPortal = E09D16672F44CA1E009C51A3 /* Project object */;
-			proxyType = 1;
-			remoteGlobalIDString = E09D166E2F44CA1E009C51A3;
-			remoteInfo = "EXO-iOS";
-		};
-		E09D16872F44CA20009C51A3 /* PBXContainerItemProxy */ = {
-			isa = PBXContainerItemProxy;
-			containerPortal = E09D16672F44CA1E009C51A3 /* Project object */;
-			proxyType = 1;
-			remoteGlobalIDString = E09D166E2F44CA1E009C51A3;
-			remoteInfo = "EXO-iOS";
-		};
-/* End PBXContainerItemProxy section */
-
-/* Begin PBXFileReference section */
-		E09D166F2F44CA1E009C51A3 /* EXO-iOS.app */ = {isa = PBXFileReference; explicitFileType = wrapper.application; includeInIndex = 0; path = "EXO-iOS.app"; sourceTree = BUILT_PRODUCTS_DIR; };
-		E09D167C2F44CA20009C51A3 /* EXO-iOSTests.xctest */ = {isa = PBXFileReference; explicitFileType = wrapper.cfbundle; includeInIndex = 0; path = "EXO-iOSTests.xctest"; sourceTree = BUILT_PRODUCTS_DIR; };
-		E09D16862F44CA20009C51A3 /* EXO-iOSUITests.xctest */ = {isa = PBXFileReference; explicitFileType = wrapper.cfbundle; includeInIndex = 0; path = "EXO-iOSUITests.xctest"; sourceTree = BUILT_PRODUCTS_DIR; };
-/* End PBXFileReference section */
-
-/* Begin PBXFileSystemSynchronizedBuildFileExceptionSet section */
-		E09D169A2F44CA20009C51A3 /* Exceptions for "EXO-iOS" folder in "EXO-iOS" target */ = {
-			isa = PBXFileSystemSynchronizedBuildFileExceptionSet;
-			membershipExceptions = (
-				Info.plist,
-			);
-			target = E09D166E2F44CA1E009C51A3 /* EXO-iOS */;
-		};
-/* End PBXFileSystemSynchronizedBuildFileExceptionSet section */
-
-/* Begin PBXFileSystemSynchronizedRootGroup section */
-		E09D16712F44CA1E009C51A3 /* EXO-iOS */ = {
-			isa = PBXFileSystemSynchronizedRootGroup;
-			exceptions = (
-				E09D169A2F44CA20009C51A3 /* Exceptions for "EXO-iOS" folder in "EXO-iOS" target */,
-			);
-			path = "EXO-iOS";
-			sourceTree = "<group>";
-		};
-		E09D167F2F44CA20009C51A3 /* EXO-iOSTests */ = {
-			isa = PBXFileSystemSynchronizedRootGroup;
-			path = "EXO-iOSTests";
-			sourceTree = "<group>";
-		};
-		E09D16892F44CA20009C51A3 /* EXO-iOSUITests */ = {
-			isa = PBXFileSystemSynchronizedRootGroup;
-			path = "EXO-iOSUITests";
-			sourceTree = "<group>";
-		};
-/* End PBXFileSystemSynchronizedRootGroup section */
-
-/* Begin PBXFrameworksBuildPhase section */
-		E09D166C2F44CA1E009C51A3 /* Frameworks */ = {
-			isa = PBXFrameworksBuildPhase;
-			buildActionMask = 2147483647;
-			files = (
-				E09D17542F44F359009C51A3 /* MLXLMCommon in Frameworks */,
-				E09D17522F44F359009C51A3 /* MLXLLM in Frameworks */,
-			);
-			runOnlyForDeploymentPostprocessing = 0;
-		};
-		E09D16792F44CA20009C51A3 /* Frameworks */ = {
-			isa = PBXFrameworksBuildPhase;
-			buildActionMask = 2147483647;
-			files = (
-			);
-			runOnlyForDeploymentPostprocessing = 0;
-		};
-		E09D16832F44CA20009C51A3 /* Frameworks */ = {
-			isa = PBXFrameworksBuildPhase;
-			buildActionMask = 2147483647;
-			files = (
-			);
-			runOnlyForDeploymentPostprocessing = 0;
-		};
-/* End PBXFrameworksBuildPhase section */
-
-/* Begin PBXGroup section */
-		E09D16662F44CA1E009C51A3 = {
-			isa = PBXGroup;
-			children = (
-				E09D16712F44CA1E009C51A3 /* EXO-iOS */,
-				E09D167F2F44CA20009C51A3 /* EXO-iOSTests */,
-				E09D16892F44CA20009C51A3 /* EXO-iOSUITests */,
-				E09D16702F44CA1E009C51A3 /* Products */,
-			);
-			sourceTree = "<group>";
-		};
-		E09D16702F44CA1E009C51A3 /* Products */ = {
-			isa = PBXGroup;
-			children = (
-				E09D166F2F44CA1E009C51A3 /* EXO-iOS.app */,
-				E09D167C2F44CA20009C51A3 /* EXO-iOSTests.xctest */,
-				E09D16862F44CA20009C51A3 /* EXO-iOSUITests.xctest */,
-			);
-			name = Products;
-			sourceTree = "<group>";
-		};
-/* End PBXGroup section */
-
-/* Begin PBXNativeTarget section */
-		E09D166E2F44CA1E009C51A3 /* EXO-iOS */ = {
-			isa = PBXNativeTarget;
-			buildConfigurationList = E09D16902F44CA20009C51A3 /* Build configuration list for PBXNativeTarget "EXO-iOS" */;
-			buildPhases = (
-				E09D166B2F44CA1E009C51A3 /* Sources */,
-				E09D166C2F44CA1E009C51A3 /* Frameworks */,
-				E09D166D2F44CA1E009C51A3 /* Resources */,
-			);
-			buildRules = (
-			);
-			dependencies = (
-			);
-			fileSystemSynchronizedGroups = (
-				E09D16712F44CA1E009C51A3 /* EXO-iOS */,
-			);
-			name = "EXO-iOS";
-			packageProductDependencies = (
-				E09D17512F44F359009C51A3 /* MLXLLM */,
-				E09D17532F44F359009C51A3 /* MLXLMCommon */,
-			);
-			productName = "EXO-iOS";
-			productReference = E09D166F2F44CA1E009C51A3 /* EXO-iOS.app */;
-			productType = "com.apple.product-type.application";
-		};
-		E09D167B2F44CA20009C51A3 /* EXO-iOSTests */ = {
-			isa = PBXNativeTarget;
-			buildConfigurationList = E09D16932F44CA20009C51A3 /* Build configuration list for PBXNativeTarget "EXO-iOSTests" */;
-			buildPhases = (
-				E09D16782F44CA20009C51A3 /* Sources */,
-				E09D16792F44CA20009C51A3 /* Frameworks */,
-				E09D167A2F44CA20009C51A3 /* Resources */,
-			);
-			buildRules = (
-			);
-			dependencies = (
-				E09D167E2F44CA20009C51A3 /* PBXTargetDependency */,
-			);
-			fileSystemSynchronizedGroups = (
-				E09D167F2F44CA20009C51A3 /* EXO-iOSTests */,
-			);
-			name = "EXO-iOSTests";
-			packageProductDependencies = (
-			);
-			productName = "EXO-iOSTests";
-			productReference = E09D167C2F44CA20009C51A3 /* EXO-iOSTests.xctest */;
-			productType = "com.apple.product-type.bundle.unit-test";
-		};
-		E09D16852F44CA20009C51A3 /* EXO-iOSUITests */ = {
-			isa = PBXNativeTarget;
-			buildConfigurationList = E09D16962F44CA20009C51A3 /* Build configuration list for PBXNativeTarget "EXO-iOSUITests" */;
-			buildPhases = (
-				E09D16822F44CA20009C51A3 /* Sources */,
-				E09D16832F44CA20009C51A3 /* Frameworks */,
-				E09D16842F44CA20009C51A3 /* Resources */,
-			);
-			buildRules = (
-			);
-			dependencies = (
-				E09D16882F44CA20009C51A3 /* PBXTargetDependency */,
-			);
-			fileSystemSynchronizedGroups = (
-				E09D16892F44CA20009C51A3 /* EXO-iOSUITests */,
-			);
-			name = "EXO-iOSUITests";
-			packageProductDependencies = (
-			);
-			productName = "EXO-iOSUITests";
-			productReference = E09D16862F44CA20009C51A3 /* EXO-iOSUITests.xctest */;
-			productType = "com.apple.product-type.bundle.ui-testing";
-		};
-/* End PBXNativeTarget section */
-
-/* Begin PBXProject section */
-		E09D16672F44CA1E009C51A3 /* Project object */ = {
-			isa = PBXProject;
-			attributes = {
-				BuildIndependentTargetsInParallel = 1;
-				LastSwiftUpdateCheck = 2620;
-				LastUpgradeCheck = 2620;
-				TargetAttributes = {
-					E09D166E2F44CA1E009C51A3 = {
-						CreatedOnToolsVersion = 26.2;
-					};
-					E09D167B2F44CA20009C51A3 = {
-						CreatedOnToolsVersion = 26.2;
-						TestTargetID = E09D166E2F44CA1E009C51A3;
-					};
-					E09D16852F44CA20009C51A3 = {
-						CreatedOnToolsVersion = 26.2;
-						TestTargetID = E09D166E2F44CA1E009C51A3;
-					};
-				};
-			};
-			buildConfigurationList = E09D166A2F44CA1E009C51A3 /* Build configuration list for PBXProject "EXO-iOS" */;
-			developmentRegion = en;
-			hasScannedForEncodings = 0;
-			knownRegions = (
-				en,
-				Base,
-			);
-			mainGroup = E09D16662F44CA1E009C51A3;
-			minimizedProjectReferenceProxies = 1;
-			packageReferences = (
-				E09D17502F44F359009C51A3 /* XCRemoteSwiftPackageReference "mlx-swift-lm" */,
-			);
-			preferredProjectObjectVersion = 77;
-			productRefGroup = E09D16702F44CA1E009C51A3 /* Products */;
-			projectDirPath = "";
-			projectRoot = "";
-			targets = (
-				E09D166E2F44CA1E009C51A3 /* EXO-iOS */,
-				E09D167B2F44CA20009C51A3 /* EXO-iOSTests */,
-				E09D16852F44CA20009C51A3 /* EXO-iOSUITests */,
-			);
-		};
-/* End PBXProject section */
-
-/* Begin PBXResourcesBuildPhase section */
-		E09D166D2F44CA1E009C51A3 /* Resources */ = {
-			isa = PBXResourcesBuildPhase;
-			buildActionMask = 2147483647;
-			files = (
-			);
-			runOnlyForDeploymentPostprocessing = 0;
-		};
-		E09D167A2F44CA20009C51A3 /* Resources */ = {
-			isa = PBXResourcesBuildPhase;
-			buildActionMask = 2147483647;
-			files = (
-			);
-			runOnlyForDeploymentPostprocessing = 0;
-		};
-		E09D16842F44CA20009C51A3 /* Resources */ = {
-			isa = PBXResourcesBuildPhase;
-			buildActionMask = 2147483647;
-			files = (
-			);
-			runOnlyForDeploymentPostprocessing = 0;
-		};
-/* End PBXResourcesBuildPhase section */
-
-/* Begin PBXSourcesBuildPhase section */
-		E09D166B2F44CA1E009C51A3 /* Sources */ = {
-			isa = PBXSourcesBuildPhase;
-			buildActionMask = 2147483647;
-			files = (
-			);
-			runOnlyForDeploymentPostprocessing = 0;
-		};
-		E09D16782F44CA20009C51A3 /* Sources */ = {
-			isa = PBXSourcesBuildPhase;
-			buildActionMask = 2147483647;
-			files = (
-			);
-			runOnlyForDeploymentPostprocessing = 0;
-		};
-		E09D16822F44CA20009C51A3 /* Sources */ = {
-			isa = PBXSourcesBuildPhase;
-			buildActionMask = 2147483647;
-			files = (
-			);
-			runOnlyForDeploymentPostprocessing = 0;
-		};
-/* End PBXSourcesBuildPhase section */
-
-/* Begin PBXTargetDependency section */
-		E09D167E2F44CA20009C51A3 /* PBXTargetDependency */ = {
-			isa = PBXTargetDependency;
-			target = E09D166E2F44CA1E009C51A3 /* EXO-iOS */;
-			targetProxy = E09D167D2F44CA20009C51A3 /* PBXContainerItemProxy */;
-		};
-		E09D16882F44CA20009C51A3 /* PBXTargetDependency */ = {
-			isa = PBXTargetDependency;
-			target = E09D166E2F44CA1E009C51A3 /* EXO-iOS */;
-			targetProxy = E09D16872F44CA20009C51A3 /* PBXContainerItemProxy */;
-		};
-/* End PBXTargetDependency section */
-
-/* Begin XCBuildConfiguration section */
-		E09D168E2F44CA20009C51A3 /* Debug */ = {
-			isa = XCBuildConfiguration;
-			buildSettings = {
-				ALWAYS_SEARCH_USER_PATHS = NO;
-				ASSETCATALOG_COMPILER_GENERATE_SWIFT_ASSET_SYMBOL_EXTENSIONS = YES;
-				CLANG_ANALYZER_NONNULL = YES;
-				CLANG_ANALYZER_NUMBER_OBJECT_CONVERSION = YES_AGGRESSIVE;
-				CLANG_CXX_LANGUAGE_STANDARD = "gnu++20";
-				CLANG_ENABLE_MODULES = YES;
-				CLANG_ENABLE_OBJC_ARC = YES;
-				CLANG_ENABLE_OBJC_WEAK = YES;
-				CLANG_WARN_BLOCK_CAPTURE_AUTORELEASING = YES;
-				CLANG_WARN_BOOL_CONVERSION = YES;
-				CLANG_WARN_COMMA = YES;
-				CLANG_WARN_CONSTANT_CONVERSION = YES;
-				CLANG_WARN_DEPRECATED_OBJC_IMPLEMENTATIONS = YES;
-				CLANG_WARN_DIRECT_OBJC_ISA_USAGE = YES_ERROR;
-				CLANG_WARN_DOCUMENTATION_COMMENTS = YES;
-				CLANG_WARN_EMPTY_BODY = YES;
-				CLANG_WARN_ENUM_CONVERSION = YES;
-				CLANG_WARN_INFINITE_RECURSION = YES;
-				CLANG_WARN_INT_CONVERSION = YES;
-				CLANG_WARN_NON_LITERAL_NULL_CONVERSION = YES;
-				CLANG_WARN_OBJC_IMPLICIT_RETAIN_SELF = YES;
-				CLANG_WARN_OBJC_LITERAL_CONVERSION = YES;
-				CLANG_WARN_OBJC_ROOT_CLASS = YES_ERROR;
-				CLANG_WARN_QUOTED_INCLUDE_IN_FRAMEWORK_HEADER = YES;
-				CLANG_WARN_RANGE_LOOP_ANALYSIS = YES;
-				CLANG_WARN_STRICT_PROTOTYPES = YES;
-				CLANG_WARN_SUSPICIOUS_MOVE = YES;
-				CLANG_WARN_UNGUARDED_AVAILABILITY = YES_AGGRESSIVE;
-				CLANG_WARN_UNREACHABLE_CODE = YES;
-				CLANG_WARN__DUPLICATE_METHOD_MATCH = YES;
-				COPY_PHASE_STRIP = NO;
-				DEBUG_INFORMATION_FORMAT = dwarf;
-				ENABLE_STRICT_OBJC_MSGSEND = YES;
-				ENABLE_TESTABILITY = YES;
-				ENABLE_USER_SCRIPT_SANDBOXING = YES;
-				GCC_C_LANGUAGE_STANDARD = gnu17;
-				GCC_DYNAMIC_NO_PIC = NO;
-				GCC_NO_COMMON_BLOCKS = YES;
-				GCC_OPTIMIZATION_LEVEL = 0;
-				GCC_PREPROCESSOR_DEFINITIONS = (
-					"DEBUG=1",
-					"$(inherited)",
-				);
-				GCC_WARN_64_TO_32_BIT_CONVERSION = YES;
-				GCC_WARN_ABOUT_RETURN_TYPE = YES_ERROR;
-				GCC_WARN_UNDECLARED_SELECTOR = YES;
-				GCC_WARN_UNINITIALIZED_AUTOS = YES_AGGRESSIVE;
-				GCC_WARN_UNUSED_FUNCTION = YES;
-				GCC_WARN_UNUSED_VARIABLE = YES;
-				IPHONEOS_DEPLOYMENT_TARGET = 26.2;
-				LOCALIZATION_PREFERS_STRING_CATALOGS = YES;
-				MTL_ENABLE_DEBUG_INFO = INCLUDE_SOURCE;
-				MTL_FAST_MATH = YES;
-				ONLY_ACTIVE_ARCH = YES;
-				SDKROOT = iphoneos;
-				SWIFT_ACTIVE_COMPILATION_CONDITIONS = "DEBUG $(inherited)";
-				SWIFT_OPTIMIZATION_LEVEL = "-Onone";
-			};
-			name = Debug;
-		};
-		E09D168F2F44CA20009C51A3 /* Release */ = {
-			isa = XCBuildConfiguration;
-			buildSettings = {
-				ALWAYS_SEARCH_USER_PATHS = NO;
-				ASSETCATALOG_COMPILER_GENERATE_SWIFT_ASSET_SYMBOL_EXTENSIONS = YES;
-				CLANG_ANALYZER_NONNULL = YES;
-				CLANG_ANALYZER_NUMBER_OBJECT_CONVERSION = YES_AGGRESSIVE;
-				CLANG_CXX_LANGUAGE_STANDARD = "gnu++20";
-				CLANG_ENABLE_MODULES = YES;
-				CLANG_ENABLE_OBJC_ARC = YES;
-				CLANG_ENABLE_OBJC_WEAK = YES;
-				CLANG_WARN_BLOCK_CAPTURE_AUTORELEASING = YES;
-				CLANG_WARN_BOOL_CONVERSION = YES;
-				CLANG_WARN_COMMA = YES;
-				CLANG_WARN_CONSTANT_CONVERSION = YES;
-				CLANG_WARN_DEPRECATED_OBJC_IMPLEMENTATIONS = YES;
-				CLANG_WARN_DIRECT_OBJC_ISA_USAGE = YES_ERROR;
-				CLANG_WARN_DOCUMENTATION_COMMENTS = YES;
-				CLANG_WARN_EMPTY_BODY = YES;
-				CLANG_WARN_ENUM_CONVERSION = YES;
-				CLANG_WARN_INFINITE_RECURSION = YES;
-				CLANG_WARN_INT_CONVERSION = YES;
-				CLANG_WARN_NON_LITERAL_NULL_CONVERSION = YES;
-				CLANG_WARN_OBJC_IMPLICIT_RETAIN_SELF = YES;
-				CLANG_WARN_OBJC_LITERAL_CONVERSION = YES;
-				CLANG_WARN_OBJC_ROOT_CLASS = YES_ERROR;
-				CLANG_WARN_QUOTED_INCLUDE_IN_FRAMEWORK_HEADER = YES;
-				CLANG_WARN_RANGE_LOOP_ANALYSIS = YES;
-				CLANG_WARN_STRICT_PROTOTYPES = YES;
-				CLANG_WARN_SUSPICIOUS_MOVE = YES;
-				CLANG_WARN_UNGUARDED_AVAILABILITY = YES_AGGRESSIVE;
-				CLANG_WARN_UNREACHABLE_CODE = YES;
-				CLANG_WARN__DUPLICATE_METHOD_MATCH = YES;
-				COPY_PHASE_STRIP = NO;
-				DEBUG_INFORMATION_FORMAT = "dwarf-with-dsym";
-				ENABLE_NS_ASSERTIONS = NO;
-				ENABLE_STRICT_OBJC_MSGSEND = YES;
-				ENABLE_USER_SCRIPT_SANDBOXING = YES;
-				GCC_C_LANGUAGE_STANDARD = gnu17;
-				GCC_NO_COMMON_BLOCKS = YES;
-				GCC_WARN_64_TO_32_BIT_CONVERSION = YES;
-				GCC_WARN_ABOUT_RETURN_TYPE = YES_ERROR;
-				GCC_WARN_UNDECLARED_SELECTOR = YES;
-				GCC_WARN_UNINITIALIZED_AUTOS = YES_AGGRESSIVE;
-				GCC_WARN_UNUSED_FUNCTION = YES;
-				GCC_WARN_UNUSED_VARIABLE = YES;
-				IPHONEOS_DEPLOYMENT_TARGET = 26.2;
-				LOCALIZATION_PREFERS_STRING_CATALOGS = YES;
-				MTL_ENABLE_DEBUG_INFO = NO;
-				MTL_FAST_MATH = YES;
-				SDKROOT = iphoneos;
-				SWIFT_COMPILATION_MODE = wholemodule;
-				VALIDATE_PRODUCT = YES;
-			};
-			name = Release;
-		};
-		E09D16912F44CA20009C51A3 /* Debug */ = {
-			isa = XCBuildConfiguration;
-			buildSettings = {
-				ASSETCATALOG_COMPILER_APPICON_NAME = AppIcon;
-				ASSETCATALOG_COMPILER_GLOBAL_ACCENT_COLOR_NAME = AccentColor;
-				CODE_SIGN_STYLE = Automatic;
-				CURRENT_PROJECT_VERSION = 1;
-				DEVELOPMENT_TEAM = 3M3M67U93M;
-				ENABLE_PREVIEWS = YES;
-				GENERATE_INFOPLIST_FILE = YES;
-				INFOPLIST_FILE = "EXO-iOS/Info.plist";
-				INFOPLIST_KEY_UIApplicationSceneManifest_Generation = YES;
-				INFOPLIST_KEY_UIApplicationSupportsIndirectInputEvents = YES;
-				INFOPLIST_KEY_UILaunchScreen_Generation = YES;
-				INFOPLIST_KEY_UISupportedInterfaceOrientations_iPad = "UIInterfaceOrientationPortrait UIInterfaceOrientationPortraitUpsideDown UIInterfaceOrientationLandscapeLeft UIInterfaceOrientationLandscapeRight";
-				INFOPLIST_KEY_UISupportedInterfaceOrientations_iPhone = "UIInterfaceOrientationPortrait UIInterfaceOrientationLandscapeLeft UIInterfaceOrientationLandscapeRight";
-				LD_RUNPATH_SEARCH_PATHS = (
-					"$(inherited)",
-					"@executable_path/Frameworks",
-				);
-				MARKETING_VERSION = 1.0;
-				PRODUCT_BUNDLE_IDENTIFIER = "com.exo.EXO-iOS";
-				PRODUCT_NAME = "$(TARGET_NAME)";
-				STRING_CATALOG_GENERATE_SYMBOLS = YES;
-				SWIFT_APPROACHABLE_CONCURRENCY = YES;
-				SWIFT_DEFAULT_ACTOR_ISOLATION = MainActor;
-				SWIFT_EMIT_LOC_STRINGS = YES;
-				SWIFT_UPCOMING_FEATURE_MEMBER_IMPORT_VISIBILITY = YES;
-				SWIFT_VERSION = 5.0;
-				TARGETED_DEVICE_FAMILY = "1,2";
-			};
-			name = Debug;
-		};
-		E09D16922F44CA20009C51A3 /* Release */ = {
-			isa = XCBuildConfiguration;
-			buildSettings = {
-				ASSETCATALOG_COMPILER_APPICON_NAME = AppIcon;
-				ASSETCATALOG_COMPILER_GLOBAL_ACCENT_COLOR_NAME = AccentColor;
-				CODE_SIGN_STYLE = Automatic;
-				CURRENT_PROJECT_VERSION = 1;
-				DEVELOPMENT_TEAM = 3M3M67U93M;
-				ENABLE_PREVIEWS = YES;
-				GENERATE_INFOPLIST_FILE = YES;
-				INFOPLIST_FILE = "EXO-iOS/Info.plist";
-				INFOPLIST_KEY_UIApplicationSceneManifest_Generation = YES;
-				INFOPLIST_KEY_UIApplicationSupportsIndirectInputEvents = YES;
-				INFOPLIST_KEY_UILaunchScreen_Generation = YES;
-				INFOPLIST_KEY_UISupportedInterfaceOrientations_iPad = "UIInterfaceOrientationPortrait UIInterfaceOrientationPortraitUpsideDown UIInterfaceOrientationLandscapeLeft UIInterfaceOrientationLandscapeRight";
-				INFOPLIST_KEY_UISupportedInterfaceOrientations_iPhone = "UIInterfaceOrientationPortrait UIInterfaceOrientationLandscapeLeft UIInterfaceOrientationLandscapeRight";
-				LD_RUNPATH_SEARCH_PATHS = (
-					"$(inherited)",
-					"@executable_path/Frameworks",
-				);
-				MARKETING_VERSION = 1.0;
-				PRODUCT_BUNDLE_IDENTIFIER = "com.exo.EXO-iOS";
-				PRODUCT_NAME = "$(TARGET_NAME)";
-				STRING_CATALOG_GENERATE_SYMBOLS = YES;
-				SWIFT_APPROACHABLE_CONCURRENCY = YES;
-				SWIFT_DEFAULT_ACTOR_ISOLATION = MainActor;
-				SWIFT_EMIT_LOC_STRINGS = YES;
-				SWIFT_UPCOMING_FEATURE_MEMBER_IMPORT_VISIBILITY = YES;
-				SWIFT_VERSION = 5.0;
-				TARGETED_DEVICE_FAMILY = "1,2";
-			};
-			name = Release;
-		};
-		E09D16942F44CA20009C51A3 /* Debug */ = {
-			isa = XCBuildConfiguration;
-			buildSettings = {
-				BUNDLE_LOADER = "$(TEST_HOST)";
-				CODE_SIGN_STYLE = Automatic;
-				CURRENT_PROJECT_VERSION = 1;
-				GENERATE_INFOPLIST_FILE = YES;
-				IPHONEOS_DEPLOYMENT_TARGET = 26.2;
-				MARKETING_VERSION = 1.0;
-				PRODUCT_BUNDLE_IDENTIFIER = "com.exo.EXO-iOSTests";
-				PRODUCT_NAME = "$(TARGET_NAME)";
-				STRING_CATALOG_GENERATE_SYMBOLS = NO;
-				SWIFT_APPROACHABLE_CONCURRENCY = YES;
-				SWIFT_EMIT_LOC_STRINGS = NO;
-				SWIFT_UPCOMING_FEATURE_MEMBER_IMPORT_VISIBILITY = YES;
-				SWIFT_VERSION = 5.0;
-				TARGETED_DEVICE_FAMILY = "1,2";
-				TEST_HOST = "$(BUILT_PRODUCTS_DIR)/EXO-iOS.app/$(BUNDLE_EXECUTABLE_FOLDER_PATH)/EXO-iOS";
-			};
-			name = Debug;
-		};
-		E09D16952F44CA20009C51A3 /* Release */ = {
-			isa = XCBuildConfiguration;
-			buildSettings = {
-				BUNDLE_LOADER = "$(TEST_HOST)";
-				CODE_SIGN_STYLE = Automatic;
-				CURRENT_PROJECT_VERSION = 1;
-				GENERATE_INFOPLIST_FILE = YES;
-				IPHONEOS_DEPLOYMENT_TARGET = 26.2;
-				MARKETING_VERSION = 1.0;
-				PRODUCT_BUNDLE_IDENTIFIER = "com.exo.EXO-iOSTests";
-				PRODUCT_NAME = "$(TARGET_NAME)";
-				STRING_CATALOG_GENERATE_SYMBOLS = NO;
-				SWIFT_APPROACHABLE_CONCURRENCY = YES;
-				SWIFT_EMIT_LOC_STRINGS = NO;
-				SWIFT_UPCOMING_FEATURE_MEMBER_IMPORT_VISIBILITY = YES;
-				SWIFT_VERSION = 5.0;
-				TARGETED_DEVICE_FAMILY = "1,2";
-				TEST_HOST = "$(BUILT_PRODUCTS_DIR)/EXO-iOS.app/$(BUNDLE_EXECUTABLE_FOLDER_PATH)/EXO-iOS";
-			};
-			name = Release;
-		};
-		E09D16972F44CA20009C51A3 /* Debug */ = {
-			isa = XCBuildConfiguration;
-			buildSettings = {
-				CODE_SIGN_STYLE = Automatic;
-				CURRENT_PROJECT_VERSION = 1;
-				GENERATE_INFOPLIST_FILE = YES;
-				MARKETING_VERSION = 1.0;
-				PRODUCT_BUNDLE_IDENTIFIER = "com.exo.EXO-iOSUITests";
-				PRODUCT_NAME = "$(TARGET_NAME)";
-				STRING_CATALOG_GENERATE_SYMBOLS = NO;
-				SWIFT_APPROACHABLE_CONCURRENCY = YES;
-				SWIFT_EMIT_LOC_STRINGS = NO;
-				SWIFT_UPCOMING_FEATURE_MEMBER_IMPORT_VISIBILITY = YES;
-				SWIFT_VERSION = 5.0;
-				TARGETED_DEVICE_FAMILY = "1,2";
-				TEST_TARGET_NAME = "EXO-iOS";
-			};
-			name = Debug;
-		};
-		E09D16982F44CA20009C51A3 /* Release */ = {
-			isa = XCBuildConfiguration;
-			buildSettings = {
-				CODE_SIGN_STYLE = Automatic;
-				CURRENT_PROJECT_VERSION = 1;
-				GENERATE_INFOPLIST_FILE = YES;
-				MARKETING_VERSION = 1.0;
-				PRODUCT_BUNDLE_IDENTIFIER = "com.exo.EXO-iOSUITests";
-				PRODUCT_NAME = "$(TARGET_NAME)";
-				STRING_CATALOG_GENERATE_SYMBOLS = NO;
-				SWIFT_APPROACHABLE_CONCURRENCY = YES;
-				SWIFT_EMIT_LOC_STRINGS = NO;
-				SWIFT_UPCOMING_FEATURE_MEMBER_IMPORT_VISIBILITY = YES;
-				SWIFT_VERSION = 5.0;
-				TARGETED_DEVICE_FAMILY = "1,2";
-				TEST_TARGET_NAME = "EXO-iOS";
-			};
-			name = Release;
-		};
-/* End XCBuildConfiguration section */
-
-/* Begin XCConfigurationList section */
-		E09D166A2F44CA1E009C51A3 /* Build configuration list for PBXProject "EXO-iOS" */ = {
-			isa = XCConfigurationList;
-			buildConfigurations = (
-				E09D168E2F44CA20009C51A3 /* Debug */,
-				E09D168F2F44CA20009C51A3 /* Release */,
-			);
-			defaultConfigurationIsVisible = 0;
-			defaultConfigurationName = Release;
-		};
-		E09D16902F44CA20009C51A3 /* Build configuration list for PBXNativeTarget "EXO-iOS" */ = {
-			isa = XCConfigurationList;
-			buildConfigurations = (
-				E09D16912F44CA20009C51A3 /* Debug */,
-				E09D16922F44CA20009C51A3 /* Release */,
-			);
-			defaultConfigurationIsVisible = 0;
-			defaultConfigurationName = Release;
-		};
-		E09D16932F44CA20009C51A3 /* Build configuration list for PBXNativeTarget "EXO-iOSTests" */ = {
-			isa = XCConfigurationList;
-			buildConfigurations = (
-				E09D16942F44CA20009C51A3 /* Debug */,
-				E09D16952F44CA20009C51A3 /* Release */,
-			);
-			defaultConfigurationIsVisible = 0;
-			defaultConfigurationName = Release;
-		};
-		E09D16962F44CA20009C51A3 /* Build configuration list for PBXNativeTarget "EXO-iOSUITests" */ = {
-			isa = XCConfigurationList;
-			buildConfigurations = (
-				E09D16972F44CA20009C51A3 /* Debug */,
-				E09D16982F44CA20009C51A3 /* Release */,
-			);
-			defaultConfigurationIsVisible = 0;
-			defaultConfigurationName = Release;
-		};
-/* End XCConfigurationList section */
-
-/* Begin XCRemoteSwiftPackageReference section */
-		E09D17502F44F359009C51A3 /* XCRemoteSwiftPackageReference "mlx-swift-lm" */ = {
-			isa = XCRemoteSwiftPackageReference;
-			repositoryURL = "https://github.com/ml-explore/mlx-swift-lm";
-			requirement = {
-				kind = upToNextMajorVersion;
-				minimumVersion = 2.30.3;
-			};
-		};
-/* End XCRemoteSwiftPackageReference section */
-
-/* Begin XCSwiftPackageProductDependency section */
-		E09D17512F44F359009C51A3 /* MLXLLM */ = {
-			isa = XCSwiftPackageProductDependency;
-			package = E09D17502F44F359009C51A3 /* XCRemoteSwiftPackageReference "mlx-swift-lm" */;
-			productName = MLXLLM;
-		};
-		E09D17532F44F359009C51A3 /* MLXLMCommon */ = {
-			isa = XCSwiftPackageProductDependency;
-			package = E09D17502F44F359009C51A3 /* XCRemoteSwiftPackageReference "mlx-swift-lm" */;
-			productName = MLXLMCommon;
-		};
-/* End XCSwiftPackageProductDependency section */
-	};
-	rootObject = E09D16672F44CA1E009C51A3 /* Project object */;
-}
@@ -1,7 +0,0 @@
-<?xml version="1.0" encoding="UTF-8"?>
-<Workspace
-   version = "1.0">
-   <FileRef
-      location = "self:">
-   </FileRef>
-</Workspace>
@@ -1,60 +0,0 @@
-{
-  "originHash" : "facc0ac7c70363ea20f6cd1235de91dea6b06f0d00190946045a6c8ae753abc2",
-  "pins" : [
-    {
-      "identity" : "mlx-swift",
-      "kind" : "remoteSourceControl",
-      "location" : "https://github.com/ml-explore/mlx-swift",
-      "state" : {
-        "revision" : "6ba4827fb82c97d012eec9ab4b2de21f85c3b33d",
-        "version" : "0.30.6"
-      }
-    },
-    {
-      "identity" : "mlx-swift-lm",
-      "kind" : "remoteSourceControl",
-      "location" : "https://github.com/ml-explore/mlx-swift-lm",
-      "state" : {
-        "revision" : "360c5052b81cc154b04ee0933597a4ad6db4b8ae",
-        "version" : "2.30.3"
-      }
-    },
-    {
-      "identity" : "swift-collections",
-      "kind" : "remoteSourceControl",
-      "location" : "https://github.com/apple/swift-collections.git",
-      "state" : {
-        "revision" : "7b847a3b7008b2dc2f47ca3110d8c782fb2e5c7e",
-        "version" : "1.3.0"
-      }
-    },
-    {
-      "identity" : "swift-jinja",
-      "kind" : "remoteSourceControl",
-      "location" : "https://github.com/huggingface/swift-jinja.git",
-      "state" : {
-        "revision" : "d81197f35f41445bc10e94600795e68c6f5e94b0",
-        "version" : "2.3.1"
-      }
-    },
-    {
-      "identity" : "swift-numerics",
-      "kind" : "remoteSourceControl",
-      "location" : "https://github.com/apple/swift-numerics",
-      "state" : {
-        "revision" : "0c0290ff6b24942dadb83a929ffaaa1481df04a2",
-        "version" : "1.1.1"
-      }
-    },
-    {
-      "identity" : "swift-transformers",
-      "kind" : "remoteSourceControl",
-      "location" : "https://github.com/huggingface/swift-transformers",
-      "state" : {
-        "revision" : "573e5c9036c2f136b3a8a071da8e8907322403d0",
-        "version" : "1.1.6"
-      }
-    }
-  ],
-  "version" : 3
-}
@@ -1,20 +0,0 @@
-{
-  "colors" : [
-    {
-      "color" : {
-        "color-space" : "srgb",
-        "components" : {
-          "alpha" : "1.000",
-          "blue" : "0x00",
-          "green" : "0xD7",
-          "red" : "0xFF"
-        }
-      },
-      "idiom" : "universal"
-    }
-  ],
-  "info" : {
-    "author" : "xcode",
-    "version" : 1
-  }
-}
@@ -1,38 +0,0 @@
-{
-  "images" : [
-    {
-      "filename" : "AppIcon.png",
-      "idiom" : "universal",
-      "platform" : "ios",
-      "size" : "1024x1024"
-    },
-    {
-      "appearances" : [
-        {
-          "appearance" : "luminosity",
-          "value" : "dark"
-        }
-      ],
-      "filename" : "AppIcon.png",
-      "idiom" : "universal",
-      "platform" : "ios",
-      "size" : "1024x1024"
-    },
-    {
-      "appearances" : [
-        {
-          "appearance" : "luminosity",
-          "value" : "tinted"
-        }
-      ],
-      "filename" : "AppIcon.png",
-      "idiom" : "universal",
-      "platform" : "ios",
-      "size" : "1024x1024"
-    }
-  ],
-  "info" : {
-    "author" : "xcode",
-    "version" : 1
-  }
-}
@@ -1,6 +0,0 @@
-{
-  "info" : {
-    "author" : "xcode",
-    "version" : 1
-  }
-}
@@ -1,21 +0,0 @@
-{
-  "images" : [
-    {
-      "filename" : "exo-logo.png",
-      "idiom" : "universal",
-      "scale" : "1x"
-    },
-    {
-      "idiom" : "universal",
-      "scale" : "2x"
-    },
-    {
-      "idiom" : "universal",
-      "scale" : "3x"
-    }
-  ],
-  "info" : {
-    "author" : "xcode",
-    "version" : 1
-  }
-}
@@ -1,8 +0,0 @@
-<?xml version="1.0" encoding="UTF-8"?>
-<!DOCTYPE plist PUBLIC "-//Apple//DTD PLIST 1.0//EN" "http://www.apple.com/DTDs/PropertyList-1.0.dtd">
-<plist version="1.0">
-<dict>
-	<key>com.apple.developer.kernel.increased-memory-limit</key>
-	<true/>
-</dict>
-</plist>
@@ -1,67 +0,0 @@
-import SwiftUI
-import UIKit
-
-@main
-struct EXO_iOSApp: App {
-    @State private var clusterService = ClusterService()
-    @State private var discoveryService = DiscoveryService()
-    @State private var localInferenceService = LocalInferenceService()
-    @State private var chatService: ChatService?
-
-    init() {
-        let darkGray = UIColor(red: 0x1F / 255.0, green: 0x1F / 255.0, blue: 0x1F / 255.0, alpha: 1)
-        let yellow = UIColor(red: 0xFF / 255.0, green: 0xD7 / 255.0, blue: 0x00 / 255.0, alpha: 1)
-
-        let navAppearance = UINavigationBarAppearance()
-        navAppearance.configureWithOpaqueBackground()
-        navAppearance.backgroundColor = darkGray
-        navAppearance.titleTextAttributes = [
-            .foregroundColor: yellow,
-            .font: UIFont.monospacedSystemFont(ofSize: 17, weight: .semibold),
-        ]
-        navAppearance.largeTitleTextAttributes = [
-            .foregroundColor: yellow,
-            .font: UIFont.monospacedSystemFont(ofSize: 34, weight: .bold),
-        ]
-
-        UINavigationBar.appearance().standardAppearance = navAppearance
-        UINavigationBar.appearance().compactAppearance = navAppearance
-        UINavigationBar.appearance().scrollEdgeAppearance = navAppearance
-        UINavigationBar.appearance().tintColor = yellow
-    }
-
-    var body: some Scene {
-        WindowGroup {
-            if let chatService {
-                RootView()
-                    .environment(clusterService)
-                    .environment(discoveryService)
-                    .environment(chatService)
-                    .environment(localInferenceService)
-                    .preferredColorScheme(.dark)
-                    .task {
-                        await clusterService.attemptAutoReconnect()
-                        discoveryService.startBrowsing()
-                        await localInferenceService.prepareModel()
-                    }
-                    .onChange(of: discoveryService.discoveredClusters) { _, clusters in
-                        guard !clusterService.isConnected,
-                            case .disconnected = clusterService.connectionState,
-                            let first = clusters.first
-                        else { return }
-                        Task {
-                            await clusterService.connectToDiscoveredCluster(
-                                first, using: discoveryService)
-                        }
-                    }
-            } else {
-                Color.exoBlack.onAppear {
-                    chatService = ChatService(
-                        clusterService: clusterService,
-                        localInferenceService: localInferenceService
-                    )
-                }
-            }
-        }
-    }
-}
@@ -1,19 +0,0 @@
-<?xml version="1.0" encoding="UTF-8"?>
-<!DOCTYPE plist PUBLIC "-//Apple//DTD PLIST 1.0//EN" "http://www.apple.com/DTDs/PropertyList-1.0.dtd">
-<plist version="1.0">
-<dict>
-	<key>UIUserInterfaceStyle</key>
-	<string>Dark</string>
-	<key>CFBundleDisplayName</key>
-	<string>EXO</string>
-	<key>NSLocalNetworkUsageDescription</key>
-	<string>EXO needs local network access to connect to your EXO cluster.</string>
-	<key>NSBonjourServices</key>
-	<array>
-		<string>_exo._tcp</string>
-		<string>_p2p._tcp</string>
-		<string>_p2p._udp</string>
-		<string>_libp2p._udp</string>
-	</array>
-</dict>
-</plist>
@@ -1,129 +0,0 @@
-import Foundation
-
-// MARK: - Request
-
-struct ChatCompletionRequest: Encodable {
-    let model: String
-    let messages: [ChatCompletionMessageParam]
-    let stream: Bool
-    let maxTokens: Int?
-    let temperature: Double?
-
-    enum CodingKeys: String, CodingKey {
-        case model, messages, stream, temperature
-        case maxTokens = "max_tokens"
-    }
-}
-
-struct ChatCompletionMessageParam: Encodable {
-    let role: String
-    let content: String
-}
-
-// MARK: - Streaming Response
-
-struct ChatCompletionChunk: Decodable {
-    let id: String
-    let model: String?
-    let choices: [StreamingChoice]
-    let usage: ChunkUsage?
-
-    init(id: String, model: String?, choices: [StreamingChoice], usage: ChunkUsage?) {
-        self.id = id
-        self.model = model
-        self.choices = choices
-        self.usage = usage
-    }
-}
-
-struct StreamingChoice: Decodable {
-    let index: Int
-    let delta: Delta
-    let finishReason: String?
-
-    enum CodingKeys: String, CodingKey {
-        case index, delta
-        case finishReason = "finish_reason"
-    }
-
-    init(index: Int, delta: Delta, finishReason: String?) {
-        self.index = index
-        self.delta = delta
-        self.finishReason = finishReason
-    }
-}
-
-struct Delta: Decodable {
-    let role: String?
-    let content: String?
-
-    init(role: String?, content: String?) {
-        self.role = role
-        self.content = content
-    }
-}
-
-struct ChunkUsage: Decodable {
-    let promptTokens: Int?
-    let completionTokens: Int?
-    let totalTokens: Int?
-
-    enum CodingKeys: String, CodingKey {
-        case promptTokens = "prompt_tokens"
-        case completionTokens = "completion_tokens"
-        case totalTokens = "total_tokens"
-    }
-
-    init(promptTokens: Int?, completionTokens: Int?, totalTokens: Int?) {
-        self.promptTokens = promptTokens
-        self.completionTokens = completionTokens
-        self.totalTokens = totalTokens
-    }
-}
-
-// MARK: - Non-Streaming Response
-
-struct ChatCompletionResponse: Decodable {
-    let id: String
-    let model: String?
-    let choices: [ResponseChoice]
-}
-
-struct ResponseChoice: Decodable {
-    let index: Int
-    let message: ResponseMessage
-    let finishReason: String?
-
-    enum CodingKeys: String, CodingKey {
-        case index, message
-        case finishReason = "finish_reason"
-    }
-}
-
-struct ResponseMessage: Decodable {
-    let role: String?
-    let content: String?
-}
-
-// MARK: - Models List
-
-struct ModelListResponse: Decodable {
-    let data: [ModelInfo]
-}
-
-struct ModelInfo: Decodable, Identifiable {
-    let id: String
-    let name: String?
-}
-
-// MARK: - Error
-
-struct APIErrorResponse: Decodable {
-    let error: APIErrorInfo
-}
-
-struct APIErrorInfo: Decodable {
-    let message: String
-    let type: String?
-    let code: Int?
-}
@@ -1,26 +0,0 @@
-import Foundation
-
-struct ChatMessage: Identifiable, Equatable {
-    let id: UUID
-    let role: Role
-    var content: String
-    let timestamp: Date
-    var isStreaming: Bool
-
-    enum Role: String, Codable {
-        case user
-        case assistant
-        case system
-    }
-
-    init(
-        id: UUID = UUID(), role: Role, content: String, timestamp: Date = Date(),
-        isStreaming: Bool = false
-    ) {
-        self.id = id
-        self.role = role
-        self.content = content
-        self.timestamp = timestamp
-        self.isStreaming = isStreaming
-    }
-}
@@ -1,11 +0,0 @@
-import Foundation
-
-struct ConnectionInfo: Codable, Equatable {
-    let host: String
-    let port: Int
-    let nodeId: String?
-
-    var baseURL: URL { URL(string: "http://\(host):\(port)")! }
-
-    static let defaultPort = 52415
-}
@@ -1,34 +0,0 @@
-import Foundation
-
-struct Conversation: Identifiable, Codable, Equatable {
-    let id: UUID
-    var title: String
-    var messages: [StoredMessage]
-    var modelId: String?
-    let createdAt: Date
-
-    init(
-        id: UUID = UUID(), title: String = "New Chat", messages: [StoredMessage] = [],
-        modelId: String? = nil, createdAt: Date = Date()
-    ) {
-        self.id = id
-        self.title = title
-        self.messages = messages
-        self.modelId = modelId
-        self.createdAt = createdAt
-    }
-}
-
-struct StoredMessage: Identifiable, Codable, Equatable {
-    let id: UUID
-    let role: String
-    var content: String
-    let timestamp: Date
-
-    init(id: UUID = UUID(), role: String, content: String, timestamp: Date = Date()) {
-        self.id = id
-        self.role = role
-        self.content = content
-        self.timestamp = timestamp
-    }
-}
@@ -1,227 +0,0 @@
-import Foundation
-
-@Observable
-@MainActor
-final class ChatService {
-    var conversations: [Conversation] = []
-    var activeConversationId: UUID?
-    private(set) var isGenerating: Bool = false
-    private var currentGenerationTask: Task<Void, Never>?
-
-    private let clusterService: ClusterService
-    private let localInferenceService: LocalInferenceService
-
-    var canSendMessage: Bool {
-        clusterService.isConnected || localInferenceService.isAvailable
-    }
-
-    var activeConversation: Conversation? {
-        guard let id = activeConversationId else { return nil }
-        return conversations.first { $0.id == id }
-    }
-
-    var activeMessages: [ChatMessage] {
-        guard let conversation = activeConversation else { return [] }
-        return conversation.messages.map { stored in
-            ChatMessage(
-                id: stored.id,
-                role: ChatMessage.Role(rawValue: stored.role) ?? .user,
-                content: stored.content,
-                timestamp: stored.timestamp
-            )
-        }
-    }
-
-    init(clusterService: ClusterService, localInferenceService: LocalInferenceService) {
-        self.clusterService = clusterService
-        self.localInferenceService = localInferenceService
-        loadConversations()
-    }
-
-    // MARK: - Conversation Management
-
-    func createConversation(modelId: String? = nil) {
-        let conversation = Conversation(
-            modelId: modelId ?? clusterService.availableModels.first?.id)
-        conversations.insert(conversation, at: 0)
-        activeConversationId = conversation.id
-        saveConversations()
-    }
-
-    func deleteConversation(id: UUID) {
-        conversations.removeAll { $0.id == id }
-        if activeConversationId == id {
-            activeConversationId = conversations.first?.id
-        }
-        saveConversations()
-    }
-
-    func setActiveConversation(id: UUID) {
-        activeConversationId = id
-    }
-
-    func setModelForActiveConversation(_ modelId: String) {
-        guard let index = conversations.firstIndex(where: { $0.id == activeConversationId }) else {
-            return
-        }
-        conversations[index].modelId = modelId
-        saveConversations()
-    }
-
-    // MARK: - Messaging
-
-    func sendMessage(_ text: String) {
-        guard !text.trimmingCharacters(in: .whitespacesAndNewlines).isEmpty else { return }
-
-        if activeConversation == nil {
-            createConversation()
-        }
-
-        guard let index = conversations.firstIndex(where: { $0.id == activeConversationId }) else {
-            return
-        }
-
-        let userMessage = StoredMessage(role: "user", content: text)
-        conversations[index].messages.append(userMessage)
-
-        if conversations[index].title == "New Chat" {
-            let preview = String(text.prefix(40))
-            conversations[index].title = preview + (text.count > 40 ? "..." : "")
-        }
-
-        let modelId: String
-        if clusterService.isConnected {
-            guard
-                let clusterId = conversations[index].modelId
-                    ?? clusterService.availableModels.first?.id
-            else {
-                let errorMessage = StoredMessage(
-                    role: "assistant", content: "No model selected. Please select a model first.")
-                conversations[index].messages.append(errorMessage)
-                saveConversations()
-                return
-            }
-            modelId = clusterId
-        } else if localInferenceService.isAvailable {
-            modelId = localInferenceService.defaultModelId
-        } else {
-            let errorMessage = StoredMessage(
-                role: "assistant",
-                content: "Not connected to a cluster and local model is not available.")
-            conversations[index].messages.append(errorMessage)
-            saveConversations()
-            return
-        }
-
-        conversations[index].modelId = modelId
-
-        let assistantMessageId = UUID()
-        let assistantMessage = StoredMessage(
-            id: assistantMessageId, role: "assistant", content: "", timestamp: Date())
-        conversations[index].messages.append(assistantMessage)
-
-        let messagesForAPI = conversations[index].messages.dropLast().map { stored in
-            ChatCompletionMessageParam(role: stored.role, content: stored.content)
-        }
-
-        let request = ChatCompletionRequest(
-            model: modelId,
-            messages: Array(messagesForAPI),
-            stream: true,
-            maxTokens: 4096,
-            temperature: nil
-        )
-
-        let conversationId = conversations[index].id
-
-        isGenerating = true
-        currentGenerationTask = Task { [weak self] in
-            guard let self else { return }
-            await self.performStreaming(
-                request: request, conversationId: conversationId,
-                assistantMessageId: assistantMessageId)
-        }
-
-        saveConversations()
-    }
-
-    func cancelGeneration() {
-        currentGenerationTask?.cancel()
-        currentGenerationTask = nil
-        localInferenceService.cancelGeneration()
-        isGenerating = false
-    }
-
-    // MARK: - Streaming
-
-    private func performStreaming(
-        request: ChatCompletionRequest, conversationId: UUID, assistantMessageId: UUID
-    ) async {
-        defer {
-            isGenerating = false
-            currentGenerationTask = nil
-            saveConversations()
-        }
-
-        do {
-            let stream =
-                clusterService.isConnected
-                ? clusterService.streamChatCompletion(request: request)
-                : localInferenceService.streamChatCompletion(request: request)
-            for try await chunk in stream {
-                guard !Task.isCancelled else { return }
-                guard let content = chunk.choices.first?.delta.content, !content.isEmpty else {
-                    continue
-                }
-
-                if let convIndex = conversations.firstIndex(where: { $0.id == conversationId }),
-                    let msgIndex = conversations[convIndex].messages.firstIndex(where: {
-                        $0.id == assistantMessageId
-                    })
-                {
-                    conversations[convIndex].messages[msgIndex].content += content
-                }
-            }
-        } catch {
-            if !Task.isCancelled {
-                if let convIndex = conversations.firstIndex(where: { $0.id == conversationId }),
-                    let msgIndex = conversations[convIndex].messages.firstIndex(where: {
-                        $0.id == assistantMessageId
-                    })
-                {
-                    if conversations[convIndex].messages[msgIndex].content.isEmpty {
-                        conversations[convIndex].messages[msgIndex].content =
-                            "Error: \(error.localizedDescription)"
-                    }
-                }
-            }
-        }
-    }
-
-    // MARK: - Persistence
-
-    private static var storageURL: URL {
-        let documents = FileManager.default.urls(for: .documentDirectory, in: .userDomainMask)
-            .first!
-        return documents.appendingPathComponent("exo_conversations.json")
-    }
-
-    private func saveConversations() {
-        do {
-            let data = try JSONEncoder().encode(conversations)
-            try data.write(to: Self.storageURL, options: .atomic)
-        } catch {
-            // Save failed silently
-        }
-    }
-
-    private func loadConversations() {
-        do {
-            let data = try Data(contentsOf: Self.storageURL)
-            conversations = try JSONDecoder().decode([Conversation].self, from: data)
-            activeConversationId = conversations.first?.id
-        } catch {
-            conversations = []
-        }
-    }
-}
@@ -1,246 +0,0 @@
-import Foundation
-
-enum ConnectionState: Equatable {
-    case disconnected
-    case connecting
-    case connected(ConnectionInfo)
-}
-
-struct ModelOption: Identifiable, Equatable {
-    let id: String
-    let displayName: String
-}
-
-@Observable
-@MainActor
-final class ClusterService {
-    private(set) var connectionState: ConnectionState = .disconnected
-    private(set) var availableModels: [ModelOption] = []
-    private(set) var lastError: String?
-
-    private let session: URLSession
-    private let decoder: JSONDecoder
-    private var pollingTask: Task<Void, Never>?
-    private var heartbeatTask: Task<Void, Never>?
-
-    private static let connectionInfoKey = "exo_last_connection_info"
-
-    var isConnected: Bool {
-        if case .connected = connectionState { return true }
-        return false
-    }
-
-    var currentConnection: ConnectionInfo? {
-        if case .connected(let info) = connectionState { return info }
-        return nil
-    }
-
-    init(session: URLSession = .shared) {
-        self.session = session
-        let decoder = JSONDecoder()
-        self.decoder = decoder
-    }
-
-    // MARK: - Connection
-
-    func connect(to info: ConnectionInfo) async {
-        connectionState = .connecting
-        lastError = nil
-
-        do {
-            let url = info.baseURL.appendingPathComponent("node_id")
-            var request = URLRequest(url: url)
-            request.timeoutInterval = 5
-            request.cachePolicy = .reloadIgnoringLocalCacheData
-            let (_, response) = try await session.data(for: request)
-
-            guard let httpResponse = response as? HTTPURLResponse,
-                (200..<300).contains(httpResponse.statusCode)
-            else {
-                throw URLError(.badServerResponse)
-            }
-
-            connectionState = .connected(info)
-            persistConnection(info)
-            startPolling()
-            startHeartbeat()
-            await fetchModels(baseURL: info.baseURL)
-        } catch {
-            connectionState = .disconnected
-            lastError = "Could not connect to \(info.host):\(info.port)"
-        }
-    }
-
-    func connectToDiscoveredCluster(
-        _ cluster: DiscoveredCluster, using discoveryService: DiscoveryService
-    ) async {
-        guard case .disconnected = connectionState else { return }
-        connectionState = .connecting
-        lastError = nil
-
-        guard let info = await discoveryService.resolve(cluster) else {
-            connectionState = .disconnected
-            lastError = "Could not resolve \(cluster.name)"
-            return
-        }
-        connectionState = .disconnected  // reset so connect() can proceed
-        await connect(to: info)
-    }
-
-    func disconnect() {
-        stopPolling()
-        stopHeartbeat()
-        connectionState = .disconnected
-        availableModels = []
-        lastError = nil
-    }
-
-    func attemptAutoReconnect() async {
-        guard case .disconnected = connectionState,
-            let info = loadPersistedConnection()
-        else { return }
-        await connect(to: info)
-    }
-
-    // MARK: - Polling
-
-    private func startPolling(interval: TimeInterval = 2.0) {
-        stopPolling()
-        pollingTask = Task { [weak self] in
-            while !Task.isCancelled {
-                try? await Task.sleep(for: .seconds(interval))
-                guard let self, !Task.isCancelled else { return }
-                guard let connection = self.currentConnection else { return }
-                await self.fetchModels(baseURL: connection.baseURL)
-            }
-        }
-    }
-
-    private func stopPolling() {
-        pollingTask?.cancel()
-        pollingTask = nil
-    }
-
-    // MARK: - Heartbeat
-
-    private func startHeartbeat(interval: TimeInterval = 10.0) {
-        stopHeartbeat()
-        heartbeatTask = Task { [weak self] in
-            // Send immediately, then on interval
-            if let self, let connection = self.currentConnection {
-                await self.sendHeartbeat(baseURL: connection.baseURL)
-            }
-            while !Task.isCancelled {
-                try? await Task.sleep(for: .seconds(interval))
-                guard let self, !Task.isCancelled else { return }
-                guard let connection = self.currentConnection else { return }
-                await self.sendHeartbeat(baseURL: connection.baseURL)
-            }
-        }
-    }
-
-    private func stopHeartbeat() {
-        heartbeatTask?.cancel()
-        heartbeatTask = nil
-    }
-
-    private func sendHeartbeat(baseURL: URL) async {
-        do {
-            let deviceInfo = DeviceInfoService.gather()
-            let url = baseURL.appendingPathComponent("v1/lite_node/heartbeat")
-            var request = URLRequest(url: url)
-            request.httpMethod = "POST"
-            request.setValue("application/json", forHTTPHeaderField: "Content-Type")
-            request.timeoutInterval = 5
-            request.httpBody = try JSONEncoder().encode(deviceInfo)
-            let (_, response) = try await session.data(for: request)
-
-            if let httpResponse = response as? HTTPURLResponse,
-               !(200..<300).contains(httpResponse.statusCode) {
-                // Heartbeat failed silently — will retry on next interval
-            }
-        } catch {
-            // Heartbeat failed silently — will retry on next interval
-        }
-    }
-
-    // MARK: - API
-
-    private func fetchModels(baseURL: URL) async {
-        do {
-            let url = baseURL.appendingPathComponent("models")
-            var request = URLRequest(url: url)
-            request.cachePolicy = .reloadIgnoringLocalCacheData
-            let (data, response) = try await session.data(for: request)
-
-            guard let httpResponse = response as? HTTPURLResponse,
-                (200..<300).contains(httpResponse.statusCode)
-            else { return }
-
-            let list = try decoder.decode(ModelListResponse.self, from: data)
-            availableModels = list.data.map {
-                ModelOption(id: $0.id, displayName: $0.name ?? $0.id)
-            }
-        } catch {
-            // Models fetch failed silently — will retry on next poll
-        }
-    }
-
-    func streamChatCompletion(request body: ChatCompletionRequest) -> AsyncThrowingStream<
-        ChatCompletionChunk, Error
-    > {
-        AsyncThrowingStream { continuation in
-            let task = Task { [weak self] in
-                guard let self, let connection = self.currentConnection else {
-                    continuation.finish(throwing: URLError(.notConnectedToInternet))
-                    return
-                }
-
-                do {
-                    let url = connection.baseURL.appendingPathComponent("v1/chat/completions")
-                    var request = URLRequest(url: url)
-                    request.httpMethod = "POST"
-                    request.setValue("application/json", forHTTPHeaderField: "Content-Type")
-                    request.httpBody = try JSONEncoder().encode(body)
-
-                    let (bytes, response) = try await self.session.bytes(for: request)
-
-                    guard let httpResponse = response as? HTTPURLResponse,
-                        (200..<300).contains(httpResponse.statusCode)
-                    else {
-                        continuation.finish(throwing: URLError(.badServerResponse))
-                        return
-                    }
-
-                    let parser = SSEStreamParser<ChatCompletionChunk>(
-                        bytes: bytes, decoder: self.decoder)
-                    for try await chunk in parser {
-                        continuation.yield(chunk)
-                    }
-                    continuation.finish()
-                } catch {
-                    continuation.finish(throwing: error)
-                }
-            }
-
-            continuation.onTermination = { _ in
-                task.cancel()
-            }
-        }
-    }
-
-    // MARK: - Persistence
-
-    private func persistConnection(_ info: ConnectionInfo) {
-        if let data = try? JSONEncoder().encode(info) {
-            UserDefaults.standard.set(data, forKey: Self.connectionInfoKey)
-        }
-    }
-
-    private func loadPersistedConnection() -> ConnectionInfo? {
-        guard let data = UserDefaults.standard.data(forKey: Self.connectionInfoKey) else {
-            return nil
-        }
-        return try? JSONDecoder().decode(ConnectionInfo.self, from: data)
-    }
-}
@@ -1,115 +0,0 @@
-import Foundation
-import os
-import UIKit
-
-struct DeviceInfo: Encodable {
-    let nodeId: String
-    let model: String
-    let chip: String
-    let osVersion: String
-    let friendlyName: String
-    let ramTotal: Int
-    let ramAvailable: Int
-
-    enum CodingKeys: String, CodingKey {
-        case nodeId = "node_id"
-        case model
-        case chip
-        case osVersion = "os_version"
-        case friendlyName = "friendly_name"
-        case ramTotal = "ram_total"
-        case ramAvailable = "ram_available"
-    }
-}
-
-enum DeviceInfoService {
-    private static let liteNodeIdKey = "exo_lite_node_id"
-
-    static var liteNodeId: String {
-        if let existing = UserDefaults.standard.string(forKey: liteNodeIdKey) {
-            return existing
-        }
-        let newId = UUID().uuidString.lowercased()
-        UserDefaults.standard.set(newId, forKey: liteNodeIdKey)
-        return newId
-    }
-
-    static func gather() -> DeviceInfo {
-        let model = modelName()
-        let chip = chipName(for: model)
-
-        let totalRam = Int(ProcessInfo.processInfo.physicalMemory)
-        let availableRam = availableMemory()
-
-        return DeviceInfo(
-            nodeId: liteNodeId,
-            model: model,
-            chip: chip,
-            osVersion: UIDevice.current.systemVersion,
-            friendlyName: UIDevice.current.name,
-            ramTotal: totalRam,
-            ramAvailable: availableRam
-        )
-    }
-
-    // MARK: - Private
-
-    private static func modelName() -> String {
-        var systemInfo = utsname()
-        uname(&systemInfo)
-        let machine = withUnsafePointer(to: &systemInfo.machine) {
-            $0.withMemoryRebound(to: CChar.self, capacity: 1) {
-                String(cString: $0)
-            }
-        }
-        return modelMapping[machine] ?? machine
-    }
-
-    private static func chipName(for model: String) -> String {
-        let lower = model.lowercased()
-        if lower.contains("iphone 16 pro") || lower.contains("iphone 16 pro max") {
-            return "Apple A18 Pro"
-        } else if lower.contains("iphone 16") {
-            return "Apple A18"
-        } else if lower.contains("iphone 15 pro") || lower.contains("iphone 15 pro max") {
-            return "Apple A17 Pro"
-        } else if lower.contains("iphone 15") {
-            return "Apple A16 Bionic"
-        } else if lower.contains("iphone 14 pro") || lower.contains("iphone 14 pro max") {
-            return "Apple A16 Bionic"
-        } else if lower.contains("iphone 14") {
-            return "Apple A15 Bionic"
-        }
-        return "Apple Silicon"
-    }
-
-    private static func availableMemory() -> Int {
-        return Int(os_proc_available_memory())
-    }
-
-    private static let modelMapping: [String: String] = [
-        // iPhone 16 series
-        "iPhone17,1": "iPhone 16 Pro",
-        "iPhone17,2": "iPhone 16 Pro Max",
-        "iPhone17,3": "iPhone 16",
-        "iPhone17,4": "iPhone 16 Plus",
-        // iPhone 15 series
-        "iPhone16,1": "iPhone 15 Pro",
-        "iPhone16,2": "iPhone 15 Pro Max",
-        "iPhone15,4": "iPhone 15",
-        "iPhone15,5": "iPhone 15 Plus",
-        // iPhone 14 series
-        "iPhone15,2": "iPhone 14 Pro",
-        "iPhone15,3": "iPhone 14 Pro Max",
-        "iPhone14,7": "iPhone 14",
-        "iPhone14,8": "iPhone 14 Plus",
-        // iPhone 13 series
-        "iPhone14,2": "iPhone 13 Pro",
-        "iPhone14,3": "iPhone 13 Pro Max",
-        "iPhone14,5": "iPhone 13",
-        "iPhone14,4": "iPhone 13 mini",
-        // Simulator
-        "arm64": "iPhone (Simulator)",
-        "x86_64": "iPhone (Simulator)",
-    ]
-}
@@ -1,123 +0,0 @@
-import Foundation
-import Network
-import os
-
-struct DiscoveredCluster: Identifiable, Equatable {
-    let id: String
-    let name: String
-    let endpoint: NWEndpoint
-
-    static func == (lhs: DiscoveredCluster, rhs: DiscoveredCluster) -> Bool {
-        lhs.id == rhs.id && lhs.name == rhs.name
-    }
-}
-
-@Observable
-@MainActor
-final class DiscoveryService {
-    private(set) var discoveredClusters: [DiscoveredCluster] = []
-    private(set) var isSearching = false
-
-    private var browser: NWBrowser?
-
-    func startBrowsing() {
-        guard browser == nil else { return }
-
-        let browser = NWBrowser(for: .bonjour(type: "_exo._tcp", domain: nil), using: .tcp)
-
-        browser.stateUpdateHandler = { [weak self] state in
-            guard let service = self else { return }
-            Task { @MainActor in
-                switch state {
-                case .ready:
-                    service.isSearching = true
-                case .failed, .cancelled:
-                    service.isSearching = false
-                default:
-                    break
-                }
-            }
-        }
-
-        browser.browseResultsChangedHandler = { [weak self] results, _ in
-            guard let service = self else { return }
-            Task { @MainActor in
-                service.discoveredClusters = results.compactMap { result in
-                    guard case .service(let name, _, _, _) = result.endpoint else {
-                        return nil
-                    }
-                    return DiscoveredCluster(
-                        id: name,
-                        name: name,
-                        endpoint: result.endpoint
-                    )
-                }
-            }
-        }
-
-        browser.start(queue: .main)
-        self.browser = browser
-    }
-
-    func stopBrowsing() {
-        browser?.cancel()
-        browser = nil
-        isSearching = false
-        discoveredClusters = []
-    }
-
-    /// Resolve a discovered Bonjour endpoint to an IP address and port, then return a ConnectionInfo.
-    func resolve(_ cluster: DiscoveredCluster) async -> ConnectionInfo? {
-        await withCheckedContinuation { continuation in
-            let didResume = OSAllocatedUnfairLock(initialState: false)
-            let connection = NWConnection(to: cluster.endpoint, using: .tcp)
-            connection.stateUpdateHandler = { state in
-                guard
-                    didResume.withLock({
-                        guard !$0 else { return false }
-                        $0 = true
-                        return true
-                    })
-                else { return }
-                switch state {
-                case .ready:
-                    if let innerEndpoint = connection.currentPath?.remoteEndpoint,
-                        case .hostPort(let host, let port) = innerEndpoint
-                    {
-                        var hostString: String
-                        switch host {
-                        case .ipv4(let addr):
-                            hostString = "\(addr)"
-                        case .ipv6(let addr):
-                            hostString = "\(addr)"
-                        case .name(let name, _):
-                            hostString = name
-                        @unknown default:
-                            hostString = "\(host)"
-                        }
-                        // Strip interface scope suffix (e.g. "%en0")
-                        if let pct = hostString.firstIndex(of: "%") {
-                            hostString = String(hostString[..<pct])
-                        }
-                        let info = ConnectionInfo(
-                            host: hostString,
-                            port: Int(port.rawValue),
-                            nodeId: nil
-                        )
-                        connection.cancel()
-                        continuation.resume(returning: info)
-                    } else {
-                        connection.cancel()
-                        continuation.resume(returning: nil)
-                    }
-                case .failed, .cancelled:
-                    continuation.resume(returning: nil)
-                default:
-                    // Not a terminal state — allow future callbacks
-                    didResume.withLock { $0 = false }
-                }
-            }
-            connection.start(queue: .global(qos: .userInitiated))
-        }
-    }
-}
@@ -1,201 +0,0 @@
-import Foundation
-import MLXLLM
-import MLXLMCommon
-
-enum LocalModelState: Equatable {
-    case notDownloaded
-    case downloading(progress: Double)
-    case downloaded
-    case loading
-    case ready
-    case generating
-    case error(String)
-}
-
-@Observable
-@MainActor
-final class LocalInferenceService {
-    private(set) var modelState: LocalModelState = .notDownloaded
-    private var modelContainer: ModelContainer?
-    private var generationTask: Task<Void, Never>?
-
-    let defaultModelId = "mlx-community/Qwen3-0.6B-4bit"
-
-    private static let modelDownloadedKey = "exo_local_model_downloaded"
-
-    var isReady: Bool {
-        modelState == .ready
-    }
-
-    var isAvailable: Bool {
-        modelState == .ready || modelState == .generating
-    }
-
-    init() {
-        if UserDefaults.standard.bool(forKey: Self.modelDownloadedKey) {
-            modelState = .downloaded
-        }
-    }
-
-    // MARK: - Model Lifecycle
-
-    func prepareModel() async {
-        guard modelState == .notDownloaded || modelState == .downloaded else { return }
-
-        let wasDownloaded = modelState == .downloaded
-
-        if !wasDownloaded {
-            modelState = .downloading(progress: 0)
-        } else {
-            modelState = .loading
-        }
-
-        do {
-            let container = try await loadModelContainer(
-                id: defaultModelId
-            ) { [weak self] progress in
-                guard let self else { return }
-                Task { @MainActor in
-                    if case .downloading = self.modelState {
-                        self.modelState = .downloading(progress: progress.fractionCompleted)
-                    }
-                }
-            }
-
-            self.modelContainer = container
-            UserDefaults.standard.set(true, forKey: Self.modelDownloadedKey)
-            modelState = .ready
-        } catch {
-            modelState = .error(error.localizedDescription)
-        }
-    }
-
-    func unloadModel() {
-        cancelGeneration()
-        modelContainer = nil
-        modelState = .downloaded
-    }
-
-    // MARK: - Generation
-
-    func streamChatCompletion(request: ChatCompletionRequest) -> AsyncThrowingStream<
-        ChatCompletionChunk, Error
-    > {
-        AsyncThrowingStream { continuation in
-            let task = Task { [weak self] in
-                guard let self else {
-                    continuation.finish(throwing: LocalInferenceError.serviceUnavailable)
-                    return
-                }
-
-                guard let container = self.modelContainer else {
-                    continuation.finish(throwing: LocalInferenceError.modelNotLoaded)
-                    return
-                }
-
-                await MainActor.run {
-                    self.modelState = .generating
-                }
-
-                defer {
-                    Task { @MainActor [weak self] in
-                        if self?.modelState == .generating {
-                            self?.modelState = .ready
-                        }
-                    }
-                }
-
-                let chunkId = "local-\(UUID().uuidString)"
-
-                do {
-                    // Build Chat.Message array from the request
-                    var chatMessages: [Chat.Message] = []
-                    for msg in request.messages {
-                        switch msg.role {
-                        case "system":
-                            chatMessages.append(.system(msg.content))
-                        case "assistant":
-                            chatMessages.append(.assistant(msg.content))
-                        default:
-                            chatMessages.append(.user(msg.content))
-                        }
-                    }
-
-                    // Use ChatSession for streaming generation
-                    let session = ChatSession(
-                        container,
-                        history: chatMessages,
-                        generateParameters: GenerateParameters(
-                            maxTokens: request.maxTokens ?? 4096,
-                            temperature: Float(request.temperature ?? 0.7)
-                        )
-                    )
-
-                    // Stream with an empty prompt since history already contains the conversation
-                    let stream = session.streamResponse(to: "")
-                    for try await text in stream {
-                        if Task.isCancelled { break }
-
-                        let chunk = ChatCompletionChunk(
-                            id: chunkId,
-                            model: request.model,
-                            choices: [
-                                StreamingChoice(
-                                    index: 0,
-                                    delta: Delta(role: nil, content: text),
-                                    finishReason: nil
-                                )
-                            ],
-                            usage: nil
-                        )
-                        continuation.yield(chunk)
-                    }
-
-                    // Send final chunk with finish reason
-                    let finalChunk = ChatCompletionChunk(
-                        id: chunkId,
-                        model: request.model,
-                        choices: [
-                            StreamingChoice(
-                                index: 0,
-                                delta: Delta(role: nil, content: nil),
-                                finishReason: "stop"
-                            )
-                        ],
-                        usage: nil
-                    )
-                    continuation.yield(finalChunk)
-                    continuation.finish()
-                } catch {
-                    continuation.finish(throwing: error)
-                }
-            }
-
-            self.generationTask = task
-
-            continuation.onTermination = { _ in
-                task.cancel()
-            }
-        }
-    }
-
-    func cancelGeneration() {
-        generationTask?.cancel()
-        generationTask = nil
-        if modelState == .generating {
-            modelState = .ready
-        }
-    }
-}
-
-enum LocalInferenceError: LocalizedError {
-    case serviceUnavailable
-    case modelNotLoaded
-
-    var errorDescription: String? {
-        switch self {
-        case .serviceUnavailable: "Local inference service is unavailable"
-        case .modelNotLoaded: "Local model is not loaded"
-        }
-    }
-}
@@ -1,50 +0,0 @@
-import Foundation
-
-struct SSEStreamParser<T: Decodable>: AsyncSequence {
-    typealias Element = T
-
-    let bytes: URLSession.AsyncBytes
-    let decoder: JSONDecoder
-
-    init(bytes: URLSession.AsyncBytes, decoder: JSONDecoder = JSONDecoder()) {
-        self.bytes = bytes
-        self.decoder = decoder
-    }
-
-    func makeAsyncIterator() -> AsyncIterator {
-        AsyncIterator(lines: bytes.lines, decoder: decoder)
-    }
-
-    struct AsyncIterator: AsyncIteratorProtocol {
-        var lines: AsyncLineSequence<URLSession.AsyncBytes>.AsyncIterator
-        let decoder: JSONDecoder
-
-        init(lines: AsyncLineSequence<URLSession.AsyncBytes>, decoder: JSONDecoder) {
-            self.lines = lines.makeAsyncIterator()
-            self.decoder = decoder
-        }
-
-        mutating func next() async throws -> T? {
-            while let line = try await lines.next() {
-                let trimmed = line.trimmingCharacters(in: .whitespaces)
-
-                guard trimmed.hasPrefix("data: ") else { continue }
-
-                let payload = String(trimmed.dropFirst(6))
-
-                if payload == "[DONE]" {
-                    return nil
-                }
-
-                guard let data = payload.data(using: .utf8) else { continue }
-
-                do {
-                    return try decoder.decode(T.self, from: data)
-                } catch {
-                    continue
-                }
-            }
-            return nil
-        }
-    }
-}
@@ -1,203 +0,0 @@
-import SwiftUI
-
-struct ChatView: View {
-    @Environment(ClusterService.self) private var clusterService
-    @Environment(ChatService.self) private var chatService
-    @Environment(LocalInferenceService.self) private var localInferenceService
-    @State private var inputText = ""
-    @State private var showModelSelector = false
-
-    var body: some View {
-        VStack(spacing: 0) {
-            modelBar
-
-            GradientDivider()
-
-            messageList
-
-            GradientDivider()
-
-            inputBar
-        }
-        .background(Color.exoBlack)
-        .sheet(isPresented: $showModelSelector) {
-            ModelSelectorView(
-                models: clusterService.availableModels,
-                selectedModelId: chatService.activeConversation?.modelId
-            ) { modelId in
-                chatService.setModelForActiveConversation(modelId)
-            }
-            .presentationBackground(Color.exoDarkGray)
-        }
-    }
-
-    // MARK: - Model Bar
-
-    private var useLocalModel: Bool {
-        !clusterService.isConnected && localInferenceService.isAvailable
-    }
-
-    private var modelBar: some View {
-        Button {
-            if !useLocalModel {
-                showModelSelector = true
-            }
-        } label: {
-            HStack {
-                Image(systemName: useLocalModel ? "iphone" : "cpu")
-                    .font(.exoCaption)
-                    .foregroundStyle(useLocalModel ? Color.exoYellow : Color.exoLightGray)
-
-                if useLocalModel {
-                    Text(localInferenceService.defaultModelId)
-                        .font(.exoSubheadline)
-                        .foregroundStyle(Color.exoForeground)
-                        .lineLimit(1)
-                } else if let modelId = chatService.activeConversation?.modelId {
-                    Text(modelId)
-                        .font(.exoSubheadline)
-                        .foregroundStyle(Color.exoForeground)
-                        .lineLimit(1)
-                } else {
-                    Text("SELECT MODEL")
-                        .font(.exoSubheadline)
-                        .tracking(1.5)
-                        .foregroundStyle(Color.exoLightGray)
-                }
-
-                Spacer()
-
-                if useLocalModel {
-                    Text("ON-DEVICE")
-                        .font(.exoCaption)
-                        .tracking(1)
-                        .foregroundStyle(Color.exoYellow)
-                        .padding(.horizontal, 6)
-                        .padding(.vertical, 2)
-                        .background(Color.exoYellow.opacity(0.15))
-                        .clipShape(Capsule())
-                } else {
-                    Image(systemName: "chevron.right")
-                        .font(.caption)
-                        .foregroundStyle(Color.exoLightGray)
-                }
-            }
-            .padding(.horizontal)
-            .padding(.vertical, 10)
-            .background(Color.exoDarkGray)
-        }
-        .tint(.primary)
-        .disabled(useLocalModel)
-    }
-
-    // MARK: - Messages
-
-    private var messageList: some View {
-        ScrollViewReader { proxy in
-            ScrollView {
-                LazyVStack(spacing: 12) {
-                    if chatService.activeMessages.isEmpty {
-                        emptyState
-                    } else {
-                        ForEach(chatService.activeMessages) { message in
-                            MessageBubbleView(message: message)
-                                .id(message.id)
-                        }
-                    }
-                }
-                .padding()
-            }
-            .background(Color.exoBlack)
-            .onChange(of: chatService.activeMessages.last?.content) {
-                if let lastId = chatService.activeMessages.last?.id {
-                    withAnimation(.easeOut(duration: 0.2)) {
-                        proxy.scrollTo(lastId, anchor: .bottom)
-                    }
-                }
-            }
-        }
-    }
-
-    private var emptyState: some View {
-        VStack(spacing: 16) {
-            Spacer(minLength: 80)
-
-            ZStack {
-                Circle()
-                    .stroke(Color.exoYellow.opacity(0.15), lineWidth: 1)
-                    .frame(width: 80, height: 80)
-                Circle()
-                    .stroke(Color.exoYellow.opacity(0.3), lineWidth: 1)
-                    .frame(width: 56, height: 56)
-                Circle()
-                    .fill(Color.exoYellow.opacity(0.15))
-                    .frame(width: 32, height: 32)
-                Circle()
-                    .fill(Color.exoYellow)
-                    .frame(width: 8, height: 8)
-                    .shadow(color: Color.exoYellow.opacity(0.6), radius: 6)
-            }
-
-            Text("AWAITING INPUT")
-                .font(.exoSubheadline)
-                .tracking(3)
-                .foregroundStyle(Color.exoLightGray)
-
-            Text("Send a message to begin.")
-                .font(.exoCaption)
-                .foregroundStyle(Color.exoLightGray.opacity(0.6))
-
-            Spacer(minLength: 80)
-        }
-        .padding()
-    }
-
-    // MARK: - Input
-
-    private var inputBar: some View {
-        HStack(alignment: .bottom, spacing: 8) {
-            TextField("Message...", text: $inputText, axis: .vertical)
-                .font(.exoBody)
-                .lineLimit(1...6)
-                .textFieldStyle(.plain)
-                .padding(10)
-                .background(Color.exoMediumGray)
-                .foregroundStyle(Color.exoForeground)
-                .clipShape(RoundedRectangle(cornerRadius: 8))
-
-            if chatService.isGenerating {
-                Button {
-                    chatService.cancelGeneration()
-                } label: {
-                    Image(systemName: "stop.circle.fill")
-                        .font(.title2)
-                        .foregroundStyle(Color.exoDestructive)
-                }
-            } else {
-                Button {
-                    let text = inputText
-                    inputText = ""
-                    chatService.sendMessage(text)
-                } label: {
-                    Text("SEND")
-                        .font(.exoMono(12, weight: .bold))
-                        .tracking(1)
-                        .foregroundStyle(canSend ? Color.exoBlack : Color.exoLightGray)
-                        .padding(.horizontal, 14)
-                        .padding(.vertical, 8)
-                        .background(canSend ? Color.exoYellow : Color.exoMediumGray)
-                        .clipShape(RoundedRectangle(cornerRadius: 8))
-                }
-                .disabled(!canSend)
-            }
-        }
-        .padding(.horizontal)
-        .padding(.vertical, 8)
-        .background(Color.exoDarkGray)
-    }
-
-    private var canSend: Bool {
-        !inputText.trimmingCharacters(in: .whitespacesAndNewlines).isEmpty
-            && (clusterService.isConnected || localInferenceService.isAvailable)
-    }
-}
@@ -1,54 +0,0 @@
-import SwiftUI
-
-struct MessageBubbleView: View {
-    let message: ChatMessage
-
-    private var isAssistant: Bool { message.role == .assistant }
-
-    var body: some View {
-        HStack {
-            if message.role == .user { Spacer(minLength: 48) }
-
-            VStack(alignment: isAssistant ? .leading : .trailing, spacing: 6) {
-                // Header
-                HStack(spacing: 4) {
-                    if isAssistant {
-                        Circle()
-                            .fill(Color.exoYellow)
-                            .frame(width: 6, height: 6)
-                            .shadow(color: Color.exoYellow.opacity(0.6), radius: 4)
-                        Text("EXO")
-                            .font(.exoMono(10, weight: .bold))
-                            .tracking(1.5)
-                            .foregroundStyle(Color.exoYellow)
-                    } else {
-                        Text("QUERY")
-                            .font(.exoMono(10, weight: .medium))
-                            .tracking(1.5)
-                            .foregroundStyle(Color.exoLightGray)
-                    }
-                }
-
-                // Bubble
-                HStack(spacing: 0) {
-                    if isAssistant {
-                        RoundedRectangle(cornerRadius: 1)
-                            .fill(Color.exoYellow.opacity(0.5))
-                            .frame(width: 2)
-                    }
-
-                    Text(message.content + (message.isStreaming ? " \u{258C}" : ""))
-                        .font(.exoBody)
-                        .textSelection(.enabled)
-                        .foregroundStyle(Color.exoForeground)
-                        .padding(.horizontal, 14)
-                        .padding(.vertical, 10)
-                }
-                .background(Color.exoDarkGray)
-                .clipShape(RoundedRectangle(cornerRadius: 8))
-            }
-
-            if isAssistant { Spacer(minLength: 48) }
-        }
-    }
-}
@@ -1,75 +0,0 @@
-import SwiftUI
-
-struct ModelSelectorView: View {
-    let models: [ModelOption]
-    let selectedModelId: String?
-    let onSelect: (String) -> Void
-    @Environment(\.dismiss) private var dismiss
-
-    var body: some View {
-        NavigationStack {
-            List {
-                if models.isEmpty {
-                    emptyContent
-                } else {
-                    modelsList
-                }
-            }
-            .scrollContentBackground(.hidden)
-            .background(Color.exoBlack)
-            .navigationTitle("SELECT MODEL")
-            .navigationBarTitleDisplayMode(.inline)
-            .toolbar {
-                ToolbarItem(placement: .cancellationAction) {
-                    Button("Cancel") { dismiss() }
-                        .font(.exoSubheadline)
-                        .foregroundStyle(Color.exoYellow)
-                }
-            }
-        }
-    }
-
-    private var emptyContent: some View {
-        ContentUnavailableView(
-            "No Models Available",
-            systemImage: "cpu",
-            description: Text("Connect to an EXO cluster to see available models.")
-        )
-        .foregroundStyle(Color.exoLightGray)
-        .listRowBackground(Color.exoBlack)
-    }
-
-    private var modelsList: some View {
-        ForEach(models) { model in
-            Button {
-                onSelect(model.id)
-                dismiss()
-            } label: {
-                modelRow(model)
-            }
-            .tint(.primary)
-            .listRowBackground(Color.exoDarkGray)
-        }
-    }
-
-    private func modelRow(_ model: ModelOption) -> some View {
-        HStack {
-            VStack(alignment: .leading, spacing: 2) {
-                Text(model.displayName)
-                    .font(.exoSubheadline)
-                    .foregroundStyle(Color.exoForeground)
-                Text(model.id)
-                    .font(.exoCaption)
-                    .foregroundStyle(Color.exoLightGray)
-            }
-
-            Spacer()
-
-            if model.id == selectedModelId {
-                Image(systemName: "checkmark")
-                    .font(.exoSubheadline)
-                    .foregroundStyle(Color.exoYellow)
-            }
-        }
-    }
-}
@@ -1,68 +0,0 @@
-import SwiftUI
-
-struct ConnectionStatusBadge: View {
-    let connectionState: ConnectionState
-    var localModelState: LocalModelState = .notDownloaded
-
-    private var isLocalReady: Bool {
-        if case .disconnected = connectionState {
-            return localModelState == .ready || localModelState == .generating
-        }
-        return false
-    }
-
-    var body: some View {
-        HStack(spacing: 6) {
-            Circle()
-                .fill(dotColor)
-                .frame(width: 8, height: 8)
-                .shadow(color: dotColor.opacity(0.6), radius: 4)
-
-            Text(label.uppercased())
-                .font(.exoMono(10, weight: .medium))
-                .tracking(1)
-                .foregroundStyle(Color.exoForeground)
-        }
-        .padding(.horizontal, 10)
-        .padding(.vertical, 5)
-        .background(backgroundColor)
-        .clipShape(Capsule())
-        .overlay(
-            Capsule()
-                .stroke(dotColor.opacity(0.3), lineWidth: 1)
-        )
-    }
-
-    private var dotColor: Color {
-        if isLocalReady {
-            return .exoYellow
-        }
-        switch connectionState {
-        case .connected: return .green
-        case .connecting: return .orange
-        case .disconnected: return .exoLightGray
-        }
-    }
-
-    private var label: String {
-        if isLocalReady {
-            return "Local"
-        }
-        switch connectionState {
-        case .connected: return "Connected"
-        case .connecting: return "Connecting"
-        case .disconnected: return "Disconnected"
-        }
-    }
-
-    private var backgroundColor: Color {
-        if isLocalReady {
-            return Color.exoYellow.opacity(0.1)
-        }
-        switch connectionState {
-        case .connected: return .green.opacity(0.1)
-        case .connecting: return .orange.opacity(0.1)
-        case .disconnected: return Color.exoMediumGray.opacity(0.5)
-        }
-    }
-}
@@ -1,136 +0,0 @@
-import SwiftUI
-
-struct RootView: View {
-    @Environment(ClusterService.self) private var clusterService
-    @Environment(DiscoveryService.self) private var discoveryService
-    @Environment(ChatService.self) private var chatService
-    @Environment(LocalInferenceService.self) private var localInferenceService
-    @State private var showSettings = false
-    @State private var showConversations = false
-
-    var body: some View {
-        NavigationStack {
-            ChatView()
-                .navigationTitle("EXO")
-                .navigationBarTitleDisplayMode(.inline)
-                .toolbar {
-                    ToolbarItem(placement: .topBarLeading) {
-                        conversationMenuButton
-                    }
-
-                    ToolbarItem(placement: .principal) {
-                        ConnectionStatusBadge(
-                            connectionState: clusterService.connectionState,
-                            localModelState: localInferenceService.modelState
-                        )
-                    }
-
-                    ToolbarItem(placement: .topBarTrailing) {
-                        Button {
-                            showSettings = true
-                        } label: {
-                            Image(systemName: "gear")
-                                .foregroundStyle(Color.exoYellow)
-                        }
-                    }
-                }
-        }
-        .tint(Color.exoYellow)
-        .sheet(isPresented: $showSettings) {
-            SettingsView()
-                .environment(discoveryService)
-                .presentationBackground(Color.exoDarkGray)
-        }
-        .sheet(isPresented: $showConversations) {
-            conversationList
-                .presentationBackground(Color.exoDarkGray)
-        }
-    }
-
-    // MARK: - Conversations
-
-    private var conversationMenuButton: some View {
-        HStack(spacing: 12) {
-            Button {
-                showConversations = true
-            } label: {
-                Image(systemName: "sidebar.left")
-                    .foregroundStyle(Color.exoYellow)
-            }
-
-            Button {
-                chatService.createConversation()
-            } label: {
-                Image(systemName: "square.and.pencil")
-                    .foregroundStyle(Color.exoYellow)
-            }
-        }
-    }
-
-    private var conversationList: some View {
-        NavigationStack {
-            List {
-                if chatService.conversations.isEmpty {
-                    Text("No conversations yet")
-                        .font(.exoBody)
-                        .foregroundStyle(Color.exoLightGray)
-                        .listRowBackground(Color.exoDarkGray)
-                } else {
-                    ForEach(chatService.conversations) { conversation in
-                        let isActive = conversation.id == chatService.activeConversationId
-                        Button {
-                            chatService.setActiveConversation(id: conversation.id)
-                            showConversations = false
-                        } label: {
-                            VStack(alignment: .leading, spacing: 4) {
-                                Text(conversation.title)
-                                    .font(.exoSubheadline)
-                                    .fontWeight(isActive ? .semibold : .regular)
-                                    .foregroundStyle(
-                                        isActive ? Color.exoYellow : Color.exoForeground
-                                    )
-                                    .lineLimit(1)
-
-                                if let modelId = conversation.modelId {
-                                    Text(modelId)
-                                        .font(.exoCaption)
-                                        .foregroundStyle(Color.exoLightGray)
-                                        .lineLimit(1)
-                                }
-                            }
-                        }
-                        .listRowBackground(
-                            isActive
-                                ? Color.exoYellow.opacity(0.1)
-                                : Color.exoDarkGray
-                        )
-                    }
-                    .onDelete { indexSet in
-                        for index in indexSet {
-                            chatService.deleteConversation(id: chatService.conversations[index].id)
-                        }
-                    }
-                }
-            }
-            .scrollContentBackground(.hidden)
-            .background(Color.exoBlack)
-            .navigationTitle("Conversations")
-            .navigationBarTitleDisplayMode(.inline)
-            .toolbar {
-                ToolbarItem(placement: .confirmationAction) {
-                    Button("Done") { showConversations = false }
-                        .font(.exoSubheadline)
-                        .foregroundStyle(Color.exoYellow)
-                }
-                ToolbarItem(placement: .topBarLeading) {
-                    Button {
-                        chatService.createConversation()
-                    } label: {
-                        Image(systemName: "plus")
-                            .foregroundStyle(Color.exoYellow)
-                    }
-                }
-            }
-        }
-    }
-}
@@ -1,314 +0,0 @@
-import SwiftUI
-
-struct SettingsView: View {
-    @Environment(ClusterService.self) private var clusterService
-    @Environment(DiscoveryService.self) private var discoveryService
-    @Environment(LocalInferenceService.self) private var localInferenceService
-    @Environment(\.dismiss) private var dismiss
-    @State private var host: String = ""
-    @State private var port: String = "52415"
-
-    var body: some View {
-        NavigationStack {
-            Form {
-                localModelSection
-                nearbyClustersSection
-                connectionSection
-                statusSection
-            }
-            .scrollContentBackground(.hidden)
-            .background(Color.exoBlack)
-            .navigationTitle("Settings")
-            .navigationBarTitleDisplayMode(.inline)
-            .toolbar {
-                ToolbarItem(placement: .confirmationAction) {
-                    Button("Done") { dismiss() }
-                        .font(.exoSubheadline)
-                        .foregroundStyle(Color.exoYellow)
-                }
-            }
-        }
-    }
-
-    // MARK: - Section Headers
-
-    private func sectionHeader(_ title: String) -> some View {
-        Text(title.uppercased())
-            .font(.exoMono(10, weight: .semibold))
-            .tracking(2)
-            .foregroundStyle(Color.exoYellow)
-    }
-
-    // MARK: - Local Model
-
-    private var localModelSection: some View {
-        Section {
-            HStack {
-                VStack(alignment: .leading, spacing: 4) {
-                    Text(localInferenceService.defaultModelId)
-                        .font(.exoSubheadline)
-                        .foregroundStyle(Color.exoForeground)
-
-                    Text(localModelStatusText)
-                        .font(.exoCaption)
-                        .foregroundStyle(Color.exoLightGray)
-                }
-
-                Spacer()
-
-                localModelActionButton
-            }
-            .listRowBackground(Color.exoDarkGray)
-
-            if case .downloading(let progress) = localInferenceService.modelState {
-                ProgressView(value: progress)
-                    .tint(Color.exoYellow)
-                    .listRowBackground(Color.exoDarkGray)
-            }
-        } header: {
-            sectionHeader("Local Model")
-        } footer: {
-            Text(
-                "When disconnected from a cluster, messages are processed on-device using this model."
-            )
-            .font(.exoCaption)
-            .foregroundStyle(Color.exoLightGray.opacity(0.7))
-        }
-    }
-
-    private var localModelStatusText: String {
-        switch localInferenceService.modelState {
-        case .notDownloaded: "Not downloaded"
-        case .downloading(let progress): "Downloading \(Int(progress * 100))%..."
-        case .downloaded: "Downloaded — not loaded"
-        case .loading: "Loading into memory..."
-        case .ready: "Ready"
-        case .generating: "Generating..."
-        case .error(let message): "Error: \(message)"
-        }
-    }
-
-    @ViewBuilder
-    private var localModelActionButton: some View {
-        switch localInferenceService.modelState {
-        case .notDownloaded:
-            exoButton("Download") {
-                Task { await localInferenceService.prepareModel() }
-            }
-        case .downloading:
-            ProgressView()
-                .controlSize(.small)
-                .tint(Color.exoYellow)
-        case .downloaded:
-            exoButton("Load") {
-                Task { await localInferenceService.prepareModel() }
-            }
-        case .loading:
-            ProgressView()
-                .controlSize(.small)
-                .tint(Color.exoYellow)
-        case .ready, .generating:
-            exoButton("Unload") {
-                localInferenceService.unloadModel()
-            }
-        case .error:
-            exoButton("Retry", destructive: true) {
-                Task { await localInferenceService.prepareModel() }
-            }
-        }
-    }
-
-    private func exoButton(_ title: String, destructive: Bool = false, action: @escaping () -> Void)
-        -> some View
-    {
-        let borderColor = destructive ? Color.exoDestructive : Color.exoYellow
-        return Button(action: action) {
-            Text(title.uppercased())
-                .font(.exoMono(11, weight: .semibold))
-                .tracking(1)
-                .foregroundStyle(borderColor)
-                .padding(.horizontal, 10)
-                .padding(.vertical, 5)
-                .overlay(
-                    RoundedRectangle(cornerRadius: 6)
-                        .stroke(borderColor, lineWidth: 1)
-                )
-        }
-    }
-
-    // MARK: - Nearby Clusters
-
-    private var nearbyClustersSection: some View {
-        Section {
-            if discoveryService.discoveredClusters.isEmpty {
-                if discoveryService.isSearching {
-                    HStack {
-                        ProgressView()
-                            .tint(Color.exoYellow)
-                            .padding(.trailing, 8)
-                        Text("Searching for clusters...")
-                            .font(.exoBody)
-                            .foregroundStyle(Color.exoLightGray)
-                    }
-                    .listRowBackground(Color.exoDarkGray)
-                } else {
-                    Text("No clusters found")
-                        .font(.exoBody)
-                        .foregroundStyle(Color.exoLightGray)
-                        .listRowBackground(Color.exoDarkGray)
-                }
-            } else {
-                ForEach(discoveryService.discoveredClusters) { cluster in
-                    HStack {
-                        VStack(alignment: .leading) {
-                            Text(cluster.name)
-                                .font(.exoBody)
-                                .foregroundStyle(Color.exoForeground)
-                        }
-                        Spacer()
-                        exoButton("Connect") {
-                            Task {
-                                await clusterService.connectToDiscoveredCluster(
-                                    cluster, using: discoveryService
-                                )
-                                if clusterService.isConnected {
-                                    dismiss()
-                                }
-                            }
-                        }
-                    }
-                    .listRowBackground(Color.exoDarkGray)
-                }
-            }
-        } header: {
-            sectionHeader("Nearby Clusters")
-        }
-    }
-
-    // MARK: - Manual Connection
-
-    private var connectionSection: some View {
-        Section {
-            TextField("IP Address (e.g. 192.168.1.42)", text: $host)
-                .font(.exoBody)
-                .keyboardType(.decimalPad)
-                .textContentType(.URL)
-                .autocorrectionDisabled()
-                .foregroundStyle(Color.exoForeground)
-                .listRowBackground(Color.exoDarkGray)
-
-            TextField("Port", text: $port)
-                .font(.exoBody)
-                .keyboardType(.numberPad)
-                .foregroundStyle(Color.exoForeground)
-                .listRowBackground(Color.exoDarkGray)
-
-            Button {
-                Task {
-                    let portNum = Int(port) ?? ConnectionInfo.defaultPort
-                    let info = ConnectionInfo(host: host, port: portNum, nodeId: nil)
-                    await clusterService.connect(to: info)
-                    if clusterService.isConnected {
-                        dismiss()
-                    }
-                }
-            } label: {
-                Text(clusterService.isConnected ? "RECONNECT" : "CONNECT")
-                    .font(.exoMono(13, weight: .semibold))
-                    .tracking(1.5)
-                    .foregroundStyle(
-                        host.trimmingCharacters(in: .whitespacesAndNewlines).isEmpty
-                            ? Color.exoLightGray : Color.exoYellow
-                    )
-                    .frame(maxWidth: .infinity)
-            }
-            .disabled(host.trimmingCharacters(in: .whitespacesAndNewlines).isEmpty)
-            .listRowBackground(Color.exoDarkGray)
-        } header: {
-            sectionHeader("Manual Connection")
-        }
-    }
-
-    // MARK: - Status
-
-    private var statusSection: some View {
-        Section {
-            if let connection = clusterService.currentConnection {
-                LabeledContent {
-                    Text(connection.host)
-                        .font(.exoCaption)
-                        .foregroundStyle(Color.exoForeground)
-                } label: {
-                    Text("Host")
-                        .font(.exoCaption)
-                        .foregroundStyle(Color.exoLightGray)
-                }
-                .listRowBackground(Color.exoDarkGray)
-
-                LabeledContent {
-                    Text("\(connection.port)")
-                        .font(.exoCaption)
-                        .foregroundStyle(Color.exoForeground)
-                } label: {
-                    Text("Port")
-                        .font(.exoCaption)
-                        .foregroundStyle(Color.exoLightGray)
-                }
-                .listRowBackground(Color.exoDarkGray)
-
-                if let nodeId = connection.nodeId {
-                    LabeledContent {
-                        Text(String(nodeId.prefix(12)) + "...")
-                            .font(.exoCaption)
-                            .foregroundStyle(Color.exoForeground)
-                    } label: {
-                        Text("Node ID")
-                            .font(.exoCaption)
-                            .foregroundStyle(Color.exoLightGray)
-                    }
-                    .listRowBackground(Color.exoDarkGray)
-                }
-
-                LabeledContent {
-                    Text("\(clusterService.availableModels.count)")
-                        .font(.exoCaption)
-                        .foregroundStyle(Color.exoForeground)
-                } label: {
-                    Text("Models")
-                        .font(.exoCaption)
-                        .foregroundStyle(Color.exoLightGray)
-                }
-                .listRowBackground(Color.exoDarkGray)
-
-                Button(role: .destructive) {
-                    clusterService.disconnect()
-                } label: {
-                    Text("DISCONNECT")
-                        .font(.exoMono(13, weight: .semibold))
-                        .tracking(1.5)
-                        .foregroundStyle(Color.exoDestructive)
-                        .frame(maxWidth: .infinity)
-                }
-                .listRowBackground(Color.exoDarkGray)
-            } else {
-                if let error = clusterService.lastError {
-                    Label {
-                        Text(error)
-                            .font(.exoCaption)
-                    } icon: {
-                        Image(systemName: "exclamationmark.triangle")
-                    }
-                    .foregroundStyle(Color.exoDestructive)
-                    .listRowBackground(Color.exoDarkGray)
-                } else {
-                    Text("Not connected")
-                        .font(.exoBody)
-                        .foregroundStyle(Color.exoLightGray)
-                        .listRowBackground(Color.exoDarkGray)
-                }
-            }
-        } header: {
-            sectionHeader("Status")
-        }
-    }
-}
@@ -1,51 +0,0 @@
-import SwiftUI
-
-// MARK: - EXO Color Palette
-
-extension Color {
-    /// Primary background — near-black (#121212)
-    static let exoBlack = Color(red: 0x12 / 255.0, green: 0x12 / 255.0, blue: 0x12 / 255.0)
-    /// Card / surface background (#1F1F1F)
-    static let exoDarkGray = Color(red: 0x1F / 255.0, green: 0x1F / 255.0, blue: 0x1F / 255.0)
-    /// Input field / elevated surface (#353535)
-    static let exoMediumGray = Color(red: 0x35 / 255.0, green: 0x35 / 255.0, blue: 0x35 / 255.0)
-    /// Secondary text (#999999)
-    static let exoLightGray = Color(red: 0x99 / 255.0, green: 0x99 / 255.0, blue: 0x99 / 255.0)
-    /// Accent yellow — matches dashboard (#FFD700)
-    static let exoYellow = Color(red: 0xFF / 255.0, green: 0xD7 / 255.0, blue: 0x00 / 255.0)
-    /// Primary foreground text (#E5E5E5)
-    static let exoForeground = Color(red: 0xE5 / 255.0, green: 0xE5 / 255.0, blue: 0xE5 / 255.0)
-    /// Destructive / error (#E74C3C)
-    static let exoDestructive = Color(red: 0xE7 / 255.0, green: 0x4C / 255.0, blue: 0x3C / 255.0)
-}
-
-// MARK: - EXO Typography (SF Mono via .monospaced design)
-
-extension Font {
-    /// Monospaced font at a given size and weight.
-    static func exoMono(_ size: CGFloat, weight: Font.Weight = .regular) -> Font {
-        .system(size: size, weight: weight, design: .monospaced)
-    }
-
-    /// Body text — 15pt monospaced
-    static let exoBody: Font = .system(size: 15, weight: .regular, design: .monospaced)
-    /// Caption — 11pt monospaced
-    static let exoCaption: Font = .system(size: 11, weight: .regular, design: .monospaced)
-    /// Subheadline — 13pt monospaced medium
-    static let exoSubheadline: Font = .system(size: 13, weight: .medium, design: .monospaced)
-    /// Headline — 17pt monospaced semibold
-    static let exoHeadline: Font = .system(size: 17, weight: .semibold, design: .monospaced)
-}
-
-// MARK: - Reusable Gradient Divider
-
-struct GradientDivider: View {
-    var body: some View {
-        LinearGradient(
-            colors: [.clear, Color.exoYellow.opacity(0.3), .clear],
-            startPoint: .leading,
-            endPoint: .trailing
-        )
-        .frame(height: 1)
-    }
-}
@@ -1,18 +0,0 @@
-//
-//  EXO_iOSTests.swift
-//  EXO-iOSTests
-//
-//  Created by Sami Khan on 2026-02-17.
-//
-
-import Testing
-
-@testable import EXO_iOS
-
-struct EXO_iOSTests {
-
-    @Test func example() async throws {
-        // Write your test here and use APIs like `#expect(...)` to check expected conditions.
-    }
-
-}
@@ -1,41 +0,0 @@
-//
-//  EXO_iOSUITests.swift
-//  EXO-iOSUITests
-//
-//  Created by Sami Khan on 2026-02-17.
-//
-
-import XCTest
-
-final class EXO_iOSUITests: XCTestCase {
-
-    override func setUpWithError() throws {
-        // Put setup code here. This method is called before the invocation of each test method in the class.
-
-        // In UI tests it is usually best to stop immediately when a failure occurs.
-        continueAfterFailure = false
-
-        // In UI tests it’s important to set the initial state - such as interface orientation - required for your tests before they run. The setUp method is a good place to do this.
-    }
-
-    override func tearDownWithError() throws {
-        // Put teardown code here. This method is called after the invocation of each test method in the class.
-    }
-
-    @MainActor
-    func testExample() throws {
-        // UI tests must launch the application that they test.
-        let app = XCUIApplication()
-        app.launch()
-
-        // Use XCTAssert and related functions to verify your tests produce the correct results.
-    }
-
-    @MainActor
-    func testLaunchPerformance() throws {
-        // This measures how long it takes to launch your application.
-        measure(metrics: [XCTApplicationLaunchMetric()]) {
-            XCUIApplication().launch()
-        }
-    }
-}
@@ -1,33 +0,0 @@
-//
-//  EXO_iOSUITestsLaunchTests.swift
-//  EXO-iOSUITests
-//
-//  Created by Sami Khan on 2026-02-17.
-//
-
-import XCTest
-
-final class EXO_iOSUITestsLaunchTests: XCTestCase {
-
-    override class var runsForEachTargetApplicationUIConfiguration: Bool {
-        true
-    }
-
-    override func setUpWithError() throws {
-        continueAfterFailure = false
-    }
-
-    @MainActor
-    func testLaunch() throws {
-        let app = XCUIApplication()
-        app.launch()
-
-        // Insert steps here to perform after app launch but before taking a screenshot,
-        // such as logging into a test account or navigating somewhere in the app
-
-        let attachment = XCTAttachment(screenshot: app.screenshot())
-        attachment.name = "Launch Screen"
-        attachment.lifetime = .keepAlways
-        add(attachment)
-    }
-}
@@ -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 {
@@ -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
@@ -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?
@@ -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 {
@@ -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 [] }
@@ -1,7 +0,0 @@
-# Canary benchmark manifest
-#
-# Lists the suite files to include. Each file defines benchmarks
-# with shared constraints, topology, and default args.
-include = [
-    "single-m3-ultra.toml",
-]
@@ -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:
@@ -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"
@@ -1,189 +0,0 @@
-# Single-node M3 Ultra benchmarks
-#
-# Shared constraints applied to ALL benchmarks in this file.
-constraints = [
-    "All(MacOsBuild(=25D125))",
-    "Hosts(=1)",
-    "All(Chip(m3_ultra))",
-    "All(GpuCores(=80))",
-]
-
-[topology]
-type = "none"
-
-# Default args merged into each benchmark's args (benchmark-level args win).
-[defaults]
-pp = [512, 2048, 8192, 16384]
-tg = 128
-
-[[benchmark]]
-model = "mlx-community/Meta-Llama-3.1-70B-Instruct-4bit"
-extra_constraints = ["All(Memory(>=96GiB))"]
-
-[[benchmark]]
-model = "mlx-community/gpt-oss-120b-MXFP4-Q8"
-extra_constraints = ["All(Memory(>=96GiB))"]
-
-[[benchmark]]
-model = "mlx-community/GLM-4.7-Flash-8bit"
-extra_constraints = ["All(Memory(>=96GiB))"]
-
-[[benchmark]]
-model = "mlx-community/Qwen3-Coder-Next-6bit"
-extra_constraints = ["All(Memory(>=96GiB))"]
-
-[[benchmark]]
-model = "mlx-community/Qwen3-30B-A3B-8bit"
-extra_constraints = ["All(Memory(>=96GiB))"]
-
-[[benchmark]]
-model = "mlx-community/Qwen3-0.6B-4bit"
-extra_constraints = ["All(Memory(>=96GiB))"]
-
-[[benchmark]]
-model = "mlx-community/Qwen3-0.6B-8bit"
-extra_constraints = ["All(Memory(>=96GiB))"]
-
-[[benchmark]]
-model = "mlx-community/Llama-3.2-1B-Instruct-4bit"
-extra_constraints = ["All(Memory(>=96GiB))"]
-
-[[benchmark]]
-model = "mlx-community/Llama-3.2-3B-Instruct-4bit"
-extra_constraints = ["All(Memory(>=96GiB))"]
-
-[[benchmark]]
-model = "mlx-community/Llama-3.2-3B-Instruct-8bit"
-extra_constraints = ["All(Memory(>=96GiB))"]
-
-[[benchmark]]
-model = "mlx-community/Meta-Llama-3.1-8B-Instruct-4bit"
-extra_constraints = ["All(Memory(>=96GiB))"]
-
-[[benchmark]]
-model = "mlx-community/Meta-Llama-3.1-8B-Instruct-8bit"
-extra_constraints = ["All(Memory(>=96GiB))"]
-
-[[benchmark]]
-model = "mlx-community/Meta-Llama-3.1-8B-Instruct-bf16"
-extra_constraints = ["All(Memory(>=96GiB))"]
-
-[[benchmark]]
-model = "mlx-community/gpt-oss-20b-MXFP4-Q8"
-extra_constraints = ["All(Memory(>=96GiB))"]
-
-[[benchmark]]
-model = "mlx-community/Qwen3-30B-A3B-4bit"
-extra_constraints = ["All(Memory(>=96GiB))"]
-
-[[benchmark]]
-model = "mlx-community/GLM-4.7-Flash-4bit"
-extra_constraints = ["All(Memory(>=96GiB))"]
-
-[[benchmark]]
-model = "mlx-community/GLM-4.7-Flash-5bit"
-extra_constraints = ["All(Memory(>=96GiB))"]
-
-[[benchmark]]
-model = "mlx-community/GLM-4.7-Flash-6bit"
-extra_constraints = ["All(Memory(>=96GiB))"]
-
-[[benchmark]]
-model = "mlx-community/Llama-3.3-70B-Instruct-4bit"
-extra_constraints = ["All(Memory(>=96GiB))"]
-
-[[benchmark]]
-model = "mlx-community/Qwen3-Coder-Next-4bit"
-extra_constraints = ["All(Memory(>=96GiB))"]
-
-[[benchmark]]
-model = "mlx-community/Qwen3-Coder-Next-5bit"
-extra_constraints = ["All(Memory(>=96GiB))"]
-
-[[benchmark]]
-model = "mlx-community/Qwen3-Coder-Next-8bit"
-extra_constraints = ["All(Memory(>=96GiB))"]
-
-[[benchmark]]
-model = "mlx-community/Qwen3-Next-80B-A3B-Instruct-4bit"
-extra_constraints = ["All(Memory(>=96GiB))"]
-
-[[benchmark]]
-model = "mlx-community/Qwen3-Next-80B-A3B-Instruct-8bit"
-extra_constraints = ["All(Memory(>=96GiB))"]
-
-[[benchmark]]
-model = "mlx-community/Qwen3-Next-80B-A3B-Thinking-4bit"
-extra_constraints = ["All(Memory(>=96GiB))"]
-
-[[benchmark]]
-model = "mlx-community/Qwen3-Next-80B-A3B-Thinking-8bit"
-extra_constraints = ["All(Memory(>=96GiB))"]
-
-[[benchmark]]
-model = "mlx-community/Llama-3.3-70B-Instruct-8bit"
-extra_constraints = ["All(Memory(>=256GiB))"]
-
-[[benchmark]]
-model = "mlx-community/llama-3.3-70b-instruct-fp16"
-extra_constraints = ["All(Memory(>=256GiB))"]
-
-[[benchmark]]
-model = "mlx-community/GLM-4.5-Air-8bit"
-extra_constraints = ["All(Memory(>=256GiB))"]
-
-[[benchmark]]
-model = "mlx-community/GLM-4.5-Air-bf16"
-extra_constraints = ["All(Memory(>=256GiB))"]
-
-[[benchmark]]
-model = "mlx-community/GLM-4.7-4bit"
-extra_constraints = ["All(Memory(>=256GiB))"]
-
-[[benchmark]]
-model = "mlx-community/MiniMax-M2.1-3bit"
-extra_constraints = ["All(Memory(>=256GiB))"]
-
-[[benchmark]]
-model = "mlx-community/MiniMax-M2.1-8bit"
-extra_constraints = ["All(Memory(>=256GiB))"]
-
-[[benchmark]]
-model = "mlx-community/Qwen3-235B-A22B-Instruct-2507-4bit"
-extra_constraints = ["All(Memory(>=256GiB))"]
-
-[[benchmark]]
-model = "mlx-community/Qwen3-Coder-Next-bf16"
-extra_constraints = ["All(Memory(>=256GiB))"]
-
-[[benchmark]]
-model = "mlx-community/Step-3.5-Flash-4bit"
-extra_constraints = ["All(Memory(>=256GiB))"]
-
-[[benchmark]]
-model = "mlx-community/Step-3.5-Flash-6bit"
-extra_constraints = ["All(Memory(>=256GiB))"]
-
-[[benchmark]]
-model = "mlx-community/Step-3.5-Flash-8Bit"
-extra_constraints = ["All(Memory(>=256GiB))"]
-
-[[benchmark]]
-model = "mlx-community/DeepSeek-V3.1-4bit"
-extra_constraints = ["All(Memory(>=512GiB))"]
-
-[[benchmark]]
-model = "mlx-community/GLM-4.7-6bit"
-extra_constraints = ["All(Memory(>=512GiB))"]
-
-[[benchmark]]
-model = "mlx-community/GLM-4.7-8bit-gs32"
-extra_constraints = ["All(Memory(>=512GiB))"]
-
-[[benchmark]]
-model = "mlx-community/Qwen3-235B-A22B-Instruct-2507-8bit"
-extra_constraints = ["All(Memory(>=512GiB))"]
-
-[[benchmark]]
-model = "mlx-community/Qwen3-Coder-480B-A35B-Instruct-4bit"
-extra_constraints = ["All(Memory(>=512GiB))"]
@@ -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>

@@ -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)}
-/>
@@ -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
@@ -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"
@@ -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}
@@ -186,9 +186,7 @@
  // topology payload is missing them. Topology order is preserved exactly so
  // that the mini preview matches the main TopologyGraph layout.
  const nodeList = $derived(() => {
-    const nodesFromTopology = Object.keys(nodes)
-      .filter((id) => nodes[id].node_type !== "lite")
-      .map((id) => {
+    const nodesFromTopology = Object.keys(nodes).map((id) => {
      const info = nodes[id];
      const totalBytes =
        info.macmon_info?.memory?.ram_total ?? info.system_info?.memory ?? 0;
@@ -424,16 +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 });
@@ -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>
@@ -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>

@@ -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}
@@ -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 ${edge.sinkRdmaIface || "?"}`;
-        missingIface = false;
-      } else {
-        ip = edge.sendBackIp || "?";
-        const ifaceInfo = getInterfaceLabel(edge.source, ip);
-        ifaceLabel = ifaceInfo.label;
-        missingIface = ifaceInfo.missing;
-      }
-
+      const ip = edge.sendBackIp || "?";
+      const ifaceInfo = getInterfaceLabel(edge.source, ip);
      entry.connections.push({
        from: edge.source,
        to: edge.target,
        ip,
-        ifaceLabel,
-        missingIface,
+        ifaceLabel: ifaceInfo.label,
+        missingIface: ifaceInfo.missing,
      });
      pairMap.set(key, entry);
    });
@@ -554,7 +537,6 @@
      const clipPathId = `clip-${nodeInfo.id.replace(/[^a-zA-Z0-9]/g, "-")}`;

      const modelLower = modelId.toLowerCase();
-      const isLiteNode = node.node_type === "lite";

      // Check node states for styling
      const isHighlighted = highlightedNodes.has(nodeInfo.id);
@@ -907,94 +889,6 @@
          .attr("height", trackpadHeight)
          .attr("fill", "rgba(255,255,255,0.08)")
          .attr("rx", 2);
-      } else if (modelLower.includes("iphone")) {
-        // iPhone - rounded rectangle phone shape with Dynamic Island
-        iconBaseWidth = nodeRadius * 0.7;
-        iconBaseHeight = nodeRadius * 1.4;
-        const x = nodeInfo.x - iconBaseWidth / 2;
-        const y = nodeInfo.y - iconBaseHeight / 2;
-        const cornerRadius = iconBaseWidth * 0.2;
-        const bezel = 3;
-
-        // Phone body (outer frame)
-        nodeG
-          .append("rect")
-          .attr("class", "node-outline")
-          .attr("x", x)
-          .attr("y", y)
-          .attr("width", iconBaseWidth)
-          .attr("height", iconBaseHeight)
-          .attr("rx", cornerRadius)
-          .attr("fill", "#1a1a1a")
-          .attr("stroke", wireColor)
-          .attr("stroke-width", strokeWidth);
-
-        // Screen area (inner)
-        const screenClipId = `iphone-clip-${nodeInfo.id.replace(/[^a-zA-Z0-9]/g, "-")}`;
-        defs
-          .append("clipPath")
-          .attr("id", screenClipId)
-          .append("rect")
-          .attr("x", x + bezel)
-          .attr("y", y + bezel)
-          .attr("width", iconBaseWidth - bezel * 2)
-          .attr("height", iconBaseHeight - bezel * 2)
-          .attr("rx", cornerRadius - 1);
-
-        nodeG
-          .append("rect")
-          .attr("x", x + bezel)
-          .attr("y", y + bezel)
-          .attr("width", iconBaseWidth - bezel * 2)
-          .attr("height", iconBaseHeight - bezel * 2)
-          .attr("rx", cornerRadius - 1)
-          .attr("fill", screenFill);
-
-        // Memory fill on screen (fills from bottom up)
-        if (ramUsagePercent > 0) {
-          const memFillTotalHeight = iconBaseHeight - bezel * 2;
-          const memFillActualHeight =
-            (ramUsagePercent / 100) * memFillTotalHeight;
-          nodeG
-            .append("rect")
-            .attr("x", x + bezel)
-            .attr(
-              "y",
-              y + bezel + (memFillTotalHeight - memFillActualHeight),
-            )
-            .attr("width", iconBaseWidth - bezel * 2)
-            .attr("height", memFillActualHeight)
-            .attr("fill", "rgba(255,215,0,0.85)")
-            .attr("clip-path", `url(#${screenClipId})`);
-        }
-
-        // Dynamic Island notch (centered near top)
-        const diWidth = iconBaseWidth * 0.3;
-        const diHeight = iconBaseHeight * 0.04;
-        nodeG
-          .append("rect")
-          .attr("x", nodeInfo.x - diWidth / 2)
-          .attr("y", y + bezel + 4)
-          .attr("width", diWidth)
-          .attr("height", diHeight)
-          .attr("rx", diHeight / 2)
-          .attr("fill", "#000000");
-
-        // Apple logo on screen (centered)
-        const targetLogoHeight = iconBaseHeight * 0.14;
-        const logoScale = targetLogoHeight / LOGO_NATIVE_HEIGHT;
-        const logoX = nodeInfo.x - (LOGO_NATIVE_WIDTH * logoScale) / 2;
-        const logoY =
-          nodeInfo.y - (LOGO_NATIVE_HEIGHT * logoScale) / 2;
-        nodeG
-          .append("path")
-          .attr("d", APPLE_LOGO_PATH)
-          .attr(
-            "transform",
-            `translate(${logoX}, ${logoY}) scale(${logoScale})`,
-          )
-          .attr("fill", "#FFFFFF")
-          .attr("opacity", 0.9);
      } else {
        // Default/Unknown - holographic hexagon
        const hexRadius = nodeRadius * 0.6;
@@ -1013,43 +907,9 @@
          .attr("stroke-width", strokeWidth);
      }

-      // --- LITE badge for lite nodes ---
-      if (isLiteNode) {
-        const badgeX = nodeInfo.x + iconBaseWidth / 2 + 4;
-        const badgeY = nodeInfo.y - iconBaseHeight / 2 - 2;
-        const badgeFontSize = Math.max(9, nodeRadius * 0.12);
-        const badgePadH = 4;
-        const badgePadV = 2;
-        const badgeWidth = badgeFontSize * 2.8 + badgePadH * 2;
-        const badgeHeight = badgeFontSize + badgePadV * 2;
-
-        nodeG
-          .append("rect")
-          .attr("x", badgeX)
-          .attr("y", badgeY)
-          .attr("width", badgeWidth)
-          .attr("height", badgeHeight)
-          .attr("rx", 3)
-          .attr("fill", "rgba(255,215,0,0.15)")
-          .attr("stroke", "rgba(255,215,0,0.6)")
-          .attr("stroke-width", 1);
-
-        nodeG
-          .append("text")
-          .attr("x", badgeX + badgeWidth / 2)
-          .attr("y", badgeY + badgeHeight / 2)
-          .attr("text-anchor", "middle")
-          .attr("dominant-baseline", "central")
-          .attr("fill", "rgba(255,215,0,0.9)")
-          .attr("font-size", badgeFontSize)
-          .attr("font-weight", "700")
-          .attr("font-family", "SF Mono, Monaco, monospace")
-          .text("LITE");
-      }
-
      // --- Vertical GPU Bar (right side of icon) ---
-      // Show in both full mode and minimized mode (scaled appropriately), but not for lite nodes
-      if ((showFullLabels || isMinimized) && !isLiteNode) {
+      // Show in both full mode and minimized mode (scaled appropriately)
+      if (showFullLabels || isMinimized) {
        const gpuBarWidth = isMinimized
          ? Math.max(16, nodeRadius * 0.32)
          : Math.max(28, nodeRadius * 0.3);
@@ -1260,17 +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)";
@@ -1278,46 +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})` : ""}`,
-            );
        }
      }
    });
@@ -49,8 +49,6 @@ export interface NodeInfo {
  };
  last_macmon_update: number;
  friendly_name?: string;
-  os_version?: string;
-  node_type?: string;
 }

 export interface TopologyEdge {
@@ -58,8 +56,6 @@ export interface TopologyEdge {
  target: string;
  sendBackIp?: string;
  sendBackInterface?: string;
-  sourceRdmaIface?: string;
-  sinkRdmaIface?: string;
 }

 export interface TopologyData {
@@ -80,9 +76,6 @@ interface RawNodeIdentity {
  modelId?: string;
  chipId?: string;
  friendlyName?: string;
-  osVersion?: string;
-  osBuildVersion?: string;
-  nodeType?: string;
 }

 interface RawMemoryUsage {
@@ -232,19 +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,
@@ -298,7 +278,6 @@ export interface Conversation {
  modelId: string | null;
  sharding: string | null;
  instanceType: string | null;
-  enableThinking: boolean | null;
 }

 const STORAGE_KEY = "exo-conversations";
@@ -446,8 +425,6 @@ function transformTopology(
      },
      last_macmon_update: Date.now() / 1000,
      friendly_name: identity?.friendlyName,
-      os_version: identity?.osVersion,
-      node_type: identity?.nodeType,
    };
  }

@@ -460,8 +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) {
@@ -469,23 +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 });
          }
        }
      }
@@ -528,32 +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,
@@ -609,7 +551,6 @@ class AppStore {
          modelId: conversation.modelId ?? null,
          sharding: conversation.sharding ?? null,
          instanceType: conversation.instanceType ?? null,
-          enableThinking: conversation.enableThinking ?? null,
        }));
      }
    } catch (error) {
@@ -799,7 +740,6 @@ class AppStore {
      modelId: derivedModelId,
      sharding: derivedSharding,
      instanceType: derivedInstanceType,
-      enableThinking: null,
    };

    this.conversations.unshift(conversation);
@@ -825,7 +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;
@@ -1267,15 +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
@@ -1939,11 +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)
   */
@@ -2122,7 +2047,6 @@ class AppStore {
      textContent?: string;
      preview?: string;
    }[],
-    enableThinking?: boolean | null,
  ): Promise<void> {
    if ((!content.trim() && (!files || files.length === 0)) || this.isLoading)
      return;
@@ -2270,9 +2194,6 @@ class AppStore {
          stream: true,
          logprobs: true,
          top_logprobs: 5,
-          ...(enableThinking != null && {
-            enable_thinking: enableThinking,
-          }),
        }),
      });

@@ -2931,18 +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
   */
@@ -3049,14 +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();
@@ -3072,8 +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 = (
@@ -3116,8 +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;
@@ -3134,12 +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;

@@ -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 = $state<RecentEntry[]>([]);
-
-  constructor() {
-    if (browser) {
-      this.loadFromStorage();
-    }
-  }
-
-  private loadFromStorage() {
-    try {
-      const stored = localStorage.getItem(RECENTS_KEY);
-      if (stored) {
-        const parsed = JSON.parse(stored) as RecentEntry[];
-        this.recents = parsed;
-      }
-    } catch (error) {
-      console.error("Failed to load recent models:", error);
-    }
-  }
-
-  private saveToStorage() {
-    try {
-      localStorage.setItem(RECENTS_KEY, JSON.stringify(this.recents));
-    } catch (error) {
-      console.error("Failed to save recent models:", error);
-    }
-  }
-
-  recordLaunch(modelId: string) {
-    // Remove existing entry for this model (if any) to move it to top
-    const filtered = this.recents.filter((r) => r.modelId !== modelId);
-    // Prepend new entry
-    const next = [{ modelId, launchedAt: Date.now() }, ...filtered];
-    // Cap at max
-    this.recents = next.slice(0, MAX_RECENT_MODELS);
-    this.saveToStorage();
-  }
-
-  getRecentModelIds(): string[] {
-    return this.recents.map((r) => r.modelId);
-  }
-
-  hasAny(): boolean {
-    return this.recents.length > 0;
-  }
-
-  clearAll() {
-    this.recents = [];
-    this.saveToStorage();
-  }
-}
-
-export const recentsStore = new RecentsStore();
-
-export const hasRecents = () => recentsStore.hasAny();
-export const getRecentModelIds = () => recentsStore.getRecentModelIds();
-export const getRecentEntries = () => recentsStore.recents;
-export const recordRecentLaunch = (modelId: string) =>
-  recentsStore.recordLaunch(modelId);
-export const clearRecents = () => recentsStore.clearAll();
@@ -12,11 +12,6 @@
    toggleFavorite,
    getFavoritesSet,
  } from "$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";
@@ -70,51 +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 full macOS nodes (version starts with a digit, e.g. "15.3"), excluding lite nodes
-    const macosNodes = entries.filter(([_, id]) => {
-      if (id.nodeType === "lite") return false;
-      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];
@@ -147,12 +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
@@ -170,10 +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(() => {
@@ -191,19 +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(
@@ -302,10 +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);
@@ -528,41 +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
@@ -639,9 +534,7 @@
        models = data.data || [];
        // Restore last launch defaults if available
        const currentNodeCount = topologyData()
-          ? Object.values(topologyData()!.nodes).filter(
-              (n) => n.node_type !== "lite",
-            ).length
+          ? Object.keys(topologyData()!.nodes).length
          : 1;
        applyLaunchDefaults(models, currentNodeCount);
      }
@@ -737,9 +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 = () => {
@@ -1649,12 +1539,7 @@
    saveLaunchDefaults();
  }

-  const totalNodeCount = $derived(data ? Object.keys(data.nodes).length : 0);
-  const fullNodeCount = $derived(
-    data
-      ? Object.values(data.nodes).filter((n) => n.node_type !== "lite").length
-      : 0,
-  );
+  const nodeCount = $derived(data ? Object.keys(data.nodes).length : 0);
  const instanceCount = $derived(Object.keys(instanceData).length);

  // Helper to get the number of nodes in a placement preview
@@ -1667,7 +1552,7 @@
  }

  // Available min nodes options based on topology (like old dashboard)
-  const availableMinNodes = $derived(Math.max(1, fullNodeCount));
+  const availableMinNodes = $derived(Math.max(1, nodeCount));

  // Compute which min node values have valid previews for the current model/sharding/instance type
  // A minNodes value N is valid if there exists a placement with nodeCount >= N
@@ -1760,263 +1645,18 @@
  // Calculate total memory usage across all nodes
  const clusterMemory = $derived(() => {
    if (!data) return { used: 0, total: 0 };
-    return Object.values(data.nodes)
-      .filter((n) => n.node_type !== "lite")
-      .reduce(
-        (acc, n) => {
-          const total =
-            n.macmon_info?.memory?.ram_total ?? n.system_info?.memory ?? 0;
-          const used = n.macmon_info?.memory?.ram_usage ?? 0;
-          return { used: acc.used + used, total: acc.total + total };
-        },
-        { used: 0, total: 0 },
-      );
+    return Object.values(data.nodes).reduce(
+      (acc, n) => {
+        const total =
+          n.macmon_info?.memory?.ram_total ?? n.system_info?.memory ?? 0;
+        const used = n.macmon_info?.memory?.ram_usage ?? 0;
+        return { used: acc.used + used, total: acc.total + total };
+      },
+      { used: 0, total: 0 },
+    );
  });
 </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}
@@ -2084,40 +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"
@@ -2126,10 +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}

@@ -2176,21 +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"
@@ -2199,62 +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}

@@ -2293,7 +1954,6 @@
                showHelperText={false}
                showModelSelector={true}
                modelTasks={modelTasks()}
-                modelCapabilities={modelCapabilities()}
              />
            </div>
          </div>
@@ -3073,7 +2733,6 @@
                placeholder="Ask anything"
                showModelSelector={true}
                modelTasks={modelTasks()}
-                modelCapabilities={modelCapabilities()}
              />
            </div>
          </div>
@@ -3101,7 +2760,7 @@
                  TOPOLOGY
                </div>
                <span class="text-xs text-white/70 tabular-nums"
-                  >{totalNodeCount} {totalNodeCount === 1 ? "NODE" : "NODES"}</span
+                  >{nodeCount} {nodeCount === 1 ? "NODE" : "NODES"}</span
                >
              </div>

@@ -3114,7 +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>

@@ -3570,17 +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}
@@ -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";
@@ -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";
-  };
-}
@@ -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="
-  }
-}
@@ -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}")
@@ -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]
@@ -132,7 +129,7 @@ markers = [
 env = [
  "EXO_TESTS=1"
 ]
-addopts = "-m 'not slow' --ignore=tests/start_distributed_test.py"
+addopts = "-m 'not slow'"
 filterwarnings = [
    "ignore:builtin type Swig:DeprecationWarning",
 ]
@@ -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
-          '';
      };
    };
 }
@@ -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
@@ -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
@@ -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
@@ -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
@@ -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
@@ -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
@@ -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
@@ -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
@@ -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
@@ -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
@@ -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
@@ -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
@@ -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
@@ -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
@@ -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
@@ -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
@@ -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
@@ -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
@@ -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
@@ -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
@@ -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
@@ -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)
@@ -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()
@@ -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 }
@@ -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()
+        }
+    }
+}
@@ -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()
+    }
+}
@@ -14,7 +14,6 @@ from exo.download.download_utils import (
    map_repo_download_progress_to_download_progress_data,
 )
 from exo.download.shard_downloader import ShardDownloader
-from exo.shared.constants import EXO_MODELS_DIR
 from exo.shared.models.model_cards import ModelId
 from exo.shared.types.commands import (
    CancelDownload,
@@ -57,54 +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)
-
-    def _model_dir(self, model_id: ModelId) -> str:
-        return str(EXO_MODELS_DIR / model_id.normalize())
-
-    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,
-                model_directory=self._model_dir(model_id),
-            )
-            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
-                ),
-                model_directory=self._model_dir(model_id),
-            )
-            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")
@@ -166,21 +119,17 @@ 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

        # Emit pending status
-        progress = DownloadPending(
-            shard_metadata=shard,
-            node_id=self.node_id,
-            model_directory=self._model_dir(model_id),
-        )
+        progress = DownloadPending(shard_metadata=shard, node_id=self.node_id)
        self.download_status[model_id] = progress
        await self.event_sender.send(NodeDownloadProgress(download_progress=progress))

@@ -194,7 +143,6 @@ class DownloadCoordinator:
                shard_metadata=shard,
                node_id=self.node_id,
                total_bytes=initial_progress.total_bytes,
-                model_directory=self._model_dir(model_id),
            )
            self.download_status[model_id] = completed
            await self.event_sender.send(
@@ -217,11 +165,50 @@ class DownloadCoordinator:
            download_progress=map_repo_download_progress_to_download_progress_data(
                initial_progress
            ),
-            model_directory=self._model_dir(model_id),
        )
        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)
@@ -231,7 +218,6 @@ class DownloadCoordinator:
                    shard_metadata=shard,
                    node_id=self.node_id,
                    error_message=str(e),
-                    model_directory=self._model_dir(model_id),
                )
                self.download_status[model_id] = failed
                await self.event_sender.send(
@@ -266,7 +252,6 @@ class DownloadCoordinator:
            pending = DownloadPending(
                shard_metadata=current_status.shard_metadata,
                node_id=self.node_id,
-                model_directory=self._model_dir(model_id),
            )
            await self.event_sender.send(
                NodeDownloadProgress(download_progress=pending)
@@ -298,29 +283,16 @@ 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,
                            shard_metadata=progress.shard,
                            total_bytes=progress.total_bytes,
-                            model_directory=self._model_dir(
-                                progress.shard.model_card.model_id
-                            ),
                        )
                    elif progress.status in ["in_progress", "not_started"]:
                        if progress.downloaded_bytes_this_session.in_bytes == 0:
                            status = DownloadPending(
-                                node_id=self.node_id,
-                                shard_metadata=progress.shard,
-                                model_directory=self._model_dir(
-                                    progress.shard.model_card.model_id
-                                ),
+                                node_id=self.node_id, shard_metadata=progress.shard
                            )
                        else:
                            status = DownloadOngoing(
@@ -329,9 +301,6 @@ class DownloadCoordinator:
                                download_progress=map_repo_download_progress_to_download_progress_data(
                                    progress
                                ),
-                                model_directory=self._model_dir(
-                                    progress.shard.model_card.model_id
-                                ),
                            )
                    else:
                        continue
@@ -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
@@ -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
@@ -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
+    )
--- a/Show More
+++ b/Show More
Author	SHA1	Message	Date
Ryuichi Leo Takashige	11f9e2e1d8	fix chat completions call_	2026-02-06 18:44:34 +00:00
Ryuichi Leo Takashige	870d53329b	fix tool calling again	2026-02-06 18:26:11 +00:00
Ryuichi Leo Takashige	4dc8654ee7	move	2026-02-06 17:36:53 +00:00
Ryuichi Leo Takashige	76d7994fa1	Fix kimi tool calling id	2026-02-06 17:31:55 +00:00
Ryuichi Leo Takashige	2c1b8f79b2	Fix kimi tool calling id	2026-02-06 17:17:36 +00:00