fix: pass _cancel_sender in RunnerSupervisor test helper

After merging main (api cancellation #1276), the RunnerSupervisor
dataclass requires a _cancel_sender field. Update the test helper
to create and pass this channel.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

.dockerignore

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

.github/workflows/e2e.yml

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

.mlx_typings/mlx/core/__init__.pyi

@@ -215,22 +215,6 @@ class StreamContext:
         traceback: object | None = ...,
     ) -> None: ...
 
-def device_info() -> dict[str, str | int]:
-    """
-    Get information about the GPU device and system settings.
-
-    Currently returns:
-
-    * ``architecture``
-    * ``max_buffer_size``
-    * ``max_recommended_working_set_size``
-    * ``memory_size``
-    * ``resource_limit``
-
-    Returns:
-        dict: A dictionary with string keys and string or integer values.
-    """
-
 def abs(a: array, /, *, stream: Stream | Device | None = ...) -> array:
     """
     Element-wise absolute value.

.mlx_typings/mlx/nn/layers/base.pyi

@@ -200,7 +200,7 @@ class Module(dict):
     ) -> mx.MX_ARRAY_TREE:  # -> dict[Any, Any | dict[Any, Any | dict[Any, Any] | list[Any]] | dict[Any, Any] | list[Any]]:
         """Return the submodules that do not contain other modules."""
 
-    def update(self, parameters: dict[str, Any], strict: bool = ...) -> Module:
+    def update(self, parameters: dict, strict: bool = ...) -> Module:
         """Replace the parameters of this Module with the provided ones in the
         dict of dicts and lists.
 

.mlx_typings/mlx/utils.pyi

@@ -7,10 +7,7 @@ from typing import Any, Callable, Dict, List, Optional, Tuple, Union
 from mlx.core import MX_ARRAY_TREE
 
 def tree_map(
-    fn: Callable[..., Any],
-    tree: Any,
-    *rest: Any,
-    is_leaf: Callable[..., bool] | None = ...,
+    fn: Callable, tree: Any, *rest: Any, is_leaf: Optional[Callable] = ...
 ) -> Any:
     """Applies ``fn`` to the leaves of the Python tree ``tree`` and
     returns a new collection with the results.
@@ -47,11 +44,11 @@ def tree_map(
     """
 
 def tree_map_with_path(
-    fn: Callable[..., Any],
+    fn: Callable,
     tree: Any,
     *rest: Any,
-    is_leaf: Callable[..., bool] | None = ...,
-    path: str | None = ...,
+    is_leaf: Optional[Callable] = ...,
+    path: Optional[Any] = ...,
 ) -> Any:
     """Applies ``fn`` to the path and leaves of the Python tree ``tree`` and
     returns a new collection with the results.
@@ -83,9 +80,9 @@ def tree_map_with_path(
 def tree_flatten(
     tree: Any,
     prefix: str = ...,
-    is_leaf: Callable[..., bool] | None = ...,
-    destination: list[tuple[str, Any]] | dict[str, Any] | None = ...,
-) -> list[tuple[str, Any]] | dict[str, Any]:
+    is_leaf: Optional[Callable] = ...,
+    destination: Optional[Union[List[Tuple[str, Any]], Dict[str, Any]]] = ...,
+) -> Union[List[Tuple[str, Any]], Dict[str, Any]]:
     """Flattens a Python tree to a list of key, value tuples.
 
     The keys are using the dot notation to define trees of arbitrary depth and
@@ -121,7 +118,7 @@ def tree_flatten(
             the Python tree.
     """
 
-def tree_unflatten(tree: list[tuple[str, Any]] | dict[str, Any]) -> Any:
+def tree_unflatten(tree: Union[List[Tuple[str, Any]], Dict[str, Any]]) -> Any:
     """Recreate a Python tree from its flat representation.
 
     .. code-block:: python

.mlx_typings/mlx_lm/generate.pyi

@@ -73,11 +73,9 @@ class GenerationResponse:
     finish_reason: Optional[str] = ...
 
 def maybe_quantize_kv_cache(
-    prompt_cache: Any,
-    quantized_kv_start: int | None,
-    kv_group_size: int | None,
-    kv_bits: int | None,
-) -> None: ...
+    prompt_cache, quantized_kv_start, kv_group_size, kv_bits
+):  # -> None:
+    ...
 def generate_step(
     prompt: mx.array,
     model: nn.Module,

.mlx_typings/mlx_lm/models/cache.pyi

@@ -16,7 +16,7 @@ class Cache(Protocol):
         self, keys: mx.array, values: mx.array
     ) -> tuple[mx.array, mx.array]: ...
     @property
-    def state(self) -> tuple[mx.array | None, mx.array | None]: ...
+    def state(self) -> tuple[mx.array, mx.array]: ...
     @state.setter
     def state(self, v) -> None: ...
 
@@ -92,14 +92,13 @@ class _BaseCache(Cache):
     values: mx.array
     offset: int
     @property
-    def state(self) -> tuple[mx.array | None, mx.array | None]: ...
+    def state(self) -> tuple[mx.array, mx.array]: ...
     @state.setter
     def state(self, v) -> None: ...
     @property
     def meta_state(self) -> Literal[""]: ...
     @meta_state.setter
     def meta_state(self, v) -> None: ...
-    def trim(self, n: int) -> int: ...
     def is_trimmable(self) -> Literal[False]: ...
     @classmethod
     def from_state(cls, state, meta_state) -> Self: ...
@@ -115,13 +114,15 @@ class ConcatenateKVCache(_BaseCache):
     def update_and_fetch(self, keys, values):  # -> tuple[Any | array, Any | array]:
         ...
     @property
-    def state(self) -> tuple[mx.array | None, mx.array | None]: ...
+    def state(self):  # -> tuple[Any | array | None, Any | array | None]:
+        ...
     @state.setter
     def state(self, v):  # -> None:
         ...
     def is_trimmable(self):  # -> Literal[True]:
         ...
-    def trim(self, n: int) -> int: ...
+    def trim(self, n):  # -> int:
+        ...
     def make_mask(self, *args, **kwargs):  # -> array | Literal['causal'] | None:
         ...
 
@@ -131,7 +132,10 @@ class QuantizedKVCache(_BaseCache):
     def update_and_fetch(self, keys, values):  # -> Any:
         ...
     @property
-    def state(self) -> tuple[mx.array | None, mx.array | None]: ...
+    def state(
+        self,
+    ):  # -> tuple[Any | tuple[array, array, array] | None, Any | tuple[array, array, array] | None] | Any:
+        ...
     @state.setter
     def state(self, v):  # -> None:
         ...
@@ -143,7 +147,8 @@ class QuantizedKVCache(_BaseCache):
         ...
     def is_trimmable(self):  # -> Literal[True]:
         ...
-    def trim(self, n: int) -> int: ...
+    def trim(self, n):  # -> int:
+        ...
     def make_mask(self, *args, **kwargs):  # -> array | Literal['causal'] | None:
         ...
 
@@ -155,18 +160,18 @@ class KVCache(_BaseCache):
     @property
     def state(
         self,
-    ) -> tuple[mx.array | None, mx.array | None]: ...
+    ) -> tuple[array, array]: ...
     @state.setter
     def state(self, v) -> None: ...
     def is_trimmable(self):  # -> Literal[True]:
         ...
-    def trim(self, n: int) -> int: ...
+    def trim(self, n):  # -> int:
+        ...
     def to_quantized(
         self, group_size: int = ..., bits: int = ...
     ) -> QuantizedKVCache: ...
-    def make_mask(
-        self, *args: Any, **kwargs: Any
-    ) -> mx.array | Literal["causal"] | None: ...
+    def make_mask(self, *args, **kwargs):  # -> array | Literal['causal'] | None:
+        ...
 
 class RotatingKVCache(_BaseCache):
     step = ...
@@ -178,7 +183,8 @@ class RotatingKVCache(_BaseCache):
     @property
     def state(
         self,
-    ) -> tuple[mx.array | None, mx.array | None]: ...
+    ):  # -> tuple[Any | array, Any | array] | tuple[Any | array | None, Any | array | None]:
+        ...
     @state.setter
     def state(self, v):  # -> None:
         ...
@@ -190,7 +196,8 @@ class RotatingKVCache(_BaseCache):
         ...
     def is_trimmable(self):  # -> bool:
         ...
-    def trim(self, n: int) -> int: ...
+    def trim(self, n):  # -> int:
+        ...
     def to_quantized(
         self, group_size: int = ..., bits: int = ...
     ) -> QuantizedKVCache: ...
@@ -205,7 +212,8 @@ class ArraysCache(_BaseCache):
         ...
     def __getitem__(self, idx): ...
     @property
-    def state(self) -> tuple[mx.array | None, mx.array | None]: ...
+    def state(self):  # -> list[Any | array] | list[array]:
+        ...
     @state.setter
     def state(self, v):  # -> None:
         ...
@@ -219,7 +227,8 @@ class ArraysCache(_BaseCache):
         In-place extend this cache with the other cache.
         """
 
-    def make_mask(self, N: int) -> mx.array | None: ...
+    def make_mask(self, N: int):  # -> array | None:
+        ...
 
 class MambaCache(ArraysCache):
     def __init__(self, left_padding: Optional[List[int]] = ...) -> None: ...
@@ -230,7 +239,8 @@ class ChunkedKVCache(KVCache):
         ...
     def update_and_fetch(self, keys, values):  # -> tuple[array, array]:
         ...
-    def trim(self, n: int) -> int: ...
+    def trim(self, n):  # -> int:
+        ...
     @property
     def meta_state(self):  # -> tuple[str, ...]:
         ...
@@ -243,9 +253,10 @@ class CacheList(_BaseCache):
     def __getitem__(self, idx): ...
     def is_trimmable(self):  # -> bool:
         ...
-    def trim(self, n: int) -> int: ...
+    def trim(self, n): ...
     @property
-    def state(self) -> list[tuple[mx.array | None, mx.array | None]]: ...
+    def state(self):  # -> list[Any]:
+        ...
     @state.setter
     def state(self, v):  # -> None:
         ...

.mlx_typings/mlx_lm/models/glm_moe_dsa.pyi

@@ -1,46 +0,0 @@
-"""Type stubs for mlx_lm.models.glm_moe_dsa"""
-
-from dataclasses import dataclass
-from typing import Any, Dict, Optional
-
-from .base import BaseModelArgs
-from .deepseek_v32 import Model as DSV32Model
-
-@dataclass
-class ModelArgs(BaseModelArgs):
-    model_type: str
-    vocab_size: int
-    hidden_size: int
-    index_head_dim: int
-    index_n_heads: int
-    index_topk: int
-    intermediate_size: int
-    moe_intermediate_size: int
-    num_hidden_layers: int
-    num_attention_heads: int
-    num_key_value_heads: int
-    n_shared_experts: Optional[int]
-    n_routed_experts: Optional[int]
-    routed_scaling_factor: float
-    kv_lora_rank: int
-    q_lora_rank: int
-    qk_rope_head_dim: int
-    v_head_dim: int
-    qk_nope_head_dim: int
-    topk_method: str
-    scoring_func: str
-    norm_topk_prob: bool
-    n_group: int
-    topk_group: int
-    num_experts_per_tok: int
-    moe_layer_freq: int
-    first_k_dense_replace: int
-    max_position_embeddings: int
-    rms_norm_eps: float
-    rope_parameters: Dict[str, Any]
-    attention_bias: bool
-    rope_scaling: Dict[str, Any] | None
-    rope_theta: float | None
-
-class Model(DSV32Model):
-    def __init__(self, config: ModelArgs) -> None: ...

.mlx_typings/mlx_lm/models/qwen3_5.pyi

@@ -1,153 +0,0 @@
-from dataclasses import dataclass
-from typing import Any, Optional
-
-import mlx.core as mx
-import mlx.nn as nn
-
-from .cache import ArraysCache, KVCache
-from .qwen3_next import (
-    Qwen3NextAttention as Attention,
-    Qwen3NextMLP as MLP,
-    Qwen3NextRMSNormGated as RMSNormGated,
-    Qwen3NextSparseMoeBlock,
-)
-
-SparseMoeBlock = Qwen3NextSparseMoeBlock
-from .switch_layers import SwitchGLU
-
-@dataclass
-class TextModelArgs:
-    model_type: str
-    hidden_size: int
-    intermediate_size: int
-    num_hidden_layers: int
-    num_attention_heads: int
-    rms_norm_eps: float
-    vocab_size: int
-    num_key_value_heads: int
-    max_position_embeddings: int
-    linear_num_value_heads: int
-    linear_num_key_heads: int
-    linear_key_head_dim: int
-    linear_value_head_dim: int
-    linear_conv_kernel_dim: int
-    tie_word_embeddings: bool
-    attention_bias: bool
-    head_dim: Optional[int]
-    full_attention_interval: int
-    num_experts: int
-    num_experts_per_tok: int
-    decoder_sparse_step: int
-    shared_expert_intermediate_size: int
-    moe_intermediate_size: int
-    norm_topk_prob: bool
-    rope_parameters: Optional[dict[str, Any]]
-    partial_rotary_factor: float
-    rope_theta: float
-    rope_scaling: Optional[dict[str, Any]]
-
-    @classmethod
-    def from_dict(cls, params: dict[str, Any]) -> TextModelArgs: ...
-    def __post_init__(self) -> None: ...
-
-class GatedDeltaNet(nn.Module):
-    hidden_size: int
-    num_v_heads: int
-    num_k_heads: int
-    head_k_dim: int
-    head_v_dim: int
-    key_dim: int
-    value_dim: int
-    conv_kernel_size: int
-    conv_dim: int
-    conv1d: nn.Conv1d
-    in_proj_qkv: nn.Linear
-    in_proj_z: nn.Linear
-    in_proj_b: nn.Linear
-    in_proj_a: nn.Linear
-    dt_bias: mx.array
-    A_log: mx.array
-    norm: RMSNormGated
-    out_proj: nn.Linear
-
-    def __init__(self, config: TextModelArgs) -> None: ...
-    def __call__(
-        self,
-        inputs: mx.array,
-        mask: Optional[mx.array] = None,
-        cache: Optional[Any] = None,
-    ) -> mx.array: ...
-
-class DecoderLayer(nn.Module):
-    is_linear: bool
-    linear_attn: GatedDeltaNet
-    self_attn: Attention
-    input_layernorm: nn.RMSNorm
-    post_attention_layernorm: nn.RMSNorm
-    mlp: MLP | SparseMoeBlock
-
-    def __init__(self, args: TextModelArgs, layer_idx: int) -> None: ...
-    def __call__(
-        self,
-        x: mx.array,
-        mask: Optional[mx.array] = None,
-        cache: Optional[Any] = None,
-    ) -> mx.array: ...
-
-class Qwen3_5TextModel(nn.Module):
-    embed_tokens: nn.Embedding
-    layers: list[DecoderLayer]
-    norm: nn.RMSNorm
-    ssm_idx: int
-    fa_idx: int
-
-    def __init__(self, args: TextModelArgs) -> None: ...
-    def __call__(
-        self,
-        inputs: mx.array,
-        cache: Optional[Any] = None,
-        input_embeddings: Optional[mx.array] = None,
-    ) -> mx.array: ...
-
-class TextModel(nn.Module):
-    args: TextModelArgs
-    model_type: str
-    model: Qwen3_5TextModel
-    lm_head: nn.Linear
-
-    def __init__(self, args: TextModelArgs) -> None: ...
-    def __call__(
-        self,
-        inputs: mx.array,
-        cache: Optional[Any] = None,
-        input_embeddings: Optional[mx.array] = None,
-    ) -> mx.array: ...
-    @property
-    def layers(self) -> list[DecoderLayer]: ...
-    def make_cache(self) -> list[ArraysCache | KVCache]: ...
-    def sanitize(self, weights: dict[str, Any]) -> dict[str, Any]: ...
-
-@dataclass
-class ModelArgs:
-    model_type: str
-    text_config: dict[str, Any]
-
-    @classmethod
-    def from_dict(cls, params: dict[str, Any]) -> ModelArgs: ...
-
-class Model(nn.Module):
-    args: ModelArgs
-    model_type: str
-    language_model: TextModel
-
-    def __init__(self, args: ModelArgs) -> None: ...
-    def __call__(
-        self,
-        inputs: mx.array,
-        cache: Optional[Any] = None,
-        input_embeddings: Optional[mx.array] = None,
-    ) -> mx.array: ...
-    def sanitize(self, weights: dict[str, Any]) -> dict[str, Any]: ...
-    @property
-    def layers(self) -> list[DecoderLayer]: ...
-    def make_cache(self) -> list[ArraysCache | KVCache]: ...

.mlx_typings/mlx_lm/models/qwen3_5_moe.pyi

@@ -1,19 +0,0 @@
-from dataclasses import dataclass
-from typing import Any, Optional
-
-import mlx.core as mx
-import mlx.nn as nn
-
-from .cache import ArraysCache, KVCache
-from .qwen3_5 import DecoderLayer, Model as Qwen3_5Model, TextModel
-
-@dataclass
-class ModelArgs:
-    model_type: str
-    text_config: dict[str, Any]
-
-    @classmethod
-    def from_dict(cls, params: dict[str, Any]) -> ModelArgs: ...
-
-class Model(Qwen3_5Model):
-    def sanitize(self, weights: dict[str, Any]) -> dict[str, Any]: ...

.mlx_typings/mlx_lm/models/qwen3_next.pyi

@@ -7,15 +7,6 @@ import mlx.nn as nn
 
 from .switch_layers import SwitchGLU
 
-class Qwen3NextRMSNormGated(nn.Module):
-    eps: float
-    weight: mx.array
-
-    def __init__(self, hidden_size: int, eps: float = ...) -> None: ...
-    def __call__(
-        self, hidden_states: mx.array, gate: mx.array | None = None
-    ) -> mx.array: ...
-
 class Qwen3NextMLP(nn.Module):
     gate_proj: nn.Linear
     down_proj: nn.Linear

Cargo.lock

@@ -141,6 +141,12 @@ version = "0.3.9"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "76a2e8124351fda1ef8aaaa3bbd7ebbcb486bbcd4225aca0aa0d84bb2db8fecb"
 
+[[package]]
+name = "arrayvec"
+version = "0.7.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7c02d123df017efcdfbd739ef81735b36c5ba83ec3c59c80a9d7ecc718f92e50"
+
 [[package]]
 name = "asn1-rs"
 version = "0.7.1"
@@ -216,28 +222,6 @@ dependencies = [
  "windows-sys 0.61.2",
 ]
 
-[[package]]
-name = "async-stream"
-version = "0.3.6"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "0b5a71a6f37880a80d1d7f19efd781e4b5de42c88f0722cc13bcb6cc2cfe8476"
-dependencies = [
- "async-stream-impl",
- "futures-core",
- "pin-project-lite",
-]
-
-[[package]]
-name = "async-stream-impl"
-version = "0.3.6"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c7c24de15d275a1ecfd47a380fb4d5ec9bfe0933f309ed5e705b775596a3574d"
-dependencies = [
- "proc-macro2",
- "quote",
- "syn 2.0.111",
-]
-
 [[package]]
 name = "async-trait"
 version = "0.1.89"
@@ -320,6 +304,19 @@ version = "1.8.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "55248b47b0caf0546f7988906588779981c43bb1bc9d0c44087278f80cdb44ba"
 
+[[package]]
+name = "bigdecimal"
+version = "0.4.9"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "560f42649de9fa436b73517378a147ec21f6c997a546581df4b4b31677828934"
+dependencies = [
+ "autocfg",
+ "libm",
+ "num-bigint",
+ "num-integer",
+ "num-traits",
+]
+
 [[package]]
 name = "bimap"
 version = "0.6.3"
@@ -519,6 +516,15 @@ version = "0.4.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "2f421161cb492475f1661ddc9815a745a1c894592070661180fdec3d4872e9c3"
 
+[[package]]
+name = "convert_case"
+version = "0.10.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "633458d4ef8c78b72454de2d54fd6ab2e60f9e02be22f3c6104cdc8a4e0fceb9"
+dependencies = [
+ "unicode-segmentation",
+]
+
 [[package]]
 name = "core-foundation"
 version = "0.9.4"
@@ -740,6 +746,29 @@ dependencies = [
  "powerfmt",
 ]
 
+[[package]]
+name = "derive_more"
+version = "2.1.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "10b768e943bed7bf2cab53df09f4bc34bfd217cdb57d971e769874c9a6710618"
+dependencies = [
+ "derive_more-impl",
+]
+
+[[package]]
+name = "derive_more-impl"
+version = "2.1.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "6d286bfdaf75e988b4a78e013ecd79c581e06399ab53fbacd2d916c2f904f30b"
+dependencies = [
+ "convert_case",
+ "proc-macro2",
+ "quote",
+ "rustc_version",
+ "syn 2.0.111",
+ "unicode-xid",
+]
+
 [[package]]
 name = "digest"
 version = "0.10.7"
@@ -910,17 +939,22 @@ name = "exo_pyo3_bindings"
 version = "0.0.1"
 dependencies = [
  "delegate",
+ "derive_more",
  "env_logger",
  "extend",
- "futures-lite",
+ "futures",
+ "impl-trait-for-tuples",
  "libp2p",
  "log",
  "networking",
+ "once_cell",
  "pin-project",
  "pyo3",
  "pyo3-async-runtimes",
  "pyo3-log",
  "pyo3-stub-gen",
+ "thiserror 2.0.17",
+ "thread_local",
  "tokio",
  "util",
 ]
@@ -936,12 +970,6 @@ dependencies = [
  "syn 2.0.111",
 ]
 
-[[package]]
-name = "fastrand"
-version = "2.3.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "37909eebbb50d72f9059c3b6d82c0463f2ff062c9e95845c43a6c9c0355411be"
-
 [[package]]
 name = "ff"
 version = "0.13.1"
@@ -1050,10 +1078,7 @@ version = "2.6.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "f78e10609fe0e0b3f4157ffab1876319b5b0db102a2c60dc4626306dc46b44ad"
 dependencies = [
- "fastrand",
  "futures-core",
- "futures-io",
- "parking",
  "pin-project-lite",
 ]
 
@@ -1615,6 +1640,17 @@ dependencies = [
  "xmltree",
 ]
 
+[[package]]
+name = "impl-trait-for-tuples"
+version = "0.2.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a0eb5a3343abf848c0984fe4604b2b105da9539376e24fc0a3b0007411ae4fd9"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn 2.0.111",
+]
+
 [[package]]
 name = "indexmap"
 version = "2.12.1"
@@ -1793,6 +1829,12 @@ version = "0.2.178"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "37c93d8daa9d8a012fd8ab92f088405fb202ea0b6ab73ee2482ae66af4f42091"
 
+[[package]]
+name = "libm"
+version = "0.2.15"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f9fbbcab51052fe104eb5e5d351cf728d30a5be1fe14d9be8a3b097481fb97de"
+
 [[package]]
 name = "libp2p"
 version = "0.56.0"
@@ -2781,16 +2823,17 @@ dependencies = [
 name = "networking"
 version = "0.0.1"
 dependencies = [
- "async-stream",
  "delegate",
+ "derive_more",
  "either",
  "extend",
- "futures-lite",
+ "futures",
  "futures-timer",
+ "impl-trait-for-tuples",
  "keccak-const",
  "libp2p",
  "log",
- "pin-project",
+ "thiserror 2.0.17",
  "tokio",
  "tracing-subscriber",
  "util",
@@ -2875,6 +2918,17 @@ dependencies = [
  "num-traits",
 ]
 
+[[package]]
+name = "num-rational"
+version = "0.4.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f83d14da390562dca69fc84082e73e548e1ad308d24accdedd2720017cb37824"
+dependencies = [
+ "num-bigint",
+ "num-integer",
+ "num-traits",
+]
+
 [[package]]
 name = "num-traits"
 version = "0.2.19"
@@ -3225,14 +3279,28 @@ version = "0.27.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "ab53c047fcd1a1d2a8820fe84f05d6be69e9526be40cb03b73f86b6b03e6d87d"
 dependencies = [
+ "bigdecimal",
+ "either",
+ "hashbrown 0.16.1",
+ "indexmap",
  "indoc",
+ "inventory",
  "libc",
+ "lock_api",
  "memoffset",
+ "num-bigint",
+ "num-complex",
+ "num-rational",
+ "num-traits",
  "once_cell",
+ "ordered-float",
+ "parking_lot",
  "portable-atomic",
  "pyo3-build-config",
  "pyo3-ffi",
  "pyo3-macros",
+ "rust_decimal",
+ "smallvec",
  "unindent",
 ]
 
@@ -3673,6 +3741,16 @@ dependencies = [
  "tokio",
 ]
 
+[[package]]
+name = "rust_decimal"
+version = "1.39.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "35affe401787a9bd846712274d97654355d21b2a2c092a3139aabe31e9022282"
+dependencies = [
+ "arrayvec",
+ "num-traits",
+]
+
 [[package]]
 name = "rustc-hash"
 version = "1.1.0"
@@ -4537,12 +4615,24 @@ version = "1.0.22"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "9312f7c4f6ff9069b165498234ce8be658059c6728633667c526e27dc2cf1df5"
 
+[[package]]
+name = "unicode-segmentation"
+version = "1.12.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f6ccf251212114b54433ec949fd6a7841275f9ada20dddd2f29e9ceea4501493"
+
 [[package]]
 name = "unicode-width"
 version = "0.2.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "b4ac048d71ede7ee76d585517add45da530660ef4390e49b098733c6e897f254"
 
+[[package]]
+name = "unicode-xid"
+version = "0.2.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ebc1c04c71510c7f702b52b7c350734c9ff1295c464a03335b00bb84fc54f853"
+
 [[package]]
 name = "unicode_names2"
 version = "1.3.0"

Cargo.toml

@@ -1,6 +1,10 @@
 [workspace]
 resolver = "3"
-members = ["rust/networking", "rust/exo_pyo3_bindings", "rust/util"]
+members = [
+    "rust/networking",
+    "rust/exo_pyo3_bindings",
+    "rust/util",
+]
 
 [workspace.package]
 version = "0.0.1"
@@ -22,21 +26,49 @@ opt-level = 3
 networking = { path = "rust/networking" }
 util = { path = "rust/util" }
 
+# Proc-macro authoring tools
+syn = "2.0"
+quote = "1.0"
+proc-macro2 = "1.0"
+darling = "0.20"
+
 # Macro dependecies
 extend = "1.2"
 delegate = "0.13"
+impl-trait-for-tuples = "0.2"
+clap = "4.5"
+derive_more = { version = "2.0.1", features = ["display"] }
+pin-project = "1"
 
 # Utility dependencies
+itertools = "0.14"
+thiserror = "2"
+internment = "0.8"
+recursion = "0.5"
+regex = "1.11"
+once_cell = "1.21"
+thread_local = "1.1"
+bon = "3.4"
+generativity = "1.1"
+anyhow = "1.0"
 keccak-const = "0.2"
 
+# Functional generics/lenses frameworks
+frunk_core = "0.4"
+frunk = "0.4"
+frunk_utils = "0.2"
+frunk-enum-core = "0.3"
+
 # Async dependencies
-async-stream = "0.3"
 tokio = "1.46"
-futures-lite = "2.6.1"
+futures = "0.3"
+futures-util = "0.3"
 futures-timer = "3.0"
 
 # Data structures
 either = "1.15"
+ordered-float = "5.0"
+ahash = "0.8"
 
 # Tracing/logging
 log = "0.4"

README.md

@@ -72,30 +72,16 @@ There are two ways to run exo:
 
 ### Run from Source (macOS)
 
-If you have [Nix](https://nixos.org/) installed, you can skip most of the steps below and run exo directly:
-
-```bash
-nix run .#exo
-```
-
-**Note:** To accept the Cachix binary cache (and avoid the Xcode Metal ToolChain), add to `/etc/nix/nix.conf`:
-```
-trusted-users = root    (or your username)
-experimental-features = nix-command flakes
-```
-Then restart the Nix daemon: `sudo launchctl kickstart -k system/org.nixos.nix-daemon`
-
 **Prerequisites:**
-- [Xcode](https://developer.apple.com/xcode/) (provides the Metal ToolChain required for MLX compilation)
 - [brew](https://github.com/Homebrew/brew) (for simple package management on macOS)
-
+  
   ```bash
   /bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/HEAD/install.sh)"
   ```
 - [uv](https://github.com/astral-sh/uv) (for Python dependency management)
 - [macmon](https://github.com/vladkens/macmon) (for hardware monitoring on Apple Silicon)
 - [node](https://github.com/nodejs/node) (for building the dashboard)
-
+  
   ```bash
   brew install uv macmon node
   ```

app/EXO/EXO/ContentView.swift

@@ -15,23 +15,14 @@ struct ContentView: View {
     @EnvironmentObject private var localNetworkChecker: LocalNetworkChecker
     @EnvironmentObject private var updater: SparkleUpdater
     @EnvironmentObject private var thunderboltBridgeService: ThunderboltBridgeService
-    @EnvironmentObject private var settingsWindowController: SettingsWindowController
     @State private var focusedNode: NodeViewModel?
     @State private var deletingInstanceIDs: Set<String> = []
     @State private var showAllNodes = false
     @State private var showAllInstances = false
-    @State private var baseURLCopied = false
     @State private var showAdvanced = false
     @State private var showDebugInfo = false
-    private enum BugReportPhase: Equatable {
-        case idle
-        case prompting
-        case sending(String)
-        case success(String)
-        case failure(String)
-    }
-    @State private var bugReportPhase: BugReportPhase = .idle
-    @State private var bugReportUserDescription: String = ""
+    @State private var bugReportInFlight = false
+    @State private var bugReportMessage: String?
     @State private var uninstallInProgress = false
     @State private var pendingNamespace: String = ""
     @State private var pendingHFToken: String = ""
@@ -267,79 +258,139 @@ struct ContentView: View {
         VStack(alignment: .leading, spacing: 0) {
             if controller.status != .stopped {
                 dashboardButton
-                baseURLRow
                 Divider()
                     .padding(.vertical, 8)
             } else {
                 Divider()
                     .padding(.vertical, 4)
             }
-            HoverButton(
-                title: "Settings",
-                tint: .primary,
-                trailingSystemImage: "gear"
-            ) {
-                settingsWindowController.open(
-                    controller: controller,
-                    updater: updater,
-                    networkStatusService: networkStatusService,
-                    thunderboltBridgeService: thunderboltBridgeService,
-                    stateService: stateService
-                )
-            }
-            HoverButton(
-                title: "Check for Updates",
-                tint: .primary,
-                trailingSystemImage: "arrow.triangle.2.circlepath"
-            ) {
-                updater.checkForUpdates()
-            }
-            .padding(.bottom, 8)
-            HoverButton(title: "Quit", tint: .secondary) {
+            advancedSection
+                .padding(.bottom, 8)
+            controlButton(title: "Quit", tint: .secondary) {
                 controller.stop()
                 NSApplication.shared.terminate(nil)
             }
         }
     }
 
-    private var dashboardButton: some View {
-        HoverButton(
-            title: "Web Dashboard",
-            tint: .primary,
-            trailingSystemImage: "arrow.up.right"
-        ) {
-            guard let url = URL(string: "http://localhost:52415/") else { return }
-            NSWorkspace.shared.open(url)
+    private var advancedSection: some View {
+        VStack(alignment: .leading, spacing: 6) {
+            HStack {
+                Text("Advanced")
+                    .font(.caption)
+                    .foregroundColor(.secondary)
+                Spacer()
+                collapseButton(isExpanded: $showAdvanced)
+            }
+            .animation(nil, value: showAdvanced)
+            if showAdvanced {
+                VStack(alignment: .leading, spacing: 8) {
+                    VStack(alignment: .leading, spacing: 4) {
+                        Text("Cluster Namespace")
+                            .font(.caption2)
+                            .foregroundColor(.secondary)
+                        HStack {
+                            TextField("optional", text: $pendingNamespace)
+                                .textFieldStyle(.roundedBorder)
+                                .font(.caption2)
+                                .onAppear {
+                                    pendingNamespace = controller.customNamespace
+                                }
+                            Button("Save & Restart") {
+                                controller.customNamespace = pendingNamespace
+                                if controller.status == .running || controller.status == .starting {
+                                    controller.restart()
+                                }
+                            }
+                            .font(.caption2)
+                            .disabled(pendingNamespace == controller.customNamespace)
+                        }
+                    }
+                    VStack(alignment: .leading, spacing: 4) {
+                        Text("HuggingFace Token")
+                            .font(.caption2)
+                            .foregroundColor(.secondary)
+                        HStack {
+                            SecureField("optional", text: $pendingHFToken)
+                                .textFieldStyle(.roundedBorder)
+                                .font(.caption2)
+                                .onAppear {
+                                    pendingHFToken = controller.hfToken
+                                }
+                            Button("Save & Restart") {
+                                controller.hfToken = pendingHFToken
+                                if controller.status == .running || controller.status == .starting {
+                                    controller.restart()
+                                }
+                            }
+                            .font(.caption2)
+                            .disabled(pendingHFToken == controller.hfToken)
+                        }
+                    }
+                    Divider()
+                    HStack {
+                        Toggle(
+                            "Enable Image Models (experimental)", isOn: $pendingEnableImageModels
+                        )
+                        .toggleStyle(.switch)
+                        .font(.caption2)
+                        .onAppear {
+                            pendingEnableImageModels = controller.enableImageModels
+                        }
+
+                        Spacer()
+
+                        Button("Save & Restart") {
+                            controller.enableImageModels = pendingEnableImageModels
+                            if controller.status == .running || controller.status == .starting {
+                                controller.restart()
+                            }
+                        }
+                        .font(.caption2)
+                        .disabled(pendingEnableImageModels == controller.enableImageModels)
+                    }
+                    HoverButton(title: "Check for Updates", small: true) {
+                        updater.checkForUpdates()
+                    }
+                    debugSection
+                    HoverButton(title: "Uninstall", tint: .red, small: true) {
+                        showUninstallConfirmationAlert()
+                    }
+                    .disabled(uninstallInProgress)
+                }
+                .transition(.opacity)
+            }
         }
+        .animation(.easeInOut(duration: 0.25), value: showAdvanced)
     }
 
-    private var baseURLRow: some View {
-        HStack(spacing: 6) {
-            Image(systemName: "link")
-                .imageScale(.small)
-                .foregroundColor(.secondary)
-            Text("localhost:52415/v1")
-                .font(.system(.caption, design: .monospaced))
-                .foregroundColor(.primary)
-            Spacer()
-            Button {
-                NSPasteboard.general.clearContents()
-                NSPasteboard.general.setString("http://localhost:52415/v1", forType: .string)
-                baseURLCopied = true
-                DispatchQueue.main.asyncAfter(deadline: .now() + 2) {
-                    baseURLCopied = false
-                }
-            } label: {
-                Image(systemName: baseURLCopied ? "checkmark" : "doc.on.doc")
+    private func controlButton(title: String, tint: Color = .primary, action: @escaping () -> Void)
+        -> some View
+    {
+        HoverButton(title: title, tint: tint, trailingSystemImage: nil, action: action)
+    }
+
+    private var dashboardButton: some View {
+        Button {
+            guard let url = URL(string: "http://localhost:52415/") else { return }
+            NSWorkspace.shared.open(url)
+        } label: {
+            HStack {
+                Image(systemName: "arrow.up.right.square")
                     .imageScale(.small)
-                    .foregroundColor(baseURLCopied ? .green : .secondary)
-                    .contentTransition(.symbolEffect(.replace))
+                Text("Dashboard")
+                    .fontWeight(.medium)
+                Spacer()
             }
-            .buttonStyle(.plain)
-            .help("Copy API base URL")
+            .padding(.vertical, 8)
+            .padding(.horizontal, 10)
+            .background(
+                RoundedRectangle(cornerRadius: 8, style: .continuous)
+                    .fill(Color(red: 1.0, green: 0.87, blue: 0.0).opacity(0.2))
+            )
         }
-        .padding(.vertical, 4)
-        .padding(.horizontal, 8)
+        .buttonStyle(.plain)
+        .padding(.bottom, 4)
     }
 
     private func collapseButton(isExpanded: Binding<Bool>) -> some View {
@@ -560,115 +611,39 @@ struct ContentView: View {
     }
 
     private var sendBugReportButton: some View {
-        VStack(alignment: .leading, spacing: 6) {
-            switch bugReportPhase {
-            case .idle:
-                Button {
-                    bugReportPhase = .prompting
-                    bugReportUserDescription = ""
-                } label: {
-                    HStack {
-                        Text("Send Bug Report")
-                            .font(.caption)
-                            .fontWeight(.semibold)
-                        Spacer()
-                    }
-                    .padding(.vertical, 6)
-                    .padding(.horizontal, 8)
-                    .background(
-                        RoundedRectangle(cornerRadius: 6)
-                            .fill(Color.accentColor.opacity(0.12))
-                    )
+        VStack(alignment: .leading, spacing: 4) {
+            Button {
+                Task {
+                    await sendBugReport()
                 }
-                .buttonStyle(.plain)
-
-            case .prompting:
-                VStack(alignment: .leading, spacing: 6) {
-                    Text("What's the issue? (optional)")
-                        .font(.caption2)
-                        .foregroundColor(.secondary)
-                    TextEditor(text: $bugReportUserDescription)
-                        .font(.caption2)
-                        .frame(height: 60)
-                        .overlay(
-                            RoundedRectangle(cornerRadius: 4)
-                                .stroke(Color.secondary.opacity(0.3), lineWidth: 1)
-                        )
-                    HStack(spacing: 8) {
-                        Button("Send") {
-                            Task {
-                                await sendBugReport()
-                            }
-                        }
-                        .font(.caption2)
-                        .buttonStyle(.borderedProminent)
-                        .controlSize(.small)
-                        Button("Cancel") {
-                            bugReportPhase = .idle
-                        }
-                        .font(.caption2)
-                        .buttonStyle(.bordered)
-                        .controlSize(.small)
+            } label: {
+                HStack {
+                    if bugReportInFlight {
+                        ProgressView()
+                            .scaleEffect(0.6)
                     }
+                    Text("Send Bug Report")
+                        .font(.caption)
+                        .fontWeight(.semibold)
+                    Spacer()
                 }
-                .padding(8)
+                .padding(.vertical, 6)
+                .padding(.horizontal, 8)
                 .background(
                     RoundedRectangle(cornerRadius: 6)
-                        .fill(Color.accentColor.opacity(0.06))
+                        .fill(Color.accentColor.opacity(0.12))
                 )
+            }
+            .buttonStyle(.plain)
+            .disabled(bugReportInFlight)
 
-            case .sending(let message):
-                HStack(spacing: 6) {
-                    ProgressView()
-                        .scaleEffect(0.6)
-                    Text(message)
-                        .font(.caption2)
-                        .foregroundColor(.secondary)
-                }
-
-            case .success(let message):
-                VStack(alignment: .leading, spacing: 6) {
-                    Text(message)
-                        .font(.caption2)
-                        .foregroundColor(.secondary)
-                        .fixedSize(horizontal: false, vertical: true)
-                    Button {
-                        openGitHubIssue()
-                    } label: {
-                        HStack(spacing: 4) {
-                            Image(systemName: "arrow.up.right.square")
-                                .imageScale(.small)
-                            Text("Create GitHub Issue")
-                                .font(.caption2)
-                        }
-                    }
-                    .buttonStyle(.bordered)
-                    .controlSize(.small)
-                    Button("Done") {
-                        bugReportPhase = .idle
-                        bugReportUserDescription = ""
-                    }
+            if let message = bugReportMessage {
+                Text(message)
                     .font(.caption2)
-                    .buttonStyle(.plain)
                     .foregroundColor(.secondary)
-                }
-
-            case .failure(let message):
-                VStack(alignment: .leading, spacing: 4) {
-                    Text(message)
-                        .font(.caption2)
-                        .foregroundColor(.red)
-                        .fixedSize(horizontal: false, vertical: true)
-                    Button("Dismiss") {
-                        bugReportPhase = .idle
-                    }
-                    .font(.caption2)
-                    .buttonStyle(.plain)
-                    .foregroundColor(.secondary)
-                }
+                    .fixedSize(horizontal: false, vertical: true)
             }
         }
-        .animation(.easeInOut(duration: 0.2), value: bugReportPhase)
     }
 
     private var processToggleBinding: Binding<Bool> {
@@ -712,58 +687,16 @@ struct ContentView: View {
     }
 
     private func sendBugReport() async {
-        bugReportPhase = .sending("Collecting logs...")
+        bugReportInFlight = true
+        bugReportMessage = "Collecting logs..."
         let service = BugReportService()
-        let description = bugReportUserDescription.trimmingCharacters(in: .whitespacesAndNewlines)
         do {
-            let outcome = try await service.sendReport(
-                isManual: true,
-                userDescription: description.isEmpty ? nil : description
-            )
-            if outcome.success {
-                bugReportPhase = .success(outcome.message)
-            } else {
-                bugReportPhase = .failure(outcome.message)
-            }
+            let outcome = try await service.sendReport(isManual: true)
+            bugReportMessage = outcome.message
         } catch {
-            bugReportPhase = .failure(error.localizedDescription)
-        }
-    }
-
-    private func openGitHubIssue() {
-        let description = bugReportUserDescription.trimmingCharacters(in: .whitespacesAndNewlines)
-
-        var bodyParts: [String] = []
-        bodyParts.append("## Describe the bug")
-        bodyParts.append("")
-        if !description.isEmpty {
-            bodyParts.append(description)
-        } else {
-            bodyParts.append("A clear and concise description of what the bug is.")
-        }
-        bodyParts.append("")
-        bodyParts.append("## Environment")
-        bodyParts.append("")
-        bodyParts.append("- macOS Version: \(ProcessInfo.processInfo.operatingSystemVersionString)")
-        bodyParts.append("- EXO Version: \(buildTag) (\(buildCommit))")
-        bodyParts.append("")
-        bodyParts.append("## Additional context")
-        bodyParts.append("")
-        bodyParts.append("A bug report with diagnostic logs was submitted via the app.")
-
-        let body = bodyParts.joined(separator: "\n")
-
-        var components = URLComponents(string: "https://github.com/exo-explore/exo/issues/new")!
-        components.queryItems = [
-            URLQueryItem(name: "template", value: "bug_report.md"),
-            URLQueryItem(name: "title", value: "[BUG] "),
-            URLQueryItem(name: "body", value: body),
-            URLQueryItem(name: "labels", value: "bug"),
-        ]
-
-        if let url = components.url {
-            NSWorkspace.shared.open(url)
+            bugReportMessage = error.localizedDescription
         }
+        bugReportInFlight = false
     }
 
     private func showUninstallConfirmationAlert() {

app/EXO/EXO/EXOApp.swift

@@ -21,9 +21,7 @@ struct EXOApp: App {
     @StateObject private var localNetworkChecker: LocalNetworkChecker
     @StateObject private var updater: SparkleUpdater
     @StateObject private var thunderboltBridgeService: ThunderboltBridgeService
-    @StateObject private var settingsWindowController: SettingsWindowController
     private let terminationObserver: TerminationObserver
-    private let firstLaunchPopout = FirstLaunchPopout()
     private let ciContext = CIContext(options: nil)
 
     init() {
@@ -45,13 +43,12 @@ struct EXOApp: App {
         _updater = StateObject(wrappedValue: updater)
         let thunderboltBridge = ThunderboltBridgeService(clusterStateService: service)
         _thunderboltBridgeService = StateObject(wrappedValue: thunderboltBridge)
-        _settingsWindowController = StateObject(wrappedValue: SettingsWindowController())
         enableLaunchAtLoginIfNeeded()
         // Install LaunchDaemon to disable Thunderbolt Bridge on startup (prevents network loops)
         NetworkSetupHelper.promptAndInstallIfNeeded()
         // Check local network access periodically (warning disappears when user grants permission)
         localNetwork.startPeriodicChecking(interval: 10)
-        controller.scheduleLaunch(after: 5)
+        controller.scheduleLaunch(after: 15)
         service.startPolling()
         networkStatus.startPolling()
     }
@@ -65,19 +62,8 @@ struct EXOApp: App {
                 .environmentObject(localNetworkChecker)
                 .environmentObject(updater)
                 .environmentObject(thunderboltBridgeService)
-                .environmentObject(settingsWindowController)
         } label: {
             menuBarIcon
-                .onReceive(controller.$isFirstLaunchReady) { ready in
-                    if ready {
-                        DispatchQueue.main.asyncAfter(deadline: .now() + 3.0) {
-                            self.firstLaunchPopout.onComplete = { [weak controller] in
-                                controller?.markOnboardingCompleted()
-                            }
-                            self.firstLaunchPopout.show()
-                        }
-                    }
-                }
         }
         .menuBarExtraStyle(.window)
     }

app/EXO/EXO/ExoProcessController.swift

@@ -5,8 +5,6 @@ import Foundation
 private let customNamespaceKey = "EXOCustomNamespace"
 private let hfTokenKey = "EXOHFToken"
 private let enableImageModelsKey = "EXOEnableImageModels"
-private let offlineModeKey = "EXOOfflineMode"
-private let onboardingCompletedKey = "EXOOnboardingCompleted"
 
 @MainActor
 final class ExoProcessController: ObservableObject {
@@ -61,17 +59,6 @@ final class ExoProcessController: ObservableObject {
             UserDefaults.standard.set(enableImageModels, forKey: enableImageModelsKey)
         }
     }
-    @Published var offlineMode: Bool = {
-        return UserDefaults.standard.bool(forKey: offlineModeKey)
-    }()
-    {
-        didSet {
-            UserDefaults.standard.set(offlineMode, forKey: offlineModeKey)
-        }
-    }
-
-    /// Fires once when EXO transitions to `.running` for the very first time (fresh install).
-    @Published private(set) var isFirstLaunchReady = false
 
     private var process: Process?
     private var runtimeDirectoryURL: URL?
@@ -126,9 +113,6 @@ final class ExoProcessController: ObservableObject {
             try child.run()
             process = child
             status = .running
-
-            // Show welcome popout on every launch
-            isFirstLaunchReady = true
         } catch {
             process = nil
             status = .failed(message: "Launch error")
@@ -142,37 +126,11 @@ final class ExoProcessController: ObservableObject {
             return
         }
         process.terminationHandler = nil
-        status = .stopped
-
-        guard process.isRunning else {
-            self.process = nil
-            return
+        if process.isRunning {
+            process.terminate()
         }
-
-        let proc = process
         self.process = nil
-
-        Task.detached {
-            proc.interrupt()
-
-            for _ in 0..<50 {
-                if !proc.isRunning { return }
-                try? await Task.sleep(nanoseconds: 100_000_000)
-            }
-
-            if proc.isRunning {
-                proc.terminate()
-            }
-
-            for _ in 0..<30 {
-                if !proc.isRunning { return }
-                try? await Task.sleep(nanoseconds: 100_000_000)
-            }
-
-            if proc.isRunning {
-                kill(proc.processIdentifier, SIGKILL)
-            }
-        }
+        status = .stopped
     }
 
     func restart() {
@@ -180,17 +138,6 @@ final class ExoProcessController: ObservableObject {
         launch()
     }
 
-    /// Mark onboarding as completed (user interacted with the welcome popout).
-    func markOnboardingCompleted() {
-        UserDefaults.standard.set(true, forKey: onboardingCompletedKey)
-    }
-
-    /// Reset onboarding so the welcome popout appears on next launch.
-    func resetOnboarding() {
-        UserDefaults.standard.removeObject(forKey: onboardingCompletedKey)
-        isFirstLaunchReady = false
-    }
-
     func scheduleLaunch(after seconds: TimeInterval) {
         cancelPendingLaunch()
         let start = max(1, Int(ceil(seconds)))
@@ -276,9 +223,6 @@ final class ExoProcessController: ObservableObject {
         if enableImageModels {
             environment["EXO_ENABLE_IMAGE_MODELS"] = "true"
         }
-        if offlineMode {
-            environment["EXO_OFFLINE"] = "true"
-        }
 
         var paths: [String] = []
         if let existing = environment["PATH"], !existing.isEmpty {

app/EXO/EXO/Services/BugReportService.swift

@@ -38,8 +38,7 @@ struct BugReportService {
     func sendReport(
         baseURL: URL = URL(string: "http://127.0.0.1:52415")!,
         now: Date = Date(),
-        isManual: Bool = false,
-        userDescription: String? = nil
+        isManual: Bool = false
     ) async throws -> BugReportOutcome {
         let timestamp = Self.runTimestampString(now)
         let dayPrefix = Self.dayPrefixString(now)
@@ -61,8 +60,7 @@ struct BugReportService {
             ifconfig: ifconfigText,
             debugInfo: debugInfo,
             isManual: isManual,
-            clusterTbBridgeStatus: clusterTbBridgeStatus,
-            userDescription: userDescription
+            clusterTbBridgeStatus: clusterTbBridgeStatus
         )
 
         let eventLogFiles = readAllEventLogs()
@@ -308,8 +306,7 @@ struct BugReportService {
         ifconfig: String,
         debugInfo: DebugInfo,
         isManual: Bool,
-        clusterTbBridgeStatus: [[String: Any]]?,
-        userDescription: String? = nil
+        clusterTbBridgeStatus: [[String: Any]]?
     ) -> Data? {
         let system = readSystemMetadata()
         let exo = readExoMetadata()
@@ -326,9 +323,6 @@ struct BugReportService {
         if let tbStatus = clusterTbBridgeStatus {
             payload["cluster_thunderbolt_bridge"] = tbStatus
         }
-        if let desc = userDescription, !desc.isEmpty {
-            payload["user_description"] = desc
-        }
         return try? JSONSerialization.data(withJSONObject: payload, options: [.prettyPrinted])
     }
 

app/EXO/EXO/Views/FirstLaunchPopout.swift

@@ -1,200 +0,0 @@
-import AppKit
-import SwiftUI
-
-/// A popover callout anchored to the menu bar icon on every launch,
-/// pointing the user to the web dashboard with an arrow connecting to the icon.
-@MainActor
-final class FirstLaunchPopout {
-    private var popover: NSPopover?
-    private var countdownTask: Task<Void, Never>?
-    private static let dashboardURL = "http://localhost:52415/"
-
-    /// Called when the user completes onboarding (clicks Open Dashboard or dismisses).
-    var onComplete: (() -> Void)?
-
-    func show() {
-        guard popover == nil else { return }
-
-        // The status bar button may not exist yet on first launch; retry generously.
-        showWithRetry(attemptsRemaining: 15)
-    }
-
-    private func showWithRetry(attemptsRemaining: Int) {
-        guard attemptsRemaining > 0 else {
-            // Exhausted retries — fall back to just opening the dashboard directly.
-            openDashboard()
-            onComplete?()
-            return
-        }
-
-        guard let button = Self.findStatusItemButton() else {
-            DispatchQueue.main.asyncAfter(deadline: .now() + 1.0) { [weak self] in
-                self?.showWithRetry(attemptsRemaining: attemptsRemaining - 1)
-            }
-            return
-        }
-
-        let pop = NSPopover()
-        pop.behavior = .applicationDefined
-        pop.animates = true
-        pop.contentSize = NSSize(width: 280, height: 120)
-        pop.contentViewController = NSHostingController(
-            rootView: WelcomeCalloutView(
-                countdownDuration: 10,
-                onDismiss: { [weak self] in
-                    self?.onComplete?()
-                    self?.dismiss()
-                },
-                onOpen: { [weak self] in
-                    self?.openDashboard()
-                    self?.onComplete?()
-                    self?.dismiss()
-                }
-            )
-        )
-
-        self.popover = pop
-        pop.show(relativeTo: button.bounds, of: button, preferredEdge: .minY)
-
-        // Auto-open dashboard after 10s then dismiss
-        countdownTask = Task {
-            try? await Task.sleep(nanoseconds: 10_000_000_000)
-            if !Task.isCancelled {
-                openDashboard()
-                onComplete?()
-                dismiss()
-            }
-        }
-    }
-
-    func dismiss() {
-        countdownTask?.cancel()
-        countdownTask = nil
-        guard let pop = popover else { return }
-        popover = nil
-        pop.performClose(nil)
-    }
-
-    private func openDashboard() {
-        guard let url = URL(string: Self.dashboardURL) else { return }
-        NSWorkspace.shared.open(url)
-    }
-
-    /// Finds the NSStatusBarButton created by SwiftUI's MenuBarExtra.
-    /// Walks the view hierarchy to find the actual button rather than the content view.
-    private static func findStatusItemButton() -> NSView? {
-        for window in NSApp.windows {
-            let className = NSStringFromClass(type(of: window))
-            // Match NSStatusBarWindow or any internal SwiftUI status bar window
-            guard className.contains("StatusBar") || className.contains("MenuBarExtra") else {
-                continue
-            }
-            if let content = window.contentView {
-                if let button = findButton(in: content) {
-                    return button
-                }
-                // Fall back to the content view itself if it has a non-zero frame
-                if content.frame.width > 0 {
-                    return content
-                }
-            }
-        }
-        return nil
-    }
-
-    /// Recursively searches the view hierarchy for an NSStatusBarButton.
-    private static func findButton(in view: NSView) -> NSView? {
-        let className = NSStringFromClass(type(of: view))
-        if className.contains("StatusBarButton") || className.contains("StatusItem") {
-            return view
-        }
-        for subview in view.subviews {
-            if let found = findButton(in: subview) {
-                return found
-            }
-        }
-        return nil
-    }
-}
-
-/// Minimal welcome callout — friendly pointer, not a wall of text.
-/// Rendered inside the NSPopover which provides its own chrome and arrow.
-private struct WelcomeCalloutView: View {
-    let countdownDuration: Int
-    let onDismiss: () -> Void
-    let onOpen: () -> Void
-    @State private var countdown: Int
-    @State private var timerTask: Task<Void, Never>?
-
-    init(countdownDuration: Int, onDismiss: @escaping () -> Void, onOpen: @escaping () -> Void) {
-        self.countdownDuration = countdownDuration
-        self.onDismiss = onDismiss
-        self.onOpen = onOpen
-        self._countdown = State(initialValue: countdownDuration)
-    }
-
-    var body: some View {
-        VStack(alignment: .leading, spacing: 10) {
-            HStack(alignment: .top) {
-                Text("EXO is running")
-                    .font(.system(.headline, design: .rounded))
-                    .fontWeight(.semibold)
-                    .foregroundColor(.primary)
-                Spacer()
-                Button {
-                    onDismiss()
-                } label: {
-                    Image(systemName: "xmark.circle.fill")
-                        .font(.system(size: 14))
-                        .foregroundStyle(.tertiary)
-                }
-                .buttonStyle(.plain)
-            }
-
-            Text("Run your first model here:")
-                .font(.system(.subheadline, design: .default))
-                .foregroundColor(.secondary)
-
-            HStack {
-                Button {
-                    onOpen()
-                } label: {
-                    Label("Open Dashboard", systemImage: "arrow.up.right.square")
-                        .font(.system(.caption, design: .default))
-                        .fontWeight(.medium)
-                }
-                .buttonStyle(.borderedProminent)
-                .tint(.accentColor)
-                .controlSize(.small)
-
-                Spacer()
-
-                if countdown > 0 {
-                    Text("Launching in \(countdown) secs...")
-                        .font(.system(.caption2, design: .default))
-                        .foregroundColor(.secondary.opacity(0.6))
-                        .monospacedDigit()
-                }
-            }
-        }
-        .padding(14)
-        .onAppear {
-            startCountdown()
-        }
-        .onDisappear {
-            timerTask?.cancel()
-            timerTask = nil
-        }
-    }
-
-    private func startCountdown() {
-        timerTask = Task {
-            while countdown > 0 {
-                try? await Task.sleep(nanoseconds: 1_000_000_000)
-                if !Task.isCancelled {
-                    countdown -= 1
-                }
-            }
-        }
-    }
-}

app/EXO/EXO/Views/SettingsView.swift

@@ -1,489 +0,0 @@
-import AppKit
-import SwiftUI
-
-/// Native macOS Settings window following Apple HIG.
-/// Organized into General, Model, Advanced, and About sections.
-struct SettingsView: View {
-    @EnvironmentObject private var controller: ExoProcessController
-    @EnvironmentObject private var updater: SparkleUpdater
-    @EnvironmentObject private var networkStatusService: NetworkStatusService
-    @EnvironmentObject private var thunderboltBridgeService: ThunderboltBridgeService
-    @EnvironmentObject private var stateService: ClusterStateService
-
-    @State private var pendingNamespace: String = ""
-    @State private var pendingHFToken: String = ""
-    @State private var pendingEnableImageModels = false
-    @State private var pendingOfflineMode = false
-    @State private var needsRestart = false
-    @State private var bugReportInFlight = false
-    @State private var bugReportMessage: String?
-    @State private var uninstallInProgress = false
-
-    var body: some View {
-        TabView {
-            generalTab
-                .tabItem {
-                    Label("General", systemImage: "gear")
-                }
-            modelTab
-                .tabItem {
-                    Label("Model", systemImage: "cube")
-                }
-            advancedTab
-                .tabItem {
-                    Label("Advanced", systemImage: "wrench.and.screwdriver")
-                }
-            aboutTab
-                .tabItem {
-                    Label("About", systemImage: "info.circle")
-                }
-        }
-        .frame(width: 450, height: 400)
-        .onAppear {
-            pendingNamespace = controller.customNamespace
-            pendingHFToken = controller.hfToken
-            pendingEnableImageModels = controller.enableImageModels
-            pendingOfflineMode = controller.offlineMode
-            needsRestart = false
-        }
-    }
-
-    // MARK: - General Tab
-
-    private var generalTab: some View {
-        Form {
-            Section {
-                LabeledContent("Cluster Namespace") {
-                    TextField("default", text: $pendingNamespace)
-                        .textFieldStyle(.roundedBorder)
-                        .frame(width: 200)
-                }
-                Text("Nodes with the same namespace form a cluster. Leave empty for default.")
-                    .font(.caption)
-                    .foregroundColor(.secondary)
-            }
-
-            Section {
-                LabeledContent("HuggingFace Token") {
-                    SecureField("optional", text: $pendingHFToken)
-                        .textFieldStyle(.roundedBorder)
-                        .frame(width: 200)
-                }
-                Text("Required for gated models. Get yours at huggingface.co/settings/tokens")
-                    .font(.caption)
-                    .foregroundColor(.secondary)
-            }
-
-            Section {
-                Toggle("Offline Mode", isOn: $pendingOfflineMode)
-                Text("Skip internet checks and use only locally available models.")
-                    .font(.caption)
-                    .foregroundColor(.secondary)
-            }
-
-            Section {
-                HStack {
-                    Spacer()
-                    Button("Save & Restart") {
-                        applyGeneralSettings()
-                    }
-                    .disabled(!hasGeneralChanges)
-                }
-            }
-        }
-        .formStyle(.grouped)
-        .padding()
-    }
-
-    // MARK: - Model Tab
-
-    private var modelTab: some View {
-        Form {
-            Section {
-                Toggle("Enable Image Models (experimental)", isOn: $pendingEnableImageModels)
-                Text("Allow text-to-image and image-to-image models in the model picker.")
-                    .font(.caption)
-                    .foregroundColor(.secondary)
-            }
-
-            Section {
-                HStack {
-                    Spacer()
-                    Button("Save & Restart") {
-                        applyModelSettings()
-                    }
-                    .disabled(!hasModelChanges)
-                }
-            }
-        }
-        .formStyle(.grouped)
-        .padding()
-    }
-
-    // MARK: - Advanced Tab
-
-    private var advancedTab: some View {
-        Form {
-            Section("Onboarding") {
-                HStack {
-                    VStack(alignment: .leading) {
-                        Text("Reset Onboarding")
-                        Text("Opens the dashboard and resets the onboarding wizard.")
-                            .font(.caption)
-                            .foregroundColor(.secondary)
-                    }
-                    Spacer()
-                    Button("Reset") {
-                        guard let url = URL(string: "http://localhost:52415/?reset-onboarding")
-                        else { return }
-                        NSWorkspace.shared.open(url)
-                    }
-                }
-            }
-
-            Section("Debug Info") {
-                LabeledContent("Thunderbolt Bridge") {
-                    Text(thunderboltStatusText)
-                        .foregroundColor(thunderboltStatusColor)
-                }
-
-                VStack(alignment: .leading, spacing: 2) {
-                    clusterThunderboltBridgeView
-                }
-
-                VStack(alignment: .leading, spacing: 2) {
-                    interfaceIpList
-                }
-
-                VStack(alignment: .leading, spacing: 2) {
-                    rdmaStatusView
-                }
-
-                sendBugReportButton
-            }
-
-            Section("Danger Zone") {
-                Button(role: .destructive) {
-                    showUninstallConfirmationAlert()
-                } label: {
-                    HStack {
-                        Text("Uninstall EXO")
-                        Spacer()
-                        Image(systemName: "trash")
-                            .imageScale(.small)
-                    }
-                }
-                .disabled(uninstallInProgress)
-            }
-        }
-        .formStyle(.grouped)
-        .padding()
-    }
-
-    // MARK: - About Tab
-
-    private var aboutTab: some View {
-        Form {
-            Section {
-                LabeledContent("Version") {
-                    Text(buildTag)
-                        .textSelection(.enabled)
-                }
-                LabeledContent("Commit") {
-                    Text(buildCommit)
-                        .font(.system(.body, design: .monospaced))
-                        .textSelection(.enabled)
-                }
-            }
-
-            Section {
-                Button("Check for Updates") {
-                    updater.checkForUpdates()
-                }
-            }
-        }
-        .formStyle(.grouped)
-        .padding()
-    }
-
-    // MARK: - Debug Info Views (moved from ContentView)
-
-    private var thunderboltStatusText: String {
-        switch networkStatusService.status.thunderboltBridgeState {
-        case .some(.disabled):
-            return "Disabled"
-        case .some(.deleted):
-            return "Deleted"
-        case .some(.enabled):
-            return "Enabled"
-        case nil:
-            return "Unknown"
-        }
-    }
-
-    private var thunderboltStatusColor: Color {
-        switch networkStatusService.status.thunderboltBridgeState {
-        case .some(.disabled), .some(.deleted):
-            return .green
-        case .some(.enabled):
-            return .red
-        case nil:
-            return .secondary
-        }
-    }
-
-    private var clusterThunderboltBridgeView: some View {
-        let bridgeStatuses = stateService.latestSnapshot?.nodeThunderboltBridge ?? [:]
-        let localNodeId = stateService.localNodeId
-        let nodeProfiles = stateService.latestSnapshot?.nodeProfiles ?? [:]
-
-        return VStack(alignment: .leading, spacing: 1) {
-            if bridgeStatuses.isEmpty {
-                Text("Cluster TB Bridge: No data")
-                    .font(.caption2)
-                    .foregroundColor(.secondary)
-            } else {
-                Text("Cluster TB Bridge Status:")
-                    .font(.caption2)
-                    .foregroundColor(.secondary)
-                ForEach(Array(bridgeStatuses.keys.sorted()), id: \.self) { nodeId in
-                    if let status = bridgeStatuses[nodeId] {
-                        let nodeName =
-                            nodeProfiles[nodeId]?.friendlyName ?? String(nodeId.prefix(8))
-                        let isLocal = nodeId == localNodeId
-                        let prefix = isLocal ? "  \(nodeName) (local):" : "  \(nodeName):"
-                        let statusText =
-                            !status.exists
-                            ? "N/A"
-                            : (status.enabled ? "Enabled" : "Disabled")
-                        let color: Color =
-                            !status.exists
-                            ? .secondary
-                            : (status.enabled ? .red : .green)
-                        Text("\(prefix) \(statusText)")
-                            .font(.caption2)
-                            .foregroundColor(color)
-                    }
-                }
-            }
-        }
-    }
-
-    private var interfaceIpList: some View {
-        let statuses = networkStatusService.status.interfaceStatuses
-        return VStack(alignment: .leading, spacing: 1) {
-            Text("Interfaces (en0–en7):")
-                .font(.caption2)
-                .foregroundColor(.secondary)
-            if statuses.isEmpty {
-                Text("  Unknown")
-                    .font(.caption2)
-                    .foregroundColor(.secondary)
-            } else {
-                ForEach(statuses, id: \.interfaceName) { status in
-                    let ipText = status.ipAddress ?? "No IP"
-                    Text("  \(status.interfaceName): \(ipText)")
-                        .font(.caption2)
-                        .foregroundColor(status.ipAddress == nil ? .red : .green)
-                }
-            }
-        }
-    }
-
-    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
-
-        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: ", "))")
-                    .font(.caption2)
-                    .foregroundColor(.secondary)
-            }
-            if !localPorts.isEmpty {
-                Text("  Local Active Ports:")
-                    .font(.caption2)
-                    .foregroundColor(.secondary)
-                ForEach(localPorts, id: \.device) { port in
-                    Text("    \(port.device) port \(port.port): \(port.state)")
-                        .font(.caption2)
-                        .foregroundColor(.green)
-                }
-            }
-        }
-    }
-
-    private var sendBugReportButton: some View {
-        VStack(alignment: .leading, spacing: 4) {
-            Button {
-                Task {
-                    await sendBugReport()
-                }
-            } label: {
-                HStack {
-                    if bugReportInFlight {
-                        ProgressView()
-                            .scaleEffect(0.6)
-                    }
-                    Text("Send Bug Report")
-                        .font(.caption)
-                        .fontWeight(.semibold)
-                    Spacer()
-                }
-            }
-            .disabled(bugReportInFlight)
-
-            if let message = bugReportMessage {
-                Text(message)
-                    .font(.caption2)
-                    .foregroundColor(.secondary)
-                    .fixedSize(horizontal: false, vertical: true)
-            }
-        }
-    }
-
-    // MARK: - Actions
-
-    private func sendBugReport() async {
-        bugReportInFlight = true
-        bugReportMessage = "Collecting logs..."
-        let service = BugReportService()
-        do {
-            let outcome = try await service.sendReport(isManual: true)
-            bugReportMessage = outcome.message
-        } catch {
-            bugReportMessage = error.localizedDescription
-        }
-        bugReportInFlight = false
-    }
-
-    private func showUninstallConfirmationAlert() {
-        let alert = NSAlert()
-        alert.messageText = "Uninstall EXO"
-        alert.informativeText = """
-            This will remove EXO and all its system components:
-
-            • Network configuration daemon
-            • Launch at login registration
-            • EXO network location
-
-            The app will be moved to Trash.
-            """
-        alert.alertStyle = .warning
-        alert.addButton(withTitle: "Uninstall")
-        alert.addButton(withTitle: "Cancel")
-
-        if let uninstallButton = alert.buttons.first {
-            uninstallButton.hasDestructiveAction = true
-        }
-
-        let response = alert.runModal()
-        if response == .alertFirstButtonReturn {
-            performUninstall()
-        }
-    }
-
-    private func performUninstall() {
-        uninstallInProgress = true
-
-        controller.cancelPendingLaunch()
-        controller.stop()
-        stateService.stopPolling()
-
-        DispatchQueue.global(qos: .utility).async {
-            do {
-                try NetworkSetupHelper.uninstall()
-
-                DispatchQueue.main.async {
-                    LaunchAtLoginHelper.disable()
-                    self.moveAppToTrash()
-
-                    DispatchQueue.main.asyncAfter(deadline: .now() + 0.5) {
-                        NSApplication.shared.terminate(nil)
-                    }
-                }
-            } catch {
-                DispatchQueue.main.async {
-                    let errorAlert = NSAlert()
-                    errorAlert.messageText = "Uninstall Failed"
-                    errorAlert.informativeText = error.localizedDescription
-                    errorAlert.alertStyle = .critical
-                    errorAlert.addButton(withTitle: "OK")
-                    errorAlert.runModal()
-                    self.uninstallInProgress = false
-                }
-            }
-        }
-    }
-
-    private func moveAppToTrash() {
-        guard let appURL = Bundle.main.bundleURL as URL? else { return }
-        do {
-            try FileManager.default.trashItem(at: appURL, resultingItemURL: nil)
-        } catch {
-            // If we can't trash the app, that's OK - user can do it manually
-        }
-    }
-
-    // MARK: - Helpers
-
-    private var hasGeneralChanges: Bool {
-        pendingNamespace != controller.customNamespace || pendingHFToken != controller.hfToken
-            || pendingOfflineMode != controller.offlineMode
-    }
-
-    private var hasModelChanges: Bool {
-        pendingEnableImageModels != controller.enableImageModels
-    }
-
-    private func applyGeneralSettings() {
-        controller.customNamespace = pendingNamespace
-        controller.hfToken = pendingHFToken
-        controller.offlineMode = pendingOfflineMode
-        restartIfRunning()
-    }
-
-    private func applyModelSettings() {
-        controller.enableImageModels = pendingEnableImageModels
-        restartIfRunning()
-    }
-
-    private func restartIfRunning() {
-        if controller.status == .running || controller.status == .starting {
-            controller.restart()
-        }
-    }
-
-    private var buildTag: String {
-        Bundle.main.infoDictionary?["EXOBuildTag"] as? String ?? "unknown"
-    }
-
-    private var buildCommit: String {
-        Bundle.main.infoDictionary?["EXOBuildCommit"] as? String ?? "unknown"
-    }
-}

app/EXO/EXO/Views/SettingsWindowController.swift

@@ -1,47 +0,0 @@
-import AppKit
-import SwiftUI
-
-/// Manages a standalone native macOS Settings window.
-/// Ensures only one instance exists and brings it to front on repeated opens.
-@MainActor
-final class SettingsWindowController: ObservableObject {
-    private var window: NSWindow?
-
-    func open(
-        controller: ExoProcessController,
-        updater: SparkleUpdater,
-        networkStatusService: NetworkStatusService,
-        thunderboltBridgeService: ThunderboltBridgeService,
-        stateService: ClusterStateService
-    ) {
-        if let existing = window, existing.isVisible {
-            existing.makeKeyAndOrderFront(nil)
-            NSApp.activate(ignoringOtherApps: true)
-            return
-        }
-
-        let settingsView = SettingsView()
-            .environmentObject(controller)
-            .environmentObject(updater)
-            .environmentObject(networkStatusService)
-            .environmentObject(thunderboltBridgeService)
-            .environmentObject(stateService)
-
-        let hostingView = NSHostingView(rootView: settingsView)
-
-        let newWindow = NSWindow(
-            contentRect: NSRect(x: 0, y: 0, width: 450, height: 400),
-            styleMask: [.titled, .closable],
-            backing: .buffered,
-            defer: false
-        )
-        newWindow.title = "EXO Settings"
-        newWindow.contentView = hostingView
-        newWindow.center()
-        newWindow.isReleasedWhenClosed = false
-        newWindow.makeKeyAndOrderFront(nil)
-        NSApp.activate(ignoringOtherApps: true)
-
-        window = newWindow
-    }
-}

bench/bench.toml

@@ -1,5 +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"]

bench/exo_bench.py

@@ -1,48 +1,29 @@
-# type: ignore
 #!/usr/bin/env python3
-"""Tool-calling eval for exo's OpenAI-compatible API.
-
-Tests whether models correctly:
-- Trigger tool calls when appropriate
-- Return valid JSON arguments matching function schemas
-- Handle multi-turn tool use (call -> result -> final answer)
-- Avoid calling tools when unnecessary
-
-Start exo with a model first, then run:
-    uv run python tool_call_eval.py --model <model-id>
-    uv run python tool_call_eval.py --model <model-id> --host 10.0.0.5 --port 52415
-    uv run python tool_call_eval.py --model <model-id> --repeat 3
-    uv run python tool_call_eval.py --model <model-id> --scenarios weather_simple calculator_multi_turn
-"""
-
+# pyright: reportAny=false, reportUnknownMemberType=false, reportUnknownVariableType=false, reportUnknownArgumentType=false
 from __future__ import annotations
 
 import argparse
 import contextlib
+import http.client
 import itertools
 import json
+import os
 import sys
 import time
 from collections.abc import Callable
 from pathlib import Path
 from statistics import mean
 from typing import Any
+from urllib.parse import urlencode
 
-from harness import (
-    ExoClient,
-    ExoHttpError,
-    add_common_instance_args,
-    instance_id_from_instance,
-    nodes_used_in_instance,
-    resolve_model_short_id,
-    run_planning_phase,
-    settle_and_fetch_placements,
-    wait_for_instance_gone,
-    wait_for_instance_ready,
-)
 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
@@ -75,7 +56,7 @@ def load_tokenizer_for_bench(model_id: str) -> Any:
         model_path = Path(
             snapshot_download(
                 model_id,
-                allow_patterns=["*.json", "*.py", "*.tiktoken", "*.model"],
+                allow_patterns=["*.json", "*.py", "*.tiktoken"],
             )
         )
 
@@ -122,6 +103,154 @@ def load_tokenizer_for_bench(model_id: str) -> Any:
     return AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
 
 
+class ExoHttpError(RuntimeError):
+    def __init__(self, status: int, reason: str, body_preview: str):
+        super().__init__(f"HTTP {status} {reason}: {body_preview}")
+        self.status = status
+
+
+class ExoClient:
+    def __init__(self, host: str, port: int, timeout_s: float = 7200.0):
+        self.host = host
+        self.port = port
+        self.timeout_s = timeout_s
+
+    def request_json(
+        self,
+        method: str,
+        path: str,
+        params: dict[str, Any] | None = None,
+        body: dict[str, Any] | None = None,
+        headers: dict[str, str] | None = None,
+    ) -> Any:
+        if not path.startswith("/"):
+            path = "/" + path
+        if params:
+            path = path + "?" + urlencode(params)
+
+        conn = http.client.HTTPConnection(self.host, self.port, timeout=self.timeout_s)
+        try:
+            payload: bytes | None = None
+            hdrs: dict[str, str] = {"Accept": "application/json"}
+
+            if body is not None:
+                payload = json.dumps(body).encode("utf-8")
+                hdrs["Content-Type"] = "application/json"
+            if headers:
+                hdrs.update(headers)
+
+            conn.request(method.upper(), path, body=payload, headers=hdrs)
+            resp = conn.getresponse()
+            raw = resp.read()
+            text = raw.decode("utf-8", errors="replace") if raw else ""
+
+            if resp.status >= 400:
+                raise ExoHttpError(resp.status, resp.reason, text[:300])
+
+            if not text:
+                return None
+            return json.loads(text)
+        finally:
+            conn.close()
+
+    def post_bench_chat_completions(self, payload: dict[str, Any]) -> dict[str, Any]:
+        return self.request_json("POST", "/bench/chat/completions", body=payload)
+
+
+def unwrap_instance(instance: dict[str, Any]) -> dict[str, Any]:
+    if len(instance) != 1:
+        raise KeyError(f"Expected 1 key, got keys={list(instance.keys())}")
+
+    tag = next(iter(instance))
+    inner = instance[tag]
+    if not isinstance(inner, dict):
+        raise TypeError(f"payload for {tag} must be dict, got {type(inner)}")
+    return inner
+
+
+def instance_id_from_instance(instance: dict[str, Any]) -> str:
+    inner = unwrap_instance(instance)
+    return str(inner["instanceId"])
+
+
+def nodes_used_in_instance(instance: dict[str, Any]) -> int:
+    inner = unwrap_instance(instance)
+    return len(inner["shardAssignments"]["nodeToRunner"])
+
+
+def runner_ids_from_instance(instance: dict[str, Any]) -> list[str]:
+    inner = unwrap_instance(instance)
+    runner_to_shard = inner["shardAssignments"]["runnerToShard"]
+    return list(runner_to_shard.keys())
+
+
+def runner_ready(runner: dict[str, Any]) -> bool:
+    return "RunnerReady" in runner
+
+
+def runner_failed(runner: dict[str, Any]) -> bool:
+    return "RunnerFailed" in runner
+
+
+def get_runner_failed_message(runner: dict[str, Any]) -> str | None:
+    if "RunnerFailed" in runner:
+        return runner["RunnerFailed"].get("errorMessage")
+    return None
+
+
+def wait_for_instance_ready(
+    client: ExoClient, instance_id: str, timeout: float = 24000.0
+) -> None:
+    start_time = time.time()
+    instance_existed = False
+    while time.time() - start_time < timeout:
+        state = client.request_json("GET", "/state")
+        instances = state.get("instances", {})
+
+        if instance_id not in instances:
+            if instance_existed:
+                # Instance was deleted after being created - likely due to runner failure
+                raise RuntimeError(
+                    f"Instance {instance_id} was deleted (runner may have failed)"
+                )
+            time.sleep(0.1)
+            continue
+
+        instance_existed = True
+        instance = instances[instance_id]
+        runner_ids = runner_ids_from_instance(instance)
+        runners = state.get("runners", {})
+
+        # Check for failed runners first
+        for rid in runner_ids:
+            runner = runners.get(rid, {})
+            if runner_failed(runner):
+                error_msg = get_runner_failed_message(runner) or "Unknown error"
+                raise RuntimeError(f"Runner {rid} failed: {error_msg}")
+
+        if all(runner_ready(runners.get(rid, {})) for rid in runner_ids):
+            return
+
+        time.sleep(0.1)
+
+    raise TimeoutError(f"Instance {instance_id} did not become ready within {timeout=}")
+
+
+def wait_for_instance_gone(
+    client: ExoClient, instance_id: str, timeout: float = 3.0
+) -> None:
+    start_time = time.time()
+    while time.time() - start_time < timeout:
+        try:
+            client.request_json("GET", f"/instance/{instance_id}")
+            time.sleep(0.4)
+        except ExoHttpError as e:
+            if e.status == 404:
+                return
+
+    raise TimeoutError(f"Instance {instance_id} did not get deleted within {timeout=}")
+
+
 def format_peak_memory(b: float) -> str:
     for unit in ["B", "KB", "MB", "GB", "TB"]:
         if b < 1024.0:
@@ -140,6 +269,184 @@ def parse_int_list(values: list[str]) -> list[int]:
     return items
 
 
+def resolve_model_short_id(client: ExoClient, model_arg: str) -> tuple[str, str]:
+    models = client.request_json("GET", "/models") or {}
+    data = models.get("data") or []
+
+    for m in data:
+        if m.get("name").lower() == model_arg.lower():
+            short_id = str(m["name"])
+            full_id = str(m.get("hugging_face_id") or m["name"])
+            return short_id, full_id
+
+    for m in data:
+        if m.get("hugging_face_id") == model_arg:
+            short_id = str(m["name"])
+            full_id = str(m["hugging_face_id"])
+            return short_id, full_id
+
+    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":
+        return ("ring" in s) or ("jaccl" in s)
+    return wanted in s
+
+
+def sharding_filter(sharding: str, wanted: str) -> bool:
+    s = (sharding or "").lower()
+    if wanted == "both":
+        return ("pipeline" in s) or ("tensor" in s)
+    return wanted in s
+
+
 def run_one_completion(
     client: ExoClient, model_id: str, pp_hint: int, tg: int, prompt_sizer: PromptSizer
 ) -> tuple[dict[str, Any], int]:
@@ -231,12 +538,76 @@ 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",
         description="Benchmark exo model throughput across placement previews.",
     )
-    add_common_instance_args(ap)
+    ap.add_argument("--host", default=os.environ.get("EXO_HOST", "localhost"))
+    ap.add_argument(
+        "--port", type=int, default=int(os.environ.get("EXO_PORT", "52415"))
+    )
+    ap.add_argument("--model", required=True, help="Model short id or huggingface id")
     ap.add_argument(
         "--pp",
         nargs="+",
@@ -249,6 +620,34 @@ def main() -> int:
         required=True,
         help="Generation lengths (ints). Accepts commas.",
     )
+    ap.add_argument(
+        "--max-nodes",
+        type=int,
+        default=4,
+        help="Only consider placements using <= this many nodes.",
+    )
+    ap.add_argument(
+        "--min-nodes",
+        type=int,
+        default=1,
+        help="Only consider placements using >= this many nodes.",
+    )
+    ap.add_argument(
+        "--instance-meta", choices=["ring", "jaccl", "both"], default="both"
+    )
+    ap.add_argument(
+        "--sharding", choices=["pipeline", "tensor", "both"], default="both"
+    )
+    ap.add_argument(
+        "--skip-pipeline-jaccl",
+        action="store_true",
+        help="Skip pipeline+jaccl placements, as it's often pointless.",
+    )
+    ap.add_argument(
+        "--skip-tensor-ring",
+        action="store_true",
+        help="Skip tensor+ring placements, as it's so slow.",
+    )
     ap.add_argument(
         "--repeat", type=int, default=1, help="Repetitions per (pp,tg) pair."
     )
@@ -258,6 +657,9 @@ def main() -> int:
         default=0,
         help="Warmup runs per placement (uses first pp/tg).",
     )
+    ap.add_argument(
+        "--timeout", type=float, default=7200.0, help="HTTP timeout (seconds)."
+    )
     ap.add_argument(
         "--json-out",
         default="bench/results.json",
@@ -272,6 +674,17 @@ 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)
@@ -306,10 +719,24 @@ def main() -> int:
         logger.error("[exo-bench] tokenizer usable but prompt sizing failed")
         raise
 
-    selected = settle_and_fetch_placements(
-        client, full_model_id, args, settle_timeout=args.settle_timeout
+    settle_deadline = (
+        time.monotonic() + args.settle_timeout if args.settle_timeout > 0 else None
     )
 
+    selected = fetch_and_filter_placements(client, full_model_id, args)
+
+    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)..."
+            )
+            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)
+
     if not selected:
         logger.error("No valid placements matched your filters.")
         return 1
@@ -333,12 +760,8 @@ def main() -> int:
     if args.dry_run:
         return 0
 
-    settle_deadline = (
-        time.monotonic() + args.settle_timeout if args.settle_timeout > 0 else None
-    )
-
     logger.info("Planning phase: checking downloads...")
-    download_duration_s = run_planning_phase(
+    run_planning_phase(
         client,
         full_model_id,
         selected[0],
@@ -346,10 +769,6 @@ def main() -> int:
         args.timeout,
         settle_deadline,
     )
-    if download_duration_s is not None:
-        logger.info(f"Download: {download_duration_s:.1f}s (freshly downloaded)")
-    else:
-        logger.info("Download: model already cached")
 
     all_rows: list[dict[str, Any]] = []
 
@@ -413,11 +832,6 @@ def main() -> int:
                             "pp_tokens": actual_pp_tokens,
                             "tg": tg,
                             "repeat_index": r,
-                            **(
-                                {"download_duration_s": download_duration_s}
-                                if download_duration_s is not None
-                                else {}
-                            ),
                         }
                     )
                     runs.append(row)

bench/harness.py

@@ -1,489 +0,0 @@
-# type: ignore
-from __future__ import annotations
-
-import argparse
-import http.client
-import json
-import os
-import time
-from typing import Any
-from urllib.parse import urlencode
-
-from loguru import logger
-
-_SETTLE_INITIAL_BACKOFF_S = 1.0
-_SETTLE_MAX_BACKOFF_S = 60.0
-_SETTLE_BACKOFF_MULTIPLIER = 2.0
-
-
-class ExoHttpError(RuntimeError):
-    def __init__(self, status: int, reason: str, body_preview: str):
-        super().__init__(f"HTTP {status} {reason}: {body_preview}")
-        self.status = status
-
-
-class ExoClient:
-    def __init__(self, host: str, port: int, timeout_s: float = 7200.0):
-        self.host = host
-        self.port = port
-        self.timeout_s = timeout_s
-
-    def request_json(
-        self,
-        method: str,
-        path: str,
-        params: dict[str, Any] | None = None,
-        body: dict[str, Any] | None = None,
-        headers: dict[str, str] | None = None,
-    ) -> Any:
-        if not path.startswith("/"):
-            path = "/" + path
-        if params:
-            path = path + "?" + urlencode(params)
-
-        conn = http.client.HTTPConnection(self.host, self.port, timeout=self.timeout_s)
-        try:
-            payload: bytes | None = None
-            hdrs: dict[str, str] = {"Accept": "application/json"}
-
-            if body is not None:
-                payload = json.dumps(body).encode("utf-8")
-                hdrs["Content-Type"] = "application/json"
-            if headers:
-                hdrs.update(headers)
-
-            conn.request(method.upper(), path, body=payload, headers=hdrs)
-            resp = conn.getresponse()
-            raw = resp.read()
-            text = raw.decode("utf-8", errors="replace") if raw else ""
-
-            if resp.status >= 400:
-                raise ExoHttpError(resp.status, resp.reason, text[:300])
-
-            if not text:
-                return None
-            return json.loads(text)
-        finally:
-            conn.close()
-
-    def post_bench_chat_completions(self, payload: dict[str, Any]) -> dict[str, Any]:
-        return self.request_json("POST", "/bench/chat/completions", body=payload)
-
-
-def unwrap_instance(instance: dict[str, Any]) -> dict[str, Any]:
-    if len(instance) != 1:
-        raise KeyError(f"Expected 1 key, got keys={list(instance.keys())}")
-
-    tag = next(iter(instance))
-    inner = instance[tag]
-    if not isinstance(inner, dict):
-        raise TypeError(f"payload for {tag} must be dict, got {type(inner)}")
-    return inner
-
-
-def instance_id_from_instance(instance: dict[str, Any]) -> str:
-    inner = unwrap_instance(instance)
-    return str(inner["instanceId"])
-
-
-def nodes_used_in_instance(instance: dict[str, Any]) -> int:
-    inner = unwrap_instance(instance)
-    return len(inner["shardAssignments"]["nodeToRunner"])
-
-
-def runner_ids_from_instance(instance: dict[str, Any]) -> list[str]:
-    inner = unwrap_instance(instance)
-    runner_to_shard = inner["shardAssignments"]["runnerToShard"]
-    return list(runner_to_shard.keys())
-
-
-def runner_ready(runner: dict[str, Any]) -> bool:
-    return "RunnerReady" in runner
-
-
-def runner_failed(runner: dict[str, Any]) -> bool:
-    return "RunnerFailed" in runner
-
-
-def get_runner_failed_message(runner: dict[str, Any]) -> str | None:
-    if "RunnerFailed" in runner:
-        return runner["RunnerFailed"].get("errorMessage")
-    return None
-
-
-def wait_for_instance_ready(
-    client: ExoClient, instance_id: str, timeout: float = 24000.0
-) -> None:
-    start_time = time.time()
-    instance_existed = False
-    while time.time() - start_time < timeout:
-        state = client.request_json("GET", "/state")
-        instances = state.get("instances", {})
-
-        if instance_id not in instances:
-            if instance_existed:
-                # Instance was deleted after being created - likely due to runner failure
-                raise RuntimeError(
-                    f"Instance {instance_id} was deleted (runner may have failed)"
-                )
-            time.sleep(0.1)
-            continue
-
-        instance_existed = True
-        instance = instances[instance_id]
-        runner_ids = runner_ids_from_instance(instance)
-        runners = state.get("runners", {})
-
-        # Check for failed runners first
-        for rid in runner_ids:
-            runner = runners.get(rid, {})
-            if runner_failed(runner):
-                error_msg = get_runner_failed_message(runner) or "Unknown error"
-                raise RuntimeError(f"Runner {rid} failed: {error_msg}")
-
-        if all(runner_ready(runners.get(rid, {})) for rid in runner_ids):
-            return
-
-        time.sleep(0.1)
-
-    raise TimeoutError(f"Instance {instance_id} did not become ready within {timeout=}")
-
-
-def wait_for_instance_gone(
-    client: ExoClient, instance_id: str, timeout: float = 3.0
-) -> None:
-    start_time = time.time()
-    while time.time() - start_time < timeout:
-        try:
-            client.request_json("GET", f"/instance/{instance_id}")
-            time.sleep(0.4)
-        except ExoHttpError as e:
-            if e.status == 404:
-                return
-            raise
-
-    raise TimeoutError(f"Instance {instance_id} did not get deleted within {timeout=}")
-
-
-def resolve_model_short_id(client: ExoClient, model_arg: str) -> tuple[str, str]:
-    models = client.request_json("GET", "/models") or {}
-    data = models.get("data") or []
-
-    for m in data:
-        if (m.get("name") or "").lower() == model_arg.lower():
-            short_id = str(m["name"])
-            full_id = str(m.get("hugging_face_id") or m["name"])
-            return short_id, full_id
-
-    for m in data:
-        if m.get("hugging_face_id") == model_arg:
-            short_id = str(m["name"])
-            full_id = str(m["hugging_face_id"])
-            return short_id, full_id
-
-    raise ValueError(f"Model not found in /models: {model_arg}")
-
-
-def placement_filter(instance_meta: str, wanted: str) -> bool:
-    s = (instance_meta or "").lower()
-    if wanted == "both":
-        return ("ring" in s) or ("jaccl" in s)
-    return wanted in s
-
-
-def sharding_filter(sharding: str, wanted: str) -> bool:
-    s = (sharding or "").lower()
-    if wanted == "both":
-        return ("pipeline" in s) or ("tensor" in s)
-    return wanted in s
-
-
-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 settle_and_fetch_placements(
-    client: ExoClient,
-    full_model_id: str,
-    args: argparse.Namespace,
-    settle_timeout: float = 0,
-) -> list[dict[str, Any]]:
-    selected = fetch_and_filter_placements(client, full_model_id, args)
-
-    if not selected and settle_timeout > 0:
-        backoff = _SETTLE_INITIAL_BACKOFF_S
-        deadline = time.monotonic() + settle_timeout
-        while not selected and time.monotonic() < deadline:
-            remaining = 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)..."
-            )
-            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)
-
-    return selected
-
-
-def run_planning_phase(
-    client: ExoClient,
-    full_model_id: str,
-    preview: dict[str, Any],
-    danger_delete: bool,
-    timeout: float,
-    settle_deadline: float | None,
-) -> float | None:
-    """Check disk space and ensure model is downloaded before benchmarking.
-
-    Returns the wall-clock download duration in seconds if a fresh download
-    was needed, or None if the model was already cached on all nodes.
-    """
-    # 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 None
-
-    # 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", {})
-
-    needs_download = False
-
-    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
-
-        needs_download = True
-
-        # 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 (skip read-only models from EXO_MODELS_PATH)
-        completed = [
-            (
-                unwrap_instance(p["DownloadCompleted"]["shardMetadata"])["modelCard"][
-                    "modelId"
-                ],
-                p["DownloadCompleted"]["total"]["inBytes"],
-            )
-            for p in node_downloads
-            if "DownloadCompleted" in p
-            and not p["DownloadCompleted"].get("readOnly", False)
-        ]
-        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)
-    download_t0 = time.perf_counter() if needs_download else None
-    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:
-            if download_t0 is not None:
-                return time.perf_counter() - download_t0
-            return None
-        time.sleep(1)
-
-    raise TimeoutError("Downloads did not complete in time")
-
-
-def add_common_instance_args(ap: argparse.ArgumentParser) -> None:
-    ap.add_argument("--host", default=os.environ.get("EXO_HOST", "localhost"))
-    ap.add_argument(
-        "--port", type=int, default=int(os.environ.get("EXO_PORT", "52415"))
-    )
-    ap.add_argument("--model", required=True, help="Model short id or huggingface id")
-    ap.add_argument(
-        "--max-nodes",
-        type=int,
-        default=4,
-        help="Only consider placements using <= this many nodes.",
-    )
-    ap.add_argument(
-        "--min-nodes",
-        type=int,
-        default=1,
-        help="Only consider placements using >= this many nodes.",
-    )
-    ap.add_argument(
-        "--instance-meta", choices=["ring", "jaccl", "both"], default="both"
-    )
-    ap.add_argument(
-        "--sharding", choices=["pipeline", "tensor", "both"], default="both"
-    )
-    ap.add_argument(
-        "--skip-pipeline-jaccl",
-        action="store_true",
-        help="Skip pipeline+jaccl placements, as it's often pointless.",
-    )
-    ap.add_argument(
-        "--skip-tensor-ring",
-        action="store_true",
-        help="Skip tensor+ring placements, as it's so slow.",
-    )
-    ap.add_argument(
-        "--timeout", type=float, default=7200.0, help="HTTP timeout (seconds)."
-    )
-    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.",
-    )

bench/pyproject.toml

@@ -4,13 +4,11 @@ version = "0.1.0"
 description = "Benchmarking tool for exo distributed inference"
 requires-python = ">=3.13"
 dependencies = [
-  "httpx>=0.27.0",
-  "loguru>=0.7.3",
-  "transformers>=5.0.0",
-  "huggingface-hub>=0.33.4",
-  "tiktoken>=0.12.0",
-  "jinja2>=3.1.0",
-  "protobuf>=5.29.0",
+    "loguru>=0.7.3",
+    "transformers>=5.0.0",
+    "huggingface-hub>=0.33.4",
+    "tiktoken>=0.12.0",
+    "jinja2>=3.1.0",
 ]
 
 [build-system]

bench/scenarios.toml

@@ -1,306 +0,0 @@
-# Tool definitions — each becomes an OpenAI function tool.
-# All scenarios get all tools unless they specify a `tools` list.
-
-[tools.get_current_weather]
-description = "Get the current weather in a given location"
-required = ["location"]
-
-[tools.get_current_weather.properties.location]
-type = "string"
-description = "City and state, e.g. San Francisco, CA"
-
-[tools.get_current_weather.properties.unit]
-type = "string"
-enum = ["celsius", "fahrenheit"]
-description = "Temperature unit"
-
-[tools.calculate]
-description = "Evaluate a mathematical expression and return the numeric result"
-required = ["expression"]
-
-[tools.calculate.properties.expression]
-type = "string"
-description = "The math expression to evaluate, e.g. '2 + 3 * 4'"
-
-[tools.search_products]
-description = "Search for products in a catalog by query, category, and price"
-required = ["query"]
-
-[tools.search_products.properties.query]
-type = "string"
-description = "Search query string"
-
-[tools.search_products.properties.category]
-type = "string"
-enum = ["electronics", "clothing", "food", "books"]
-description = "Product category to filter by"
-
-[tools.search_products.properties.max_price]
-type = "number"
-description = "Maximum price in USD"
-
-[tools.create_todos]
-description = "Create a structured todo list"
-required = ["todos"]
-
-[tools.create_todos.properties.todos]
-type = "array"
-description = "List of todo items"
-
-[tools.create_todos.properties.todos.items]
-type = "object"
-required = ["content", "status", "priority"]
-
-[tools.create_todos.properties.todos.items.properties.content]
-type = "string"
-description = "The todo item text"
-
-[tools.create_todos.properties.todos.items.properties.status]
-type = "string"
-description = "Status: pending, in_progress, or completed"
-
-[tools.create_todos.properties.todos.items.properties.priority]
-type = "string"
-description = "Priority: low, normal, or high"
-
-# -- Should call a tool --
-
-[[scenarios]]
-name = "weather_simple"
-description = "Basic weather query -> get_current_weather"
-expect_tool_call = true
-expected_function = "get_current_weather"
-required_arg_keys = ["location"]
-
-[[scenarios.messages]]
-role = "user"
-content = "What's the weather like in Tokyo right now?"
-
-[[scenarios]]
-name = "calculator_simple"
-description = "Math question -> calculate"
-expect_tool_call = true
-expected_function = "calculate"
-required_arg_keys = ["expression"]
-
-[[scenarios.messages]]
-role = "user"
-content = "Use the calculator to compute 3847 * 926 + 17293"
-
-[[scenarios]]
-name = "search_with_filters"
-description = "Product search with category and price filter"
-expect_tool_call = true
-expected_function = "search_products"
-required_arg_keys = ["query"]
-
-[[scenarios.messages]]
-role = "user"
-content = "Find me electronics under $50"
-
-# -- Multi-turn: tool call then follow-up --
-
-[[scenarios]]
-name = "weather_multi_turn"
-description = "Weather query -> tool result -> natural language summary"
-expect_tool_call = true
-expected_function = "get_current_weather"
-required_arg_keys = ["location"]
-
-[scenarios.tool_result]
-temperature = "18C"
-condition = "partly cloudy"
-humidity = "65%"
-wind = "12 km/h NW"
-
-[[scenarios.messages]]
-role = "user"
-content = "What's the weather in Paris?"
-
-[[scenarios]]
-name = "calculator_multi_turn"
-description = "Math query -> tool result -> model reports the answer"
-expect_tool_call = true
-expected_function = "calculate"
-required_arg_keys = ["expression"]
-
-[scenarios.tool_result]
-result = 491682
-
-[[scenarios.messages]]
-role = "user"
-content = "Use the calculator to compute 1847 * 263 + 5921"
-
-[[scenarios]]
-name = "search_multi_turn"
-description = "Search query -> tool result -> model summarizes products"
-expect_tool_call = true
-expected_function = "search_products"
-required_arg_keys = ["query"]
-
-[[scenarios.tool_result.results]]
-name = "Hands-On Machine Learning"
-price = 45.99
-rating = 4.8
-
-[[scenarios.tool_result.results]]
-name = "Deep Learning with Python"
-price = 39.99
-rating = 4.6
-
-[[scenarios.messages]]
-role = "user"
-content = "Search for books about machine learning"
-
-# -- Sequential tool calls --
-
-[[scenarios]]
-name = "chained_tool_calls_same"
-description = "Thinking + weather(Tokyo) -> result -> model must call weather(London)"
-expect_tool_call = true
-expected_function = "get_current_weather"
-required_arg_keys = ["location"]
-
-[[scenarios.messages]]
-role = "user"
-content = "Compare the weather in Tokyo and London."
-
-[[scenarios.messages]]
-role = "assistant"
-content = "I'll check both cities. Let me start with Tokyo."
-
-[[scenarios.messages.tool_calls]]
-id = "call_1"
-name = "get_current_weather"
-arguments = { location = "Tokyo" }
-
-[[scenarios.messages]]
-role = "tool"
-tool_call_id = "call_1"
-content = '{"temperature": "25C", "condition": "sunny"}'
-
-[[scenarios]]
-name = "chained_tool_calls_different"
-description = "Thinking + weather(Berlin) -> result -> model must call calculator"
-expect_tool_call = true
-expected_function = "calculate"
-required_arg_keys = ["expression"]
-
-[[scenarios.messages]]
-role = "user"
-content = "What's the weather in Berlin, and also use the calculator to compute 4819 * 37 + 291."
-
-[[scenarios.messages]]
-role = "assistant"
-content = "I'll handle both. Let me check Berlin's weather first."
-
-[[scenarios.messages.tool_calls]]
-id = "call_2"
-name = "get_current_weather"
-arguments = { location = "Berlin" }
-
-[[scenarios.messages]]
-role = "tool"
-tool_call_id = "call_2"
-content = '{"temperature": "12C", "condition": "rainy"}'
-
-[[scenarios]]
-name = "chained_tool_calls_three"
-description = "Two prior thinking+tool calls -> results -> model must make a third"
-expect_tool_call = true
-expected_function = "get_current_weather"
-required_arg_keys = ["location"]
-
-[[scenarios.messages]]
-role = "user"
-content = "Compare weather in Tokyo, Paris, and London."
-
-[[scenarios.messages]]
-role = "assistant"
-content = "I'll check all three cities. Starting with Tokyo."
-
-[[scenarios.messages.tool_calls]]
-id = "call_3"
-name = "get_current_weather"
-arguments = { location = "Tokyo" }
-
-[[scenarios.messages]]
-role = "tool"
-tool_call_id = "call_3"
-content = '{"temperature": "25C", "condition": "sunny"}'
-
-[[scenarios.messages]]
-role = "assistant"
-content = "Got Tokyo. Now checking Paris."
-
-[[scenarios.messages.tool_calls]]
-id = "call_4"
-name = "get_current_weather"
-arguments = { location = "Paris" }
-
-[[scenarios.messages]]
-role = "tool"
-tool_call_id = "call_4"
-content = '{"temperature": "18C", "condition": "cloudy"}'
-
-# -- Nested object schema (regression for lossy chat template rendering) --
-
-[[scenarios]]
-name = "nested_schema_tool_call"
-description = "Tool call with nested object array schema -> create_todos"
-expect_tool_call = true
-expected_function = "create_todos"
-required_arg_keys = ["todos"]
-nested_array_key = "todos"
-required_item_keys = ["content", "status", "priority"]
-tools = ["create_todos"]
-
-[[scenarios.messages]]
-role = "user"
-content = "Create a todo list with 3 items to learn Python"
-
-# -- Tool name integrity (regression for harmony token leaking into name) --
-
-[tools.glob]
-description = "Search for files matching a glob pattern in the codebase"
-required = ["pattern"]
-
-[tools.glob.properties.pattern]
-type = "string"
-description = "The glob pattern to match files against, e.g. '**/*.py'"
-
-[tools.glob.properties.path]
-type = "string"
-description = "The directory to search in"
-
-[[scenarios]]
-name = "tool_name_integrity"
-description = "Tool name must not contain harmony tokens like <|channel|>"
-expect_tool_call = true
-expected_function = "glob"
-required_arg_keys = ["pattern"]
-tools = ["glob"]
-
-[[scenarios.messages]]
-role = "user"
-content = "Find all Python files in the src directory"
-
-# -- Should NOT call a tool --
-
-[[scenarios]]
-name = "no_tool_joke"
-description = "Joke request should NOT trigger any tool"
-expect_tool_call = false
-
-[[scenarios.messages]]
-role = "user"
-content = "Tell me a funny joke about cats."
-
-[[scenarios]]
-name = "no_tool_factual"
-description = "Factual question answerable from training data"
-expect_tool_call = false
-
-[[scenarios.messages]]
-role = "user"
-content = "What is the capital of Japan?"

bench/single-m3-ultra.toml

@@ -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))"]

conftest.py

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

dashboard/src/app.css

@@ -202,23 +202,6 @@
 	filter: drop-shadow(0 0 3px oklch(0.85 0.18 85 / 0.5));
 }
 
-/* Onboarding step 2: connection line between devices */
-.onboarding-connection-line {
-	stroke: oklch(0.85 0.18 85 / 0.5);
-	stroke-width: 1.5px;
-	stroke-dasharray: 6, 6;
-	animation: flowAnimation 1s linear infinite;
-	filter: drop-shadow(0 0 4px oklch(0.85 0.18 85 / 0.4));
-}
-
-/* Onboarding step 4: red connection line for disconnect */
-.onboarding-connection-line-red {
-	stroke: rgba(220, 38, 38, 0.7);
-	stroke-width: 1.5px;
-	stroke-dasharray: 6, 6;
-	filter: drop-shadow(0 0 2px rgba(220, 38, 38, 0.3));
-}
-
 .graph-link-active {
 	stroke: oklch(0.85 0.18 85 / 0.8);
 	stroke-width: 2px;
@@ -337,51 +320,3 @@ input:focus, textarea:focus {
 		transform: translate(400px, 400px);
 	}
 }
-
-/* Onboarding smooth fade-in */
-@keyframes onb-fade-in {
-	from { opacity: 0; transform: translateY(8px); }
-	to { opacity: 1; transform: none; }
-}
-
-/* Opacity-only fade-in — no transform, safe for containers with fixed-position children */
-@keyframes onb-fade-opacity {
-	from { opacity: 0; }
-	to { opacity: 1; }
-}
-
-/* Respect reduced motion preference */
-@media (prefers-reduced-motion: reduce) {
-	.shooting-star,
-	.shooting-star::before {
-		animation: none !important;
-		opacity: 0 !important;
-	}
-	.graph-link {
-		animation: none;
-	}
-	.status-pulse {
-		animation: none;
-	}
-	.cursor-blink {
-		animation: none;
-	}
-	.onboarding-connection-line {
-		animation: none;
-	}
-	.onboarding-connection-line-red {
-		animation: none;
-	}
-	[style*="onb-fade-in"],
-	[style*="onb-fade-opacity"] {
-		animation: none !important;
-		opacity: 1 !important;
-	}
-	*,
-	*::before,
-	*::after {
-		transition-duration: 0.01ms !important;
-		animation-duration: 0.01ms !important;
-		animation-iteration-count: 1 !important;
-	}
-}

dashboard/src/lib/components/ChatForm.svelte

@@ -7,12 +7,13 @@
     editingImage,
     clearEditingImage,
     selectedChatModel,
+    setSelectedChatModel,
+    instances,
     ttftMs,
     tps,
     totalTokens,
     thinkingEnabled as thinkingEnabledStore,
     setConversationThinking,
-    stopGeneration,
   } from "$lib/stores/app.svelte";
   import ChatAttachments from "./ChatAttachments.svelte";
   import ImageParamsPanel from "./ImageParamsPanel.svelte";
@@ -27,19 +28,6 @@
     showModelSelector?: boolean;
     modelTasks?: Record<string, string[]>;
     modelCapabilities?: Record<string, string[]>;
-    onSend?: () => void;
-    onAutoSend?: (
-      content: string,
-      files?: {
-        id: string;
-        name: string;
-        type: string;
-        textContent?: string;
-        preview?: string;
-      }[],
-    ) => void;
-    onOpenModelPicker?: () => void;
-    modelDisplayOverride?: string;
   }
 
   let {
@@ -50,10 +38,6 @@
     showModelSelector = false,
     modelTasks = {},
     modelCapabilities = {},
-    onSend,
-    onAutoSend,
-    onOpenModelPicker,
-    modelDisplayOverride,
   }: Props = $props();
 
   let message = $state("");
@@ -64,12 +48,27 @@
   const thinkingEnabled = $derived(thinkingEnabledStore());
   let loading = $derived(isLoading());
   const currentModel = $derived(selectedChatModel());
+  const instanceData = $derived(instances());
   const currentTtft = $derived(ttftMs());
   const currentTps = $derived(tps());
   const currentTokens = $derived(totalTokens());
   const currentEditingImage = $derived(editingImage());
   const isEditMode = $derived(currentEditingImage !== null);
 
+  // Custom dropdown state
+  let isModelDropdownOpen = $state(false);
+  let dropdownButtonRef: HTMLButtonElement | undefined = $state();
+  let dropdownPosition = $derived(() => {
+    if (!dropdownButtonRef || !isModelDropdownOpen)
+      return { top: 0, left: 0, width: 0 };
+    const rect = dropdownButtonRef.getBoundingClientRect();
+    return {
+      top: rect.top,
+      left: rect.left,
+      width: rect.width,
+    };
+  });
+
   // Accept all supported file types
   const acceptString = getAcceptString(["image", "text", "pdf"]);
 
@@ -104,7 +103,7 @@
   const modelSupportsThinking = $derived(() => {
     if (!currentModel) return false;
     const caps = modelCapabilities[currentModel] || [];
-    return caps.includes("thinking_toggle") && caps.includes("text");
+    return caps.includes("thinking") && caps.includes("text");
   });
 
   const isEditOnlyWithoutImage = $derived(
@@ -122,14 +121,73 @@
         uploadedFiles.length > 0),
   );
 
-  // Short label for the currently selected model
-  const currentModelLabel = $derived(
-    currentModel
-      ? currentModel.split("/").pop() || currentModel
-      : modelDisplayOverride
-        ? modelDisplayOverride.split("/").pop() || modelDisplayOverride
-        : "",
-  );
+  // Extract available models from running instances
+  const availableModels = $derived(() => {
+    const models: Array<{ id: string; label: string; isImageModel: boolean }> =
+      [];
+    for (const [, instance] of Object.entries(instanceData)) {
+      const modelId = getInstanceModelId(instance);
+      if (
+        modelId &&
+        modelId !== "Unknown" &&
+        !models.some((m) => m.id === modelId)
+      ) {
+        models.push({
+          id: modelId,
+          label: modelId.split("/").pop() || modelId,
+          isImageModel: modelSupportsImageGeneration(modelId),
+        });
+      }
+    }
+    return models;
+  });
+
+  // Track previous model IDs to detect newly added models (plain variable to avoid reactive loop)
+  let previousModelIds: Set<string> = new Set();
+
+  // Auto-select the first available model if none is selected, if current selection is stale, or if a new model is added
+  $effect(() => {
+    const models = availableModels();
+    const currentModelIds = new Set(models.map((m) => m.id));
+
+    if (models.length > 0) {
+      // Find newly added models (in current but not in previous)
+      const newModels = models.filter((m) => !previousModelIds.has(m.id));
+
+      // If no model selected, select the first available
+      if (!currentModel) {
+        setSelectedChatModel(models[0].id);
+      }
+      // If current model is stale (no longer has a running instance), reset to first available
+      else if (!models.some((m) => m.id === currentModel)) {
+        setSelectedChatModel(models[0].id);
+      }
+      // If a new model was just added, select it
+      else if (newModels.length > 0 && previousModelIds.size > 0) {
+        setSelectedChatModel(newModels[0].id);
+      }
+    } else {
+      // No instances running - clear the selected model
+      if (currentModel) {
+        setSelectedChatModel("");
+      }
+    }
+
+    // Update previous model IDs for next comparison
+    previousModelIds = currentModelIds;
+  });
+
+  function getInstanceModelId(instanceWrapped: unknown): string {
+    if (!instanceWrapped || typeof instanceWrapped !== "object") return "";
+    const keys = Object.keys(instanceWrapped as Record<string, unknown>);
+    if (keys.length === 1) {
+      const instance = (instanceWrapped as Record<string, unknown>)[
+        keys[0]
+      ] as { shardAssignments?: { modelId?: string } };
+      return instance?.shardAssignments?.modelId || "";
+    }
+    return "";
+  }
 
   async function handleFiles(files: File[]) {
     if (files.length === 0) return;
@@ -216,15 +274,6 @@
     uploadedFiles = [];
     resetTextareaHeight();
 
-    // When onAutoSend is provided, the parent controls all send logic
-    // (including launching non-running models before sending)
-    if (onAutoSend) {
-      onAutoSend(content, files);
-      onSend?.();
-      setTimeout(() => textareaRef?.focus(), 10);
-      return;
-    }
-
     // Use image editing if in edit mode
     if (isEditMode && currentEditingImage && content) {
       editImage(content, currentEditingImage.imageDataUrl);
@@ -256,8 +305,6 @@
       );
     }
 
-    onSend?.();
-
     // Refocus the textarea after sending
     setTimeout(() => textareaRef?.focus(), 10);
   }
@@ -368,7 +415,7 @@
     {/if}
 
     <!-- Model selector (when enabled) -->
-    {#if showModelSelector}
+    {#if showModelSelector && availableModels().length > 0}
       <div
         class="flex items-center justify-between gap-2 px-3 py-2 border-b border-exo-medium-gray/30"
       >
@@ -377,22 +424,33 @@
             class="text-xs text-exo-light-gray uppercase tracking-wider flex-shrink-0"
             >MODEL:</span
           >
-          <!-- Model button — opens the full model picker -->
+          <!-- Custom dropdown -->
           <div class="relative flex-1 max-w-xs">
             <button
+              bind:this={dropdownButtonRef}
               type="button"
-              onclick={() => onOpenModelPicker?.()}
-              class="w-full bg-exo-medium-gray/50 border border-exo-yellow/30 rounded pl-3 pr-8 py-1.5 text-xs font-mono text-left tracking-wide cursor-pointer transition-all duration-200 hover:border-exo-yellow/50 focus:outline-none focus:border-exo-yellow/70"
+              onclick={() => (isModelDropdownOpen = !isModelDropdownOpen)}
+              class="w-full bg-exo-medium-gray/50 border border-exo-yellow/30 rounded pl-3 pr-8 py-1.5 text-xs font-mono text-left tracking-wide cursor-pointer transition-all duration-200 hover:border-exo-yellow/50 focus:outline-none focus:border-exo-yellow/70 {isModelDropdownOpen
+                ? 'border-exo-yellow/70'
+                : ''}"
             >
-              {#if currentModelLabel}
-                <span class="text-exo-yellow truncate">{currentModelLabel}</span
+              {#if availableModels().find((m) => m.id === currentModel)}
+                <span class="text-exo-yellow truncate"
+                  >{availableModels().find((m) => m.id === currentModel)
+                    ?.label}</span
+                >
+              {:else if availableModels().length > 0}
+                <span class="text-exo-yellow truncate"
+                  >{availableModels()[0].label}</span
                 >
               {:else}
                 <span class="text-exo-light-gray/50">— SELECT MODEL —</span>
               {/if}
             </button>
             <div
-              class="absolute right-2 top-1/2 -translate-y-1/2 pointer-events-none"
+              class="absolute right-2 top-1/2 -translate-y-1/2 pointer-events-none transition-transform duration-200 {isModelDropdownOpen
+                ? 'rotate-180'
+                : ''}"
             >
               <svg
                 class="w-3 h-3 text-exo-yellow/60"
@@ -409,6 +467,78 @@
               </svg>
             </div>
           </div>
+
+          {#if isModelDropdownOpen}
+            <!-- Backdrop to close dropdown -->
+            <button
+              type="button"
+              class="fixed inset-0 z-[9998] cursor-default"
+              onclick={() => (isModelDropdownOpen = false)}
+              aria-label="Close dropdown"
+            ></button>
+
+            <!-- Dropdown Panel - fixed positioning to escape overflow:hidden -->
+            <div
+              class="fixed bg-exo-dark-gray border border-exo-yellow/30 rounded shadow-lg shadow-black/50 z-[9999] max-h-48 overflow-y-auto"
+              style="bottom: calc(100vh - {dropdownPosition()
+                .top}px + 4px); left: {dropdownPosition()
+                .left}px; width: {dropdownPosition().width}px;"
+            >
+              <div class="py-1">
+                {#each availableModels() as model}
+                  <button
+                    type="button"
+                    onclick={() => {
+                      setSelectedChatModel(model.id);
+                      isModelDropdownOpen = false;
+                    }}
+                    class="w-full px-3 py-2 text-left text-xs font-mono tracking-wide transition-colors duration-100 flex items-center gap-2 {currentModel ===
+                    model.id
+                      ? 'bg-transparent text-exo-yellow'
+                      : 'text-exo-light-gray hover:text-exo-yellow'}"
+                  >
+                    {#if currentModel === model.id}
+                      <svg
+                        class="w-3 h-3 flex-shrink-0"
+                        fill="currentColor"
+                        viewBox="0 0 20 20"
+                      >
+                        <path
+                          fill-rule="evenodd"
+                          d="M16.707 5.293a1 1 0 010 1.414l-8 8a1 1 0 01-1.414 0l-4-4a1 1 0 011.414-1.414L8 12.586l7.293-7.293a1 1 0 011.414 0z"
+                          clip-rule="evenodd"
+                        />
+                      </svg>
+                    {:else}
+                      <span class="w-3"></span>
+                    {/if}
+                    {#if model.isImageModel}
+                      <svg
+                        class="w-3.5 h-3.5 flex-shrink-0 text-exo-yellow"
+                        fill="none"
+                        viewBox="0 0 24 24"
+                        stroke="currentColor"
+                        stroke-width="2"
+                        aria-label="Image generation model"
+                      >
+                        <rect
+                          x="3"
+                          y="3"
+                          width="18"
+                          height="18"
+                          rx="2"
+                          ry="2"
+                        />
+                        <circle cx="8.5" cy="8.5" r="1.5" />
+                        <polyline points="21 15 16 10 5 21" />
+                      </svg>
+                    {/if}
+                    <span class="truncate flex-1">{model.label}</span>
+                  </button>
+                {/each}
+              </div>
+            </div>
+          {/if}
         </div>
         <!-- Thinking toggle -->
         {#if modelSupportsThinking()}
@@ -523,92 +653,86 @@
         style="min-height: 28px; max-height: 150px;"
       ></textarea>
 
-      {#if loading}
-        <button
-          type="button"
-          onclick={() => stopGeneration()}
-          class="px-2.5 sm:px-4 py-1.5 sm:py-2 rounded text-xs sm:text-xs tracking-[0.1em] sm:tracking-[0.15em] font-medium transition-all duration-200 whitespace-nowrap bg-exo-medium-gray/70 text-exo-light-gray hover:bg-exo-medium-gray hover:text-white"
-          aria-label="Stop generation"
-        >
+      <button
+        type="submit"
+        disabled={!canSend || loading || isEditOnlyWithoutImage}
+        class="px-2.5 sm:px-4 py-1.5 sm:py-2 rounded text-xs sm:text-xs tracking-[0.1em] sm:tracking-[0.15em] uppercase font-medium transition-all duration-200 whitespace-nowrap
+					{!canSend || loading || isEditOnlyWithoutImage
+          ? 'bg-exo-medium-gray/50 text-exo-light-gray cursor-not-allowed'
+          : 'bg-exo-yellow text-exo-black hover:bg-exo-yellow-darker hover:shadow-[0_0_20px_rgba(255,215,0,0.3)]'}"
+        aria-label={shouldShowEditMode
+          ? "Edit image"
+          : isImageModel()
+            ? "Generate image"
+            : "Send message"}
+      >
+        {#if loading}
           <span class="inline-flex items-center gap-1 sm:gap-2">
-            <svg
-              class="w-3 h-3 sm:w-3.5 sm:h-3.5"
-              fill="currentColor"
-              viewBox="0 0 24 24"
+            <span
+              class="w-2.5 h-2.5 sm:w-3 sm:h-3 border-2 border-current border-t-transparent rounded-full animate-spin"
+            ></span>
+            <span class="hidden sm:inline"
+              >{shouldShowEditMode
+                ? "EDITING"
+                : isImageModel()
+                  ? "GENERATING"
+                  : "PROCESSING"}</span
             >
-              <rect x="6" y="6" width="12" height="12" rx="1" />
-            </svg>
-            <span class="hidden sm:inline">Cancel</span>
+            <span class="sm:hidden">...</span>
           </span>
-        </button>
-      {:else}
-        <button
-          type="submit"
-          disabled={!canSend || isEditOnlyWithoutImage}
-          class="px-2.5 sm:px-4 py-1.5 sm:py-2 rounded text-xs sm:text-xs tracking-[0.1em] sm:tracking-[0.15em] uppercase font-medium transition-all duration-200 whitespace-nowrap
-					{!canSend || isEditOnlyWithoutImage
-            ? 'bg-exo-medium-gray/50 text-exo-light-gray cursor-not-allowed'
-            : 'bg-exo-yellow text-exo-black hover:bg-exo-yellow-darker hover:shadow-[0_0_20px_rgba(255,215,0,0.3)]'}"
-          aria-label={shouldShowEditMode
-            ? "Edit image"
-            : isImageModel()
-              ? "Generate image"
-              : "Send message"}
-        >
-          {#if shouldShowEditMode}
-            <span class="inline-flex items-center gap-1.5">
-              <svg
-                class="w-3.5 h-3.5"
-                fill="none"
-                viewBox="0 0 24 24"
-                stroke="currentColor"
-                stroke-width="2"
-              >
-                <path
-                  stroke-linecap="round"
-                  stroke-linejoin="round"
-                  d="M11 5H6a2 2 0 00-2 2v11a2 2 0 002 2h11a2 2 0 002-2v-5m-1.414-9.414a2 2 0 112.828 2.828L11.828 15H9v-2.828l8.586-8.586z"
-                />
-              </svg>
-              <span>EDIT</span>
-            </span>
-          {:else if isEditOnlyWithoutImage}
-            <span class="inline-flex items-center gap-1.5">
-              <svg
-                class="w-3.5 h-3.5"
-                fill="none"
-                viewBox="0 0 24 24"
-                stroke="currentColor"
-                stroke-width="2"
-              >
-                <path
-                  stroke-linecap="round"
-                  stroke-linejoin="round"
-                  d="M11 5H6a2 2 0 00-2 2v11a2 2 0 002 2h11a2 2 0 002-2v-5m-1.414-9.414a2 2 0 112.828 2.828L11.828 15H9v-2.828l8.586-8.586z"
-                />
-              </svg>
-              <span>EDIT</span>
-            </span>
-          {:else if isImageModel()}
-            <span class="inline-flex items-center gap-1.5">
-              <svg
-                class="w-3.5 h-3.5"
-                fill="none"
-                viewBox="0 0 24 24"
-                stroke="currentColor"
-                stroke-width="2"
-              >
-                <rect x="3" y="3" width="18" height="18" rx="2" ry="2" />
-                <circle cx="8.5" cy="8.5" r="1.5" />
-                <polyline points="21 15 16 10 5 21" />
-              </svg>
-              <span>GENERATE</span>
-            </span>
-          {:else}
-            SEND
-          {/if}
-        </button>
-      {/if}
+        {:else if shouldShowEditMode}
+          <span class="inline-flex items-center gap-1.5">
+            <svg
+              class="w-3.5 h-3.5"
+              fill="none"
+              viewBox="0 0 24 24"
+              stroke="currentColor"
+              stroke-width="2"
+            >
+              <path
+                stroke-linecap="round"
+                stroke-linejoin="round"
+                d="M11 5H6a2 2 0 00-2 2v11a2 2 0 002 2h11a2 2 0 002-2v-5m-1.414-9.414a2 2 0 112.828 2.828L11.828 15H9v-2.828l8.586-8.586z"
+              />
+            </svg>
+            <span>EDIT</span>
+          </span>
+        {:else if isEditOnlyWithoutImage}
+          <span class="inline-flex items-center gap-1.5">
+            <svg
+              class="w-3.5 h-3.5"
+              fill="none"
+              viewBox="0 0 24 24"
+              stroke="currentColor"
+              stroke-width="2"
+            >
+              <path
+                stroke-linecap="round"
+                stroke-linejoin="round"
+                d="M11 5H6a2 2 0 00-2 2v11a2 2 0 002 2h11a2 2 0 002-2v-5m-1.414-9.414a2 2 0 112.828 2.828L11.828 15H9v-2.828l8.586-8.586z"
+              />
+            </svg>
+            <span>EDIT</span>
+          </span>
+        {:else if isImageModel()}
+          <span class="inline-flex items-center gap-1.5">
+            <svg
+              class="w-3.5 h-3.5"
+              fill="none"
+              viewBox="0 0 24 24"
+              stroke="currentColor"
+              stroke-width="2"
+            >
+              <rect x="3" y="3" width="18" height="18" rx="2" ry="2" />
+              <circle cx="8.5" cy="8.5" r="1.5" />
+              <polyline points="21 15 16 10 5 21" />
+            </svg>
+            <span>GENERATE</span>
+          </span>
+        {:else}
+          SEND
+        {/if}
+      </button>
     </div>
 
     <!-- Bottom accent line -->

dashboard/src/lib/components/ChatMessages.svelte

@@ -3,17 +3,16 @@
     messages,
     currentResponse,
     isLoading,
-    prefillProgress,
     deleteMessage,
     editAndRegenerate,
     regenerateLastResponse,
     regenerateFromToken,
     setEditingImage,
   } from "$lib/stores/app.svelte";
+  import type { Message } from "$lib/stores/app.svelte";
   import type { MessageAttachment } from "$lib/stores/app.svelte";
   import MarkdownContent from "./MarkdownContent.svelte";
   import TokenHeatmap from "./TokenHeatmap.svelte";
-  import PrefillProgressBar from "./PrefillProgressBar.svelte";
   import ImageLightbox from "./ImageLightbox.svelte";
 
   interface Props {
@@ -26,7 +25,6 @@
   const messageList = $derived(messages());
   const response = $derived(currentResponse());
   const loading = $derived(isLoading());
-  const prefill = $derived(prefillProgress());
 
   // Scroll management - user controls scroll, show button when not at bottom
   const SCROLL_THRESHOLD = 100;
@@ -430,9 +428,6 @@
             {:else}
               <!-- Assistant message styling -->
               <div class="p-3 sm:p-4">
-                {#if loading && isLastAssistantMessage(message.id) && prefill && !message.content}
-                  <PrefillProgressBar progress={prefill} class="mb-3" />
-                {/if}
                 {#if message.thinking && message.thinking.trim().length > 0}
                   <div
                     class="mb-3 rounded border border-exo-yellow/20 bg-exo-black/40"
@@ -807,8 +802,8 @@
       >
         AWAITING INPUT
       </p>
-      <p class="text-xs text-white/30 tracking-wider mt-1.5 font-mono">
-        Type a message below &middot; Shift+Enter for newline
+      <p class="text-sm sm:text-xs text-exo-light-gray tracking-wider mt-1">
+        ENTER A QUERY TO BEGIN
       </p>
     </div>
   {/if}
@@ -823,7 +818,6 @@
       onclick={scrollToBottom}
       class="sticky bottom-4 left-1/2 -translate-x-1/2 w-10 h-10 rounded-full bg-exo-dark-gray/90 border border-exo-medium-gray/50 flex items-center justify-center text-exo-light-gray hover:text-exo-yellow hover:border-exo-yellow/50 transition-all shadow-lg cursor-pointer z-10"
       title="Scroll to bottom"
-      aria-label="Scroll to bottom of messages"
     >
       <svg
         class="w-5 h-5"

dashboard/src/lib/components/ChatModelSelector.svelte

@@ -1,401 +0,0 @@
-<script lang="ts" module>
-  export interface ChatModelInfo {
-    id: string;
-    name: string;
-    base_model: string;
-    storage_size_megabytes: number;
-    capabilities: string[];
-    family: string;
-    quantization: string;
-  }
-
-  // Auto mode tier list (for when user just starts typing)
-  export const AUTO_TIERS: string[][] = [
-    // Tier 1 (frontier)
-    ["DeepSeek V3.1", "GLM-5", "Kimi K2.5", "Qwen3 Coder Next"],
-    // Tier 2 (excellent)
-    [
-      "Kimi K2",
-      "Qwen3 235B",
-      "MiniMax M2.5",
-      "Step 3.5 Flash",
-      "Qwen3 Next 80B",
-    ],
-    // Tier 3 (great)
-    [
-      "GLM 4.7",
-      "MiniMax M2.1",
-      "Qwen3 Coder 480B",
-      "GLM 4.5 Air",
-      "Llama 3.3 70B",
-    ],
-    // Tier 4 (good)
-    ["GPT-OSS 120B", "Qwen3 30B", "Llama 3.1 70B", "GLM 4.7 Flash"],
-    // Tier 5 (small/fast)
-    [
-      "Llama 3.1 8B",
-      "GPT-OSS 20B",
-      "Llama 3.2 3B",
-      "Qwen3 0.6B",
-      "Llama 3.2 1B",
-    ],
-  ];
-
-  /** Return the tier index (0 = best) for a base_model name. */
-  export function getAutoTierIndex(baseModel: string): number {
-    for (let i = 0; i < AUTO_TIERS.length; i++) {
-      if (AUTO_TIERS[i].includes(baseModel)) return i;
-    }
-    return AUTO_TIERS.length; // not in any tier → lowest priority
-  }
-
-  /** Auto mode: walk tiers top-down, pick biggest fitting variant from highest tier. */
-  export function pickAutoModel(
-    modelList: ChatModelInfo[],
-    memoryGB: number,
-  ): ChatModelInfo | null {
-    for (const tier of AUTO_TIERS) {
-      const candidates: ChatModelInfo[] = [];
-      for (const baseModel of tier) {
-        const variants = modelList
-          .filter(
-            (m) =>
-              m.base_model === baseModel &&
-              (m.storage_size_megabytes || 0) / 1024 <= memoryGB &&
-              (m.storage_size_megabytes || 0) > 0,
-          )
-          .sort(
-            (a, b) =>
-              (b.storage_size_megabytes || 0) - (a.storage_size_megabytes || 0),
-          );
-        if (variants[0]) candidates.push(variants[0]);
-      }
-      if (candidates.length > 0) {
-        candidates.sort(
-          (a, b) =>
-            (b.storage_size_megabytes || 0) - (a.storage_size_megabytes || 0),
-        );
-        return candidates[0];
-      }
-    }
-    return null;
-  }
-</script>
-
-<script lang="ts">
-  interface CategoryRecommendation {
-    category: "coding" | "writing" | "agentic" | "biggest";
-    label: string;
-    model: ChatModelInfo | null;
-    tooltip: string;
-  }
-
-  interface Props {
-    models: ChatModelInfo[];
-    clusterLabel: string;
-    totalMemoryGB: number;
-    onSelect: (modelId: string, category: string) => void;
-    onAddModel: () => void;
-    class?: string;
-  }
-
-  let {
-    models,
-    clusterLabel,
-    totalMemoryGB,
-    onSelect,
-    onAddModel,
-    class: className = "",
-  }: Props = $props();
-
-  // --- Hardcoded Rankings ---
-  const CODING_RANKING = [
-    "Qwen3 Coder Next",
-    "Qwen3 Coder 480B",
-    "Qwen3 30B",
-    "GPT-OSS 20B",
-    "Llama 3.1 8B",
-    "Llama 3.2 3B",
-    "Qwen3 0.6B",
-  ];
-
-  const WRITING_RANKING = [
-    "Kimi K2.5",
-    "Kimi K2",
-    "Qwen3 Next 80B",
-    "Llama 3.3 70B",
-    "MiniMax M2.5",
-    "GLM 4.5 Air",
-    "GLM 4.7 Flash",
-    "GPT-OSS 20B",
-    "Llama 3.1 8B",
-    "Llama 3.2 3B",
-    "Qwen3 0.6B",
-  ];
-
-  const AGENTIC_RANKING = [
-    "DeepSeek V3.1",
-    "GLM-5",
-    "Qwen3 235B",
-    "Step 3.5 Flash",
-    "GLM 4.7",
-    "MiniMax M2.1",
-    "GPT-OSS 120B",
-    "Llama 3.3 70B",
-    "Llama 3.1 70B",
-    "GLM 4.7 Flash",
-    "GPT-OSS 20B",
-    "Qwen3 30B",
-    "Llama 3.1 8B",
-    "Llama 3.2 3B",
-    "Qwen3 0.6B",
-  ];
-
-  function getModelSizeGB(m: ChatModelInfo): number {
-    return (m.storage_size_megabytes || 0) / 1024;
-  }
-
-  function fitsInMemory(m: ChatModelInfo): boolean {
-    return getModelSizeGB(m) <= totalMemoryGB && getModelSizeGB(m) > 0;
-  }
-
-  /** For a given base_model name, find the biggest quant variant that fits in memory. */
-  function pickBestVariant(baseModel: string): ChatModelInfo | null {
-    const variants = models
-      .filter((m) => m.base_model === baseModel && fitsInMemory(m))
-      .sort((a, b) => getModelSizeGB(b) - getModelSizeGB(a));
-    return variants[0] ?? null;
-  }
-
-  /** Walk a ranked list of base_model names, return the first that has a fitting variant. */
-  function pickFromRanking(ranking: string[]): ChatModelInfo | null {
-    for (const baseModel of ranking) {
-      const pick = pickBestVariant(baseModel);
-      if (pick) return pick;
-    }
-    return null;
-  }
-
-  /** Pick the single biggest model that fits. */
-  function pickBiggest(): ChatModelInfo | null {
-    const fitting = models
-      .filter((m) => fitsInMemory(m))
-      .sort((a, b) => getModelSizeGB(b) - getModelSizeGB(a));
-    return fitting[0] ?? null;
-  }
-
-  const recommendations = $derived.by((): CategoryRecommendation[] => {
-    return [
-      {
-        category: "coding",
-        label: "Best for Coding",
-        model: pickFromRanking(CODING_RANKING),
-        tooltip:
-          "Ranked by coding benchmark performance (LiveCodeBench, SWE-bench)",
-      },
-      {
-        category: "writing",
-        label: "Best for Writing",
-        model: pickFromRanking(WRITING_RANKING),
-        tooltip: "Ranked by creative writing quality and instruction following",
-      },
-      {
-        category: "agentic",
-        label: "Best Agentic",
-        model: pickFromRanking(AGENTIC_RANKING),
-        tooltip: "Ranked by reasoning, planning, and tool-use capability",
-      },
-      {
-        category: "biggest",
-        label: "Biggest",
-        model: pickBiggest(),
-        tooltip: "Largest model that fits in your available memory",
-      },
-    ];
-  });
-
-  function formatSize(mb: number): string {
-    const gb = mb / 1024;
-    if (gb >= 100) return `${Math.round(gb)} GB`;
-    return `${gb.toFixed(1)} GB`;
-  }
-
-  // Category icons (SVG paths)
-  const categoryIcons: Record<string, string> = {
-    coding:
-      "M8 9l3 3-3 3m5 0h3M5 20h14a2 2 0 002-2V6a2 2 0 00-2-2H5a2 2 0 00-2 2v12a2 2 0 002 2z",
-    writing:
-      "M11 5H6a2 2 0 00-2 2v11a2 2 0 002 2h11a2 2 0 002-2v-5m-1.414-9.414a2 2 0 112.828 2.828L11.828 15H9v-2.828l8.586-8.586z",
-    agentic:
-      "M9.663 17h4.673M12 3v1m6.364 1.636l-.707.707M21 12h-1M4 12H3m3.343-5.657l-.707-.707m2.828 9.9a5 5 0 117.072 0l-.548.547A3.374 3.374 0 0014 18.469V19a2 2 0 11-4 0v-.531c0-.895-.356-1.754-.988-2.386l-.548-.547z",
-    biggest:
-      "M19 11H5m14 0a2 2 0 012 2v6a2 2 0 01-2 2H5a2 2 0 01-2-2v-6a2 2 0 012-2m14 0V9a2 2 0 00-2-2M5 11V9a2 2 0 012-2m0 0V5a2 2 0 012-2h6a2 2 0 012 2v2M7 7h10",
-  };
-
-  let hoveredTooltip = $state<string | null>(null);
-  let tooltipAnchor = $state<{ x: number; y: number } | null>(null);
-
-  function showTooltip(category: string, e: MouseEvent | FocusEvent) {
-    hoveredTooltip = category;
-    const target = e.currentTarget as HTMLElement;
-    const rect = target.getBoundingClientRect();
-    tooltipAnchor = { x: rect.left + rect.width / 2, y: rect.top };
-  }
-
-  function hideTooltip() {
-    hoveredTooltip = null;
-    tooltipAnchor = null;
-  }
-</script>
-
-<div class="flex flex-col items-center justify-center gap-6 {className}">
-  <!-- Header -->
-  <div class="text-center">
-    <p class="text-xs text-exo-light-gray uppercase tracking-[0.2em] mb-1">
-      Recommended for your
-    </p>
-    <p class="text-sm text-white font-mono tracking-wide">{clusterLabel}</p>
-  </div>
-
-  <!-- Category Cards Grid -->
-  <div class="grid grid-cols-2 gap-3 w-full max-w-md">
-    {#each recommendations as rec}
-      {#if rec.model}
-        <button
-          type="button"
-          onclick={() => rec.model && onSelect(rec.model.id, rec.category)}
-          class="group relative flex flex-col items-start gap-2 p-4 rounded-lg border border-exo-medium-gray/50 bg-exo-dark-gray/50 hover:border-exo-yellow/40 hover:bg-exo-dark-gray transition-all duration-200 cursor-pointer text-left"
-        >
-          <!-- Category icon + label -->
-          <div class="flex items-center gap-2 w-full">
-            <svg
-              class="w-4 h-4 text-exo-yellow/70 group-hover:text-exo-yellow transition-colors flex-shrink-0"
-              fill="none"
-              viewBox="0 0 24 24"
-              stroke="currentColor"
-              stroke-width="1.5"
-            >
-              <path
-                stroke-linecap="round"
-                stroke-linejoin="round"
-                d={categoryIcons[rec.category]}
-              />
-            </svg>
-            <span
-              class="text-xs font-mono uppercase tracking-wider text-exo-light-gray group-hover:text-white transition-colors"
-            >
-              {rec.label}
-            </span>
-            <!-- Info tooltip -->
-            <div class="ml-auto flex-shrink-0">
-              <span
-                role="button"
-                tabindex="-1"
-                class="text-exo-light-gray/40 hover:text-exo-light-gray transition-colors cursor-help inline-flex"
-                onmouseenter={(e: MouseEvent) => showTooltip(rec.category, e)}
-                onmouseleave={() => hideTooltip()}
-                onclick={(e: MouseEvent) => {
-                  e.stopPropagation();
-                  if (hoveredTooltip === rec.category) {
-                    hideTooltip();
-                  } else {
-                    showTooltip(rec.category, e);
-                  }
-                }}
-              >
-                <svg
-                  class="w-3.5 h-3.5"
-                  fill="none"
-                  viewBox="0 0 24 24"
-                  stroke="currentColor"
-                  stroke-width="2"
-                >
-                  <circle cx="12" cy="12" r="10" />
-                  <path d="M12 16v-4m0-4h.01" />
-                </svg>
-              </span>
-            </div>
-          </div>
-
-          <!-- Model name + size -->
-          <div class="w-full">
-            <p class="text-sm text-white font-mono truncate">
-              {rec.model.base_model}
-            </p>
-            <p class="text-xs text-exo-light-gray/60 font-mono mt-0.5">
-              {formatSize(rec.model.storage_size_megabytes)}
-              {#if rec.model.quantization}
-                <span class="text-exo-light-gray/40"
-                  >&middot; {rec.model.quantization}</span
-                >
-              {/if}
-            </p>
-          </div>
-        </button>
-      {:else}
-        <!-- No model fits for this category -->
-        <div
-          class="flex flex-col items-start gap-2 p-4 rounded-lg border border-exo-medium-gray/30 bg-exo-dark-gray/30 opacity-50"
-        >
-          <div class="flex items-center gap-2">
-            <svg
-              class="w-4 h-4 text-exo-light-gray/40 flex-shrink-0"
-              fill="none"
-              viewBox="0 0 24 24"
-              stroke="currentColor"
-              stroke-width="1.5"
-            >
-              <path
-                stroke-linecap="round"
-                stroke-linejoin="round"
-                d={categoryIcons[rec.category]}
-              />
-            </svg>
-            <span
-              class="text-xs font-mono uppercase tracking-wider text-exo-light-gray/50"
-              >{rec.label}</span
-            >
-          </div>
-          <p class="text-xs text-exo-light-gray/40 font-mono">No model fits</p>
-        </div>
-      {/if}
-    {/each}
-  </div>
-
-  <!-- Add Model Button -->
-  <button
-    type="button"
-    onclick={onAddModel}
-    class="flex items-center gap-2 px-4 py-2 text-xs font-mono uppercase tracking-wider text-exo-light-gray hover:text-exo-yellow border border-exo-medium-gray/30 hover:border-exo-yellow/30 rounded-lg transition-all duration-200 cursor-pointer"
-  >
-    <svg
-      class="w-3.5 h-3.5"
-      fill="none"
-      viewBox="0 0 24 24"
-      stroke="currentColor"
-      stroke-width="2"
-    >
-      <path stroke-linecap="round" stroke-linejoin="round" d="M12 4v16m8-8H4" />
-    </svg>
-    Add Model
-  </button>
-
-  <!-- Auto hint -->
-  <p class="text-xs text-exo-light-gray/40 font-mono tracking-wide text-center">
-    Or just start typing &mdash; we'll pick the best model automatically
-  </p>
-</div>
-
-<!-- Fixed-position tooltip (escapes overflow-hidden ancestors) -->
-{#if hoveredTooltip && tooltipAnchor}
-  {@const rec = recommendations.find((r) => r.category === hoveredTooltip)}
-  {#if rec}
-    <div
-      class="fixed z-[9999] px-3 py-2 bg-exo-black border border-exo-medium-gray/50 rounded text-xs text-exo-light-gray whitespace-nowrap shadow-lg pointer-events-none"
-      style="left: {tooltipAnchor.x}px; top: {tooltipAnchor.y -
-        8}px; transform: translate(-50%, -100%);"
-    >
-      {rec.tooltip}
-    </div>
-  {/if}
-{/if}

dashboard/src/lib/components/ChatSidebar.svelte

@@ -2,6 +2,7 @@
   import {
     conversations,
     activeConversationId,
+    createConversation,
     loadConversation,
     deleteConversation,
     deleteAllConversations,
@@ -16,15 +17,9 @@
 
   interface Props {
     class?: string;
-    onNewChat?: () => void;
-    onSelectConversation?: () => void;
   }
 
-  let {
-    class: className = "",
-    onNewChat,
-    onSelectConversation,
-  }: Props = $props();
+  let { class: className = "" }: Props = $props();
 
   const conversationList = $derived(conversations());
   const activeId = $derived(activeConversationId());
@@ -47,11 +42,10 @@
   );
 
   function handleNewChat() {
-    onNewChat?.();
+    createConversation();
   }
 
   function handleSelectConversation(id: string) {
-    onSelectConversation?.();
     loadConversation(id);
   }
 
@@ -191,7 +185,11 @@
 
     let instanceType: string | null = null;
     if (instanceTag === "MlxRingInstance") instanceType = "MLX Ring";
-    else if (instanceTag === "MlxJacclInstance") instanceType = "MLX RDMA";
+    else if (
+      instanceTag === "MlxIbvInstance" ||
+      instanceTag === "MlxJacclInstance"
+    )
+      instanceType = "MLX RDMA";
 
     let sharding: string | null = null;
     const inst = instance as {
@@ -309,7 +307,7 @@
       <div class="py-2">
         <div class="px-4 py-2">
           <span
-            class="text-xs text-exo-light-gray font-mono tracking-wider uppercase"
+            class="text-sm text-white/70 font-mono tracking-wider uppercase"
           >
             {searchQuery ? "SEARCH RESULTS" : "CONVERSATIONS"}
           </span>
@@ -378,37 +376,39 @@
                 onkeydown={(e) =>
                   e.key === "Enter" &&
                   handleSelectConversation(conversation.id)}
-                class="group w-full flex items-center justify-between p-2.5 rounded-lg mb-1 transition-all text-left cursor-pointer
+                class="group w-full flex items-center justify-between p-2 rounded mb-1 transition-all text-left cursor-pointer
 									{activeId === conversation.id
-                  ? 'bg-exo-yellow/5 border border-exo-yellow/30'
-                  : 'hover:bg-white/[0.03] hover:border-white/10 border border-transparent'}"
+                  ? 'bg-transparent border border-exo-yellow/30'
+                  : 'hover:border-exo-yellow/20 border border-transparent'}"
               >
                 <div class="flex-1 min-w-0 pr-2">
                   <div
-                    class="text-sm font-medium truncate {activeId ===
-                    conversation.id
+                    class="text-sm truncate {activeId === conversation.id
                       ? 'text-exo-yellow'
-                      : 'text-white'}"
+                      : 'text-white/90'}"
                   >
                     {conversation.name}
                   </div>
-                  <div class="text-xs text-white/60 mt-0.5">
+                  <div class="text-sm text-white/50 mt-0.5">
                     {formatDate(conversation.updatedAt)}
                   </div>
-                  <div class="text-xs text-exo-light-gray truncate">
+                  <div class="text-sm text-white/70 truncate">
                     {info.modelLabel}
                   </div>
+                  <div class="text-xs text-white/60 font-mono">
+                    Strategy: <span class="text-white/80"
+                      >{info.strategyLabel}</span
+                    >
+                  </div>
                   {#if stats}
-                    <div class="text-xs text-white/70 font-mono mt-1">
-                      {#if stats.ttftMs}<span class="text-white/50">TTFT</span>
-                        <span class="text-exo-yellow/80"
-                          >{stats.ttftMs.toFixed(0)}ms</span
-                        >{/if}{#if stats.ttftMs && stats.tps}<span
-                          class="text-white/30 mx-1.5">·</span
-                        >{/if}{#if stats.tps}<span class="text-exo-yellow/80"
-                          >{stats.tps.toFixed(1)}</span
-                        >
-                        <span class="text-white/50">tok/s</span>{/if}
+                    <div class="text-xs text-white/60 font-mono mt-1">
+                      {#if stats.ttftMs}<span class="text-white/40">TTFT</span>
+                        {stats.ttftMs.toFixed(
+                          0,
+                        )}ms{/if}{#if stats.ttftMs && stats.tps}<span
+                          class="text-white/30 mx-1.5">•</span
+                        >{/if}{#if stats.tps}{stats.tps.toFixed(1)}
+                        <span class="text-white/40">tok/s</span>{/if}
                     </div>
                   {/if}
                 </div>

dashboard/src/lib/components/ConnectionBanner.svelte

@@ -1,20 +0,0 @@
-<script lang="ts">
-  import { isConnected } from "$lib/stores/app.svelte";
-  import { slide } from "svelte/transition";
-
-  const connected = $derived(isConnected());
-</script>
-
-{#if !connected}
-  <div
-    transition:slide={{ duration: 200 }}
-    class="relative z-50 flex items-center justify-center gap-2 px-4 py-2 bg-red-950/80 border-b border-red-500/30"
-    role="alert"
-    aria-live="assertive"
-  >
-    <div class="w-2 h-2 bg-red-500 rounded-full animate-pulse"></div>
-    <span class="text-xs font-mono text-red-300 tracking-wider uppercase">
-      Connection lost &mdash; Reconnecting to backend&hellip;
-    </span>
-  </div>
-{/if}

dashboard/src/lib/components/DeviceIcon.svelte

@@ -1,277 +0,0 @@
-<script lang="ts">
-  /**
-   * DeviceIcon — renders a device icon as an SVG <g> element.
-   * Uses the exact same proportional math as TopologyGraph.svelte
-   * so that devices look identical in both the topology view and
-   * the onboarding animation.
-   *
-   * Must be placed inside an <svg> element.
-   */
-
-  interface Props {
-    /** "macbook pro" | "mac studio" | "mac mini" etc. */
-    deviceType: string;
-    /** Center X coordinate in SVG space */
-    cx: number;
-    /** Center Y coordinate in SVG space */
-    cy: number;
-    /** Base sizing factor (equivalent to TopologyGraph's nodeRadius) */
-    size?: number;
-    /** RAM usage 0–100 */
-    ramPercent?: number;
-    /** Unique id suffix for clip-path ids */
-    uid?: string;
-  }
-
-  let {
-    deviceType,
-    cx,
-    cy,
-    size = 60,
-    ramPercent = 60,
-    uid = "dev",
-  }: Props = $props();
-
-  // Apple logo path — same constant used by TopologyGraph
-  const APPLE_LOGO_PATH =
-    "M788.1 340.9c-5.8 4.5-108.2 62.2-108.2 190.5 0 148.4 130.3 200.9 134.2 202.2-.6 3.2-20.7 71.9-68.7 141.9-42.8 61.6-87.5 123.1-155.5 123.1s-85.5-39.5-164-39.5c-76.5 0-103.7 40.8-165.9 40.8s-105.6-57-155.5-127C46.7 790.7 0 663 0 541.8c0-194.4 126.4-297.5 250.8-297.5 66.1 0 121.2 43.4 162.7 43.4 39.5 0 101.1-46 176.3-46 28.5 0 130.9 2.6 198.3 99.2zm-234-181.5c31.1-36.9 53.1-88.1 53.1-139.3 0-7.1-.6-14.3-1.9-20.1-50.6 1.9-110.8 33.7-147.1 75.8-28.5 32.4-55.1 83.6-55.1 135.5 0 7.8 1.3 15.6 1.9 18.1 3.2.6 8.4 1.3 13.6 1.3 45.4 0 102.5-30.4 135.5-71.3z";
-  const LOGO_NATIVE_WIDTH = 814;
-  const LOGO_NATIVE_HEIGHT = 1000;
-
-  const wireColor = "rgba(179,179,179,0.8)";
-  const strokeWidth = 1.5;
-
-  const modelLower = $derived(deviceType.toLowerCase());
-
-  // ── Mac Studio dimensions (same ratios as TopologyGraph) ──
-  const studioW = $derived(size * 1.25);
-  const studioH = $derived(size * 0.85);
-  const studioX = $derived(cx - studioW / 2);
-  const studioY = $derived(cy - studioH / 2);
-  const studioCorner = 4;
-  const studioTopH = $derived(studioH * 0.15);
-
-  // Studio front panel details
-  const studioSlotH = $derived(studioH * 0.14);
-  const studioVSlotW = $derived(studioW * 0.05);
-  const studioVSlotY = $derived(
-    studioY + studioTopH + (studioH - studioTopH) * 0.6,
-  );
-  const studioVSlot1X = $derived(studioX + studioW * 0.18);
-  const studioVSlot2X = $derived(studioX + studioW * 0.28);
-  const studioHSlotW = $derived(studioW * 0.2);
-  const studioHSlotX = $derived(studioX + studioW * 0.5 - studioHSlotW / 2);
-
-  // Studio memory fill
-  const studioMemTotalH = $derived(studioH - studioTopH);
-  const studioMemH = $derived((ramPercent / 100) * studioMemTotalH);
-
-  // ── MacBook dimensions (same ratios as TopologyGraph) ──
-  const mbW = $derived((size * 1.6 * 0.85) / 1.15);
-  const mbH = $derived(size * 0.85);
-  const mbX = $derived(cx - mbW / 2);
-  const mbY = $derived(cy - mbH / 2);
-
-  const mbScreenH = $derived(mbH * 0.7);
-  const mbBaseH = $derived(mbH * 0.3);
-  const mbScreenW = $derived(mbW * 0.85);
-  const mbScreenX = $derived(cx - mbScreenW / 2);
-  const mbBezel = 3;
-
-  // MacBook memory fill
-  const mbMemTotalH = $derived(mbScreenH - mbBezel * 2);
-  const mbMemH = $derived((ramPercent / 100) * mbMemTotalH);
-
-  // Apple logo sizing
-  const mbLogoTargetH = $derived(mbScreenH * 0.22);
-  const mbLogoScale = $derived(mbLogoTargetH / LOGO_NATIVE_HEIGHT);
-  const mbLogoX = $derived(cx - (LOGO_NATIVE_WIDTH * mbLogoScale) / 2);
-  const mbLogoY = $derived(
-    mbY + mbScreenH / 2 - (LOGO_NATIVE_HEIGHT * mbLogoScale) / 2,
-  );
-
-  // MacBook base (trapezoidal)
-  const mbBaseY = $derived(mbY + mbScreenH);
-  const mbBaseTopW = $derived(mbScreenW);
-  const mbBaseBottomW = $derived(mbW);
-  const mbBaseTopX = $derived(cx - mbBaseTopW / 2);
-  const mbBaseBottomX = $derived(cx - mbBaseBottomW / 2);
-
-  // Keyboard
-  const mbKbX = $derived(mbBaseTopX + 6);
-  const mbKbY = $derived(mbBaseY + 3);
-  const mbKbW = $derived(mbBaseTopW - 12);
-  const mbKbH = $derived(mbBaseH * 0.55);
-
-  // Trackpad
-  const mbTpW = $derived(mbBaseTopW * 0.4);
-  const mbTpX = $derived(cx - mbTpW / 2);
-  const mbTpY = $derived(mbBaseY + mbKbH + 5);
-  const mbTpH = $derived(mbBaseH * 0.3);
-
-  // Clip IDs
-  const screenClipId = $derived(`di-screen-${uid}`);
-  const studioClipId = $derived(`di-studio-${uid}`);
-</script>
-
-{#if modelLower === "mac studio" || modelLower === "mac mini"}
-  <!-- Mac Studio / Mac Mini -->
-  <defs>
-    <clipPath id={studioClipId}>
-      <rect
-        x={studioX}
-        y={studioY + studioTopH}
-        width={studioW}
-        height={studioH - studioTopH}
-        rx={studioCorner - 1}
-      />
-    </clipPath>
-  </defs>
-
-  <!-- Main body -->
-  <rect
-    x={studioX}
-    y={studioY}
-    width={studioW}
-    height={studioH}
-    rx={studioCorner}
-    fill="#1a1a1a"
-    stroke={wireColor}
-    stroke-width={strokeWidth}
-  />
-
-  <!-- Memory fill -->
-  {#if ramPercent > 0}
-    <rect
-      x={studioX}
-      y={studioY + studioTopH + (studioMemTotalH - studioMemH)}
-      width={studioW}
-      height={studioMemH}
-      fill="rgba(255,215,0,0.75)"
-      clip-path="url(#{studioClipId})"
-    />
-  {/if}
-
-  <!-- Top surface divider -->
-  <line
-    x1={studioX}
-    y1={studioY + studioTopH}
-    x2={studioX + studioW}
-    y2={studioY + studioTopH}
-    stroke="rgba(179,179,179,0.3)"
-    stroke-width="0.5"
-  />
-
-  <!-- Front panel: vertical slots -->
-  <rect
-    x={studioVSlot1X - studioVSlotW / 2}
-    y={studioVSlotY}
-    width={studioVSlotW}
-    height={studioSlotH}
-    fill="rgba(0,0,0,0.35)"
-    rx="1.5"
-  />
-  <rect
-    x={studioVSlot2X - studioVSlotW / 2}
-    y={studioVSlotY}
-    width={studioVSlotW}
-    height={studioSlotH}
-    fill="rgba(0,0,0,0.35)"
-    rx="1.5"
-  />
-
-  <!-- Horizontal slot (SD card) -->
-  <rect
-    x={studioHSlotX}
-    y={studioVSlotY}
-    width={studioHSlotW}
-    height={studioSlotH * 0.6}
-    fill="rgba(0,0,0,0.35)"
-    rx="1"
-  />
-{:else}
-  <!-- MacBook Pro -->
-  <defs>
-    <clipPath id={screenClipId}>
-      <rect
-        x={mbScreenX + mbBezel}
-        y={mbY + mbBezel}
-        width={mbScreenW - mbBezel * 2}
-        height={mbScreenH - mbBezel * 2}
-        rx="2"
-      />
-    </clipPath>
-  </defs>
-
-  <!-- Screen outer frame -->
-  <rect
-    x={mbScreenX}
-    y={mbY}
-    width={mbScreenW}
-    height={mbScreenH}
-    rx="3"
-    fill="#1a1a1a"
-    stroke={wireColor}
-    stroke-width={strokeWidth}
-  />
-
-  <!-- Screen inner (dark) -->
-  <rect
-    x={mbScreenX + mbBezel}
-    y={mbY + mbBezel}
-    width={mbScreenW - mbBezel * 2}
-    height={mbScreenH - mbBezel * 2}
-    rx="2"
-    fill="#0a0a12"
-  />
-
-  <!-- Memory fill on screen -->
-  {#if ramPercent > 0}
-    <rect
-      x={mbScreenX + mbBezel}
-      y={mbY + mbBezel + (mbMemTotalH - mbMemH)}
-      width={mbScreenW - mbBezel * 2}
-      height={mbMemH}
-      fill="rgba(255,215,0,0.85)"
-      clip-path="url(#{screenClipId})"
-    />
-  {/if}
-
-  <!-- Apple logo -->
-  <path
-    d={APPLE_LOGO_PATH}
-    transform="translate({mbLogoX}, {mbLogoY}) scale({mbLogoScale})"
-    fill="#FFFFFF"
-    opacity="0.9"
-  />
-
-  <!-- Keyboard base (trapezoidal) -->
-  <path
-    d="M {mbBaseTopX} {mbBaseY} L {mbBaseTopX +
-      mbBaseTopW} {mbBaseY} L {mbBaseBottomX + mbBaseBottomW} {mbBaseY +
-      mbBaseH} L {mbBaseBottomX} {mbBaseY + mbBaseH} Z"
-    fill="#2c2c2c"
-    stroke={wireColor}
-    stroke-width="1"
-  />
-
-  <!-- Keyboard area -->
-  <rect
-    x={mbKbX}
-    y={mbKbY}
-    width={mbKbW}
-    height={mbKbH}
-    fill="rgba(0,0,0,0.2)"
-    rx="2"
-  />
-
-  <!-- Trackpad -->
-  <rect
-    x={mbTpX}
-    y={mbTpY}
-    width={mbTpW}
-    height={mbTpH}
-    fill="rgba(255,255,255,0.08)"
-    rx="2"
-  />
-{/if}

dashboard/src/lib/components/HeaderNav.svelte

@@ -6,10 +6,6 @@
   export let showSidebarToggle = false;
   export let sidebarVisible = true;
   export let onToggleSidebar: (() => void) | null = null;
-  export let downloadProgress: {
-    count: number;
-    percentage: number;
-  } | null = null;
 
   function handleHome(): void {
     if (onHome) {
@@ -37,17 +33,13 @@
     <div class="absolute left-6 top-1/2 -translate-y-1/2">
       <button
         onclick={handleToggleSidebar}
-        class="p-2 rounded border border-exo-light-gray/30 hover:border-exo-yellow/50 hover:bg-exo-medium-gray/30 transition-colors cursor-pointer"
+        class="p-2 rounded border border-exo-medium-gray/40 hover:border-exo-yellow/50 transition-colors cursor-pointer"
         title={sidebarVisible ? "Hide sidebar" : "Show sidebar"}
-        aria-label={sidebarVisible
-          ? "Hide conversation sidebar"
-          : "Show conversation sidebar"}
-        aria-pressed={sidebarVisible}
       >
         <svg
           class="w-5 h-5 {sidebarVisible
             ? 'text-exo-yellow'
-            : 'text-exo-light-gray'}"
+            : 'text-exo-medium-gray'}"
           fill="none"
           viewBox="0 0 24 24"
           stroke="currentColor"
@@ -83,19 +75,18 @@
     <img
       src="/exo-logo.png"
       alt="EXO"
-      class="h-18 drop-shadow-[0_0_4px_rgba(255,215,0,0.3)]"
+      class="h-18 drop-shadow-[0_0_20px_rgba(255,215,0,0.5)]"
     />
   </button>
 
   <!-- Right: Home + Downloads -->
-  <nav
+  <div
     class="absolute right-6 top-1/2 -translate-y-1/2 flex items-center gap-4"
-    aria-label="Main navigation"
   >
     {#if showHome}
       <button
         onclick={handleHome}
-        class="text-sm text-white/70 hover:text-exo-yellow transition-colors tracking-wider uppercase flex items-center gap-2 cursor-pointer"
+        class="text-sm text-exo-light-gray hover:text-exo-yellow transition-colors tracking-wider uppercase flex items-center gap-2 cursor-pointer"
         title="Back to topology view"
       >
         <svg
@@ -116,59 +107,23 @@
     {/if}
     <a
       href="/#/downloads"
-      class="text-sm text-white/70 hover:text-exo-yellow transition-colors tracking-wider uppercase flex items-center gap-2 cursor-pointer"
+      class="text-sm text-exo-light-gray hover:text-exo-yellow transition-colors tracking-wider uppercase flex items-center gap-2 cursor-pointer"
       title="View downloads overview"
     >
-      {#if downloadProgress}
-        <!-- Compact download progress indicator -->
-        <div class="relative w-4 h-4 flex-shrink-0">
-          <svg class="w-4 h-4 -rotate-90" viewBox="0 0 20 20">
-            <circle
-              cx="10"
-              cy="10"
-              r="8"
-              fill="none"
-              stroke="currentColor"
-              stroke-width="2"
-              opacity="0.2"
-            />
-            <circle
-              cx="10"
-              cy="10"
-              r="8"
-              fill="none"
-              stroke="currentColor"
-              stroke-width="2"
-              stroke-dasharray={2 * Math.PI * 8}
-              stroke-dashoffset={2 *
-                Math.PI *
-                8 *
-                (1 - downloadProgress.percentage / 100)}
-              class="text-blue-400 transition-all duration-300"
-            />
-          </svg>
-          <div
-            class="absolute inset-0 flex items-center justify-center text-[6px] font-mono text-blue-400"
-          >
-            {downloadProgress.count}
-          </div>
-        </div>
-      {:else}
-        <svg
-          class="w-4 h-4"
-          viewBox="0 0 24 24"
-          fill="none"
-          stroke="currentColor"
-          stroke-width="2"
-          stroke-linecap="round"
-          stroke-linejoin="round"
-        >
-          <path d="M12 3v12" />
-          <path d="M7 12l5 5 5-5" />
-          <path d="M5 21h14" />
-        </svg>
-      {/if}
+      <svg
+        class="w-4 h-4"
+        viewBox="0 0 24 24"
+        fill="none"
+        stroke="currentColor"
+        stroke-width="2"
+        stroke-linecap="round"
+        stroke-linejoin="round"
+      >
+        <path d="M12 3v12" />
+        <path d="M7 12l5 5 5-5" />
+        <path d="M5 21h14" />
+      </svg>
       Downloads
     </a>
-  </nav>
+  </div>
 </header>

dashboard/src/lib/components/HuggingFaceResultItem.svelte

@@ -26,8 +26,7 @@
     downloadedOnNodes = [],
   }: HuggingFaceResultItemProps = $props();
 
-  function formatNumber(num: number | undefined): string {
-    if (num == null) return "0";
+  function formatNumber(num: number): string {
     if (num >= 1000000) {
       return `${(num / 1000000).toFixed(1)}M`;
     } else if (num >= 1000) {

dashboard/src/lib/components/ImageParamsPanel.svelte

@@ -59,14 +59,13 @@
   }
 
   const sizeOptions: ImageGenerationParams["size"][] = [
-    "auto",
     "512x512",
     "768x768",
     "1024x1024",
     "1024x768",
     "768x1024",
-    "1024x1536",
-    "1536x1024",
+    "1024x1365",
+    "1365x1024",
   ];
 
   const qualityOptions: ImageGenerationParams["quality"][] = [
@@ -177,90 +176,92 @@
 <div class="border-b border-exo-medium-gray/30 px-3 py-2">
   <!-- Basic params row -->
   <div class="flex items-center gap-3 flex-wrap">
-    <!-- Size -->
-    <div class="flex items-center gap-1.5">
-      <span class="text-xs text-exo-light-gray uppercase tracking-wider"
-        >SIZE:</span
-      >
-      <div class="relative">
-        <button
-          bind:this={sizeButtonRef}
-          type="button"
-          onclick={() => (isSizeDropdownOpen = !isSizeDropdownOpen)}
-          class="bg-exo-medium-gray/50 border border-exo-yellow/30 rounded pl-2 pr-6 py-1 text-xs font-mono text-exo-yellow cursor-pointer transition-all duration-200 hover:border-exo-yellow/50 focus:outline-none focus:border-exo-yellow/70 {isSizeDropdownOpen
-            ? 'border-exo-yellow/70'
-            : ''}"
+    <!-- Size (hidden in edit mode - output size comes from input image) -->
+    {#if !isEditMode}
+      <div class="flex items-center gap-1.5">
+        <span class="text-xs text-exo-light-gray uppercase tracking-wider"
+          >SIZE:</span
         >
-          {params.size.toUpperCase()}
-        </button>
-        <div
-          class="absolute right-1.5 top-1/2 -translate-y-1/2 pointer-events-none transition-transform duration-200 {isSizeDropdownOpen
-            ? 'rotate-180'
-            : ''}"
-        >
-          <svg
-            class="w-3 h-3 text-exo-yellow/60"
-            fill="none"
-            viewBox="0 0 24 24"
-            stroke="currentColor"
+        <div class="relative">
+          <button
+            bind:this={sizeButtonRef}
+            type="button"
+            onclick={() => (isSizeDropdownOpen = !isSizeDropdownOpen)}
+            class="bg-exo-medium-gray/50 border border-exo-yellow/30 rounded pl-2 pr-6 py-1 text-xs font-mono text-exo-yellow cursor-pointer transition-all duration-200 hover:border-exo-yellow/50 focus:outline-none focus:border-exo-yellow/70 {isSizeDropdownOpen
+              ? 'border-exo-yellow/70'
+              : ''}"
           >
-            <path
-              stroke-linecap="round"
-              stroke-linejoin="round"
-              stroke-width="2"
-              d="M19 9l-7 7-7-7"
-            />
-          </svg>
-        </div>
-      </div>
-
-      {#if isSizeDropdownOpen}
-        <!-- Backdrop to close dropdown -->
-        <button
-          type="button"
-          class="fixed inset-0 z-[9998] cursor-default"
-          onclick={() => (isSizeDropdownOpen = false)}
-          aria-label="Close dropdown"
-        ></button>
-
-        <!-- Dropdown Panel - fixed positioning to escape overflow:hidden -->
-        <div
-          class="fixed bg-exo-dark-gray border border-exo-yellow/30 rounded shadow-lg shadow-black/50 z-[9999] max-h-48 overflow-y-auto overflow-x-hidden min-w-max"
-          style="bottom: calc(100vh - {sizeDropdownPosition()
-            .top}px + 4px); left: {sizeDropdownPosition().left}px;"
-        >
-          <div class="py-1">
-            {#each sizeOptions as size}
-              <button
-                type="button"
-                onclick={() => selectSize(size)}
-                class="w-full px-3 py-1.5 text-left text-xs font-mono tracking-wide transition-colors duration-100 flex items-center gap-2 {params.size ===
-                size
-                  ? 'bg-transparent text-exo-yellow'
-                  : 'text-exo-light-gray hover:text-exo-yellow'}"
-              >
-                {#if params.size === size}
-                  <svg
-                    class="w-3 h-3 flex-shrink-0"
-                    fill="currentColor"
-                    viewBox="0 0 20 20"
-                  >
-                    <path
-                      fill-rule="evenodd"
-                      d="M16.707 5.293a1 1 0 010 1.414l-8 8a1 1 0 01-1.414 0l-4-4a1 1 0 011.414-1.414L8 12.586l7.293-7.293a1 1 0 011.414 0z"
-                      clip-rule="evenodd"
-                    />
-                  </svg>
-                {:else}
-                  <span class="w-3"></span>
-                {/if}
-                <span>{size.toUpperCase()}</span>
-              </button>
-            {/each}
+            {params.size}
+          </button>
+          <div
+            class="absolute right-1.5 top-1/2 -translate-y-1/2 pointer-events-none transition-transform duration-200 {isSizeDropdownOpen
+              ? 'rotate-180'
+              : ''}"
+          >
+            <svg
+              class="w-3 h-3 text-exo-yellow/60"
+              fill="none"
+              viewBox="0 0 24 24"
+              stroke="currentColor"
+            >
+              <path
+                stroke-linecap="round"
+                stroke-linejoin="round"
+                stroke-width="2"
+                d="M19 9l-7 7-7-7"
+              />
+            </svg>
           </div>
         </div>
-      {/if}
-    </div>
+
+        {#if isSizeDropdownOpen}
+          <!-- Backdrop to close dropdown -->
+          <button
+            type="button"
+            class="fixed inset-0 z-[9998] cursor-default"
+            onclick={() => (isSizeDropdownOpen = false)}
+            aria-label="Close dropdown"
+          ></button>
+
+          <!-- Dropdown Panel - fixed positioning to escape overflow:hidden -->
+          <div
+            class="fixed bg-exo-dark-gray border border-exo-yellow/30 rounded shadow-lg shadow-black/50 z-[9999] max-h-48 overflow-y-auto min-w-max"
+            style="bottom: calc(100vh - {sizeDropdownPosition()
+              .top}px + 4px); left: {sizeDropdownPosition().left}px;"
+          >
+            <div class="py-1">
+              {#each sizeOptions as size}
+                <button
+                  type="button"
+                  onclick={() => selectSize(size)}
+                  class="w-full px-3 py-1.5 text-left text-xs font-mono tracking-wide transition-colors duration-100 flex items-center gap-2 {params.size ===
+                  size
+                    ? 'bg-transparent text-exo-yellow'
+                    : 'text-exo-light-gray hover:text-exo-yellow'}"
+                >
+                  {#if params.size === size}
+                    <svg
+                      class="w-3 h-3 flex-shrink-0"
+                      fill="currentColor"
+                      viewBox="0 0 20 20"
+                    >
+                      <path
+                        fill-rule="evenodd"
+                        d="M16.707 5.293a1 1 0 010 1.414l-8 8a1 1 0 01-1.414 0l-4-4a1 1 0 011.414-1.414L8 12.586l7.293-7.293a1 1 0 011.414 0z"
+                        clip-rule="evenodd"
+                      />
+                    </svg>
+                  {:else}
+                    <span class="w-3"></span>
+                  {/if}
+                  <span>{size}</span>
+                </button>
+              {/each}
+            </div>
+          </div>
+        {/if}
+      </div>
+    {/if}
 
     <!-- Quality -->
     <div class="flex items-center gap-1.5">
@@ -310,7 +311,7 @@
 
         <!-- Dropdown Panel - fixed positioning to escape overflow:hidden -->
         <div
-          class="fixed bg-exo-dark-gray border border-exo-yellow/30 rounded shadow-lg shadow-black/50 z-[9999] max-h-48 overflow-y-auto overflow-x-hidden min-w-max"
+          class="fixed bg-exo-dark-gray border border-exo-yellow/30 rounded shadow-lg shadow-black/50 z-[9999] max-h-48 overflow-y-auto min-w-max"
           style="bottom: calc(100vh - {qualityDropdownPosition()
             .top}px + 4px); left: {qualityDropdownPosition().left}px;"
         >

dashboard/src/lib/components/ModelCard.svelte

@@ -21,7 +21,7 @@
     } | null;
     nodes?: Record<string, NodeInfo>;
     sharding?: "Pipeline" | "Tensor";
-    runtime?: "MlxRing" | "MlxJaccl";
+    runtime?: "MlxRing" | "MlxIbv" | "MlxJaccl";
     onLaunch?: () => void;
     tags?: string[];
     apiPreview?: PlacementPreview | null;
@@ -348,7 +348,7 @@
   // Debug mode state
   const isDebugMode = $derived(debugMode());
   const topology = $derived(topologyData());
-  const isRdma = $derived(runtime === "MlxJaccl");
+  const isRdma = $derived(runtime === "MlxIbv" || runtime === "MlxJaccl");
 
   // Get interface name for an IP from node data
   function getInterfaceForIp(nodeId: string, ip?: string): string | null {
@@ -567,46 +567,20 @@
     <div class="flex items-center gap-1.5 mb-2">
       <span
         class="px-1.5 py-0.5 text-xs font-mono tracking-wider uppercase bg-exo-medium-gray/30 text-exo-light-gray border border-exo-medium-gray/40"
-        title={sharding === "Pipeline"
-          ? "Pipeline: splits model into sequential stages across devices. Lower network overhead."
-          : "Tensor: splits each layer across devices. Best with high-bandwidth connections (Thunderbolt)."}
       >
         {sharding}
       </span>
       <span
         class="px-1.5 py-0.5 text-xs font-mono tracking-wider uppercase bg-exo-medium-gray/30 text-exo-light-gray border border-exo-medium-gray/40"
-        title={runtime === "MlxRing"
-          ? "Ring: standard networking. Works over any connection (Wi-Fi, Ethernet, Thunderbolt)."
-          : "RDMA: direct memory access over Thunderbolt. Significantly faster for multi-device inference."}
       >
         {runtime === "MlxRing"
           ? "MLX Ring"
-          : runtime === "MlxJaccl"
+          : runtime === "MlxIbv" || runtime === "MlxJaccl"
             ? "MLX RDMA"
             : runtime}
       </span>
     </div>
 
-    <!-- Download Status -->
-    {#if isDownloading && progress}
-      <div class="mb-2 space-y-1">
-        <div class="flex items-center justify-between text-xs font-mono">
-          <span class="text-blue-400 tracking-wider uppercase">Downloading</span
-          >
-          <span class="text-white/60"
-            >{percentage.toFixed(1)}% &middot; {formatSpeed(progress.speed)}
-            &middot; {formatEta(progress.etaMs)}</span
-          >
-        </div>
-        <div class="h-1 bg-exo-medium-gray/30 rounded overflow-hidden">
-          <div
-            class="h-full bg-blue-500/70 transition-all duration-300"
-            style="width: {percentage}%"
-          ></div>
-        </div>
-      </div>
-    {/if}
-
     <!-- Mini Topology Preview -->
     {#if placementPreview().nodes.length > 0}
       {@const preview = placementPreview()}

dashboard/src/lib/components/ModelFilterPopover.svelte

@@ -6,7 +6,6 @@
     capabilities: string[];
     sizeRange: { min: number; max: number } | null;
     downloadedOnly: boolean;
-    readyOnly: boolean;
   }
 
   type ModelFilterPopoverProps = {
@@ -191,58 +190,34 @@
       </div>
     </div>
 
-    <!-- Availability filters -->
+    <!-- Downloaded only -->
     <div>
       <h4 class="text-xs font-mono text-white/50 mb-2">Availability</h4>
-      <div class="flex flex-wrap gap-1.5">
-        <button
-          type="button"
-          class="px-2 py-1 text-xs font-mono rounded transition-colors {filters.downloadedOnly
-            ? 'bg-green-500/20 text-green-400 border border-green-500/30'
-            : 'bg-white/5 text-white/60 hover:bg-white/10 border border-transparent'}"
-          onclick={() =>
-            onChange({ ...filters, downloadedOnly: !filters.downloadedOnly })}
+      <button
+        type="button"
+        class="px-2 py-1 text-xs font-mono rounded transition-colors {filters.downloadedOnly
+          ? 'bg-green-500/20 text-green-400 border border-green-500/30'
+          : 'bg-white/5 text-white/60 hover:bg-white/10 border border-transparent'}"
+        onclick={() =>
+          onChange({ ...filters, downloadedOnly: !filters.downloadedOnly })}
+      >
+        <svg
+          class="w-3.5 h-3.5 inline-block"
+          viewBox="0 0 24 24"
+          fill="none"
+          stroke="currentColor"
+          stroke-width="2"
+          stroke-linecap="round"
+          stroke-linejoin="round"
         >
-          <svg
-            class="w-3.5 h-3.5 inline-block"
-            viewBox="0 0 24 24"
-            fill="none"
-            stroke="currentColor"
-            stroke-width="2"
-            stroke-linecap="round"
-            stroke-linejoin="round"
-          >
-            <path
-              class="text-white/40"
-              d="M20 20a2 2 0 0 0 2-2V8a2 2 0 0 0-2-2h-7.9a2 2 0 0 1-1.69-.9L9.6 3.9A2 2 0 0 0 7.93 3H4a2 2 0 0 0-2 2v13a2 2 0 0 0 2 2Z"
-            />
-            <path class="text-green-400" d="m9 13 2 2 4-4" />
-          </svg>
-          <span class="ml-1">Downloaded</span>
-        </button>
-        <button
-          type="button"
-          class="px-2 py-1 text-xs font-mono rounded transition-colors {filters.readyOnly
-            ? 'bg-green-500/20 text-green-400 border border-green-500/30'
-            : 'bg-white/5 text-white/60 hover:bg-white/10 border border-transparent'}"
-          onclick={() =>
-            onChange({ ...filters, readyOnly: !filters.readyOnly })}
-        >
-          <svg
-            class="w-3.5 h-3.5 inline-block"
-            viewBox="0 0 24 24"
-            fill="none"
-            stroke="currentColor"
-            stroke-width="2"
-            stroke-linecap="round"
-            stroke-linejoin="round"
-          >
-            <circle cx="12" cy="12" r="10" />
-            <path d="m9 12 2 2 4-4" />
-          </svg>
-          <span class="ml-1">Ready</span>
-        </button>
-      </div>
+          <path
+            class="text-white/40"
+            d="M20 20a2 2 0 0 0 2-2V8a2 2 0 0 0-2-2h-7.9a2 2 0 0 1-1.69-.9L9.6 3.9A2 2 0 0 0 7.93 3H4a2 2 0 0 0-2 2v13a2 2 0 0 0 2 2Z"
+          />
+          <path class="text-green-400" d="m9 13 2 2 4-4" />
+        </svg>
+        <span class="ml-1">Downloaded</span>
+      </button>
     </div>
 
     <!-- Size range -->

dashboard/src/lib/components/ModelPickerGroup.svelte

@@ -41,7 +41,6 @@
     onShowInfo: (group: ModelGroup) => void;
     downloadStatusMap?: Map<string, DownloadAvailability>;
     launchedAt?: number;
-    instanceStatuses?: Record<string, { status: string; statusClass: string }>;
   };
 
   let {
@@ -57,7 +56,6 @@
     onShowInfo,
     downloadStatusMap,
     launchedAt,
-    instanceStatuses = {},
   }: ModelPickerGroupProps = $props();
 
   // Group-level download status: show if any variant is downloaded
@@ -94,12 +92,6 @@
   const anyVariantFits = $derived(
     group.variants.some((v) => canModelFit(v.id)),
   );
-  // Check if any variant has an active instance (ready, loading, downloading)
-  const anyVariantHasInstance = $derived(
-    instanceStatuses
-      ? group.variants.some((v) => instanceStatuses[v.id] != null)
-      : false,
-  );
   const groupFitStatus = $derived.by((): ModelFitStatus => {
     let hasClusterCapacityOnly = false;
     for (const variant of group.variants) {
@@ -130,35 +122,16 @@
     !group.hasMultipleVariants &&
       group.variants.some((v) => v.id === selectedModelId),
   );
-
-  // Group-level instance status: show the "best" status across all variants
-  const groupInstanceStatus = $derived.by(() => {
-    if (!instanceStatuses) return null;
-    const readyStatuses = ["READY", "LOADED", "RUNNING"];
-    const loadingStatuses = ["LOADING", "WARMING UP"];
-    let bestStatus: { status: string; statusClass: string } | null = null;
-    for (const variant of group.variants) {
-      const s = instanceStatuses[variant.id];
-      if (!s) continue;
-      if (readyStatuses.includes(s.status)) return s; // Ready is best
-      if (loadingStatuses.includes(s.status) || s.status === "DOWNLOADING") {
-        bestStatus = s;
-      }
-    }
-    return bestStatus;
-  });
 </script>
 
 <div
-  class="border-b border-white/5 last:border-b-0 {!anyVariantFits &&
-  !anyVariantHasInstance
+  class="border-b border-white/5 last:border-b-0 {!anyVariantFits
     ? 'opacity-50'
     : ''}"
 >
   <!-- Main row -->
   <div
-    class="flex items-center gap-2 px-3 py-2.5 transition-colors {anyVariantFits ||
-    anyVariantHasInstance
+    class="flex items-center gap-2 px-3 py-2.5 transition-colors {anyVariantFits
       ? 'hover:bg-white/5 cursor-pointer'
       : 'cursor-not-allowed'} {isMainSelected
       ? 'bg-exo-yellow/10 border-l-2 border-exo-yellow'
@@ -168,7 +141,7 @@
         onToggleExpand();
       } else {
         const modelId = group.variants[0]?.id;
-        if (modelId && (canModelFit(modelId) || instanceStatuses[modelId])) {
+        if (modelId && canModelFit(modelId)) {
           onSelectModel(modelId);
         }
       }
@@ -182,7 +155,7 @@
           onToggleExpand();
         } else {
           const modelId = group.variants[0]?.id;
-          if (modelId && (canModelFit(modelId) || instanceStatuses[modelId])) {
+          if (modelId && canModelFit(modelId)) {
             onSelectModel(modelId);
           }
         }
@@ -373,47 +346,6 @@
       </span>
     {/if}
 
-    <!-- Instance status badge -->
-    {#if groupInstanceStatus}
-      {#if groupInstanceStatus.status === "READY" || groupInstanceStatus.status === "LOADED" || groupInstanceStatus.status === "RUNNING"}
-        <span class="flex-shrink-0" title="Running">
-          <svg
-            class="w-3 h-3 text-green-400"
-            viewBox="0 0 12 12"
-            fill="currentColor"
-          >
-            <circle cx="6" cy="6" r="5" />
-          </svg>
-        </span>
-      {:else if groupInstanceStatus.status === "DOWNLOADING"}
-        <span class="flex-shrink-0 animate-pulse" title="Downloading">
-          <svg
-            class="w-3.5 h-3.5 text-blue-400"
-            viewBox="0 0 24 24"
-            fill="none"
-            stroke="currentColor"
-            stroke-width="2"
-            stroke-linecap="round"
-            stroke-linejoin="round"
-          >
-            <path d="M21 15v4a2 2 0 01-2 2H5a2 2 0 01-2-2v-4" />
-            <polyline points="7 10 12 15 17 10" />
-            <line x1="12" y1="15" x2="12" y2="3" />
-          </svg>
-        </span>
-      {:else if groupInstanceStatus.status === "LOADING" || groupInstanceStatus.status === "WARMING UP"}
-        <span class="flex-shrink-0 animate-pulse" title="Loading">
-          <svg
-            class="w-3 h-3 text-yellow-400"
-            viewBox="0 0 12 12"
-            fill="currentColor"
-          >
-            <circle cx="6" cy="6" r="5" />
-          </svg>
-        </span>
-      {/if}
-    {/if}
-
     <!-- Check mark if selected (single-variant) -->
     {#if isMainSelected}
       <svg
@@ -488,30 +420,20 @@
       {#each group.variants as variant}
         {@const fitStatus = getModelFitStatus(variant.id)}
         {@const modelCanFit = canModelFit(variant.id)}
-        {@const variantHasInstance = instanceStatuses[variant.id] != null}
         {@const isSelected = selectedModelId === variant.id}
-        <div
-          class="w-full flex items-center gap-3 px-3 py-2 pl-10 hover:bg-white/5 transition-colors text-left {!modelCanFit &&
-          !variantHasInstance
+        <button
+          type="button"
+          class="w-full flex items-center gap-3 px-3 py-2 pl-10 hover:bg-white/5 transition-colors text-left {!modelCanFit
             ? 'opacity-50 cursor-not-allowed'
             : 'cursor-pointer'} {isSelected
             ? 'bg-exo-yellow/10 border-l-2 border-exo-yellow'
             : 'border-l-2 border-transparent'}"
-          role="button"
-          tabindex="0"
+          disabled={!modelCanFit}
           onclick={() => {
-            if (modelCanFit || variantHasInstance) {
+            if (modelCanFit) {
               onSelectModel(variant.id);
             }
           }}
-          onkeydown={(e) => {
-            if (e.key === "Enter" || e.key === " ") {
-              e.preventDefault();
-              if (modelCanFit) {
-                onSelectModel(variant.id);
-              }
-            }
-          }}
         >
           <!-- Quantization badge -->
           <span
@@ -556,48 +478,6 @@
             {/if}
           {/if}
 
-          <!-- Instance status badge -->
-          {#if instanceStatuses[variant.id]}
-            {@const instStatus = instanceStatuses[variant.id]}
-            {#if instStatus.status === "READY" || instStatus.status === "LOADED" || instStatus.status === "RUNNING"}
-              <span class="flex-shrink-0" title="Running">
-                <svg
-                  class="w-3 h-3 text-green-400"
-                  viewBox="0 0 12 12"
-                  fill="currentColor"
-                >
-                  <circle cx="6" cy="6" r="5" />
-                </svg>
-              </span>
-            {:else if instStatus.status === "DOWNLOADING"}
-              <span class="flex-shrink-0 animate-pulse" title="Downloading">
-                <svg
-                  class="w-3.5 h-3.5 text-blue-400"
-                  viewBox="0 0 24 24"
-                  fill="none"
-                  stroke="currentColor"
-                  stroke-width="2"
-                  stroke-linecap="round"
-                  stroke-linejoin="round"
-                >
-                  <path d="M21 15v4a2 2 0 01-2 2H5a2 2 0 01-2-2v-4" />
-                  <polyline points="7 10 12 15 17 10" />
-                  <line x1="12" y1="15" x2="12" y2="3" />
-                </svg>
-              </span>
-            {:else if instStatus.status === "LOADING" || instStatus.status === "WARMING UP"}
-              <span class="flex-shrink-0 animate-pulse" title="Loading">
-                <svg
-                  class="w-3 h-3 text-yellow-400"
-                  viewBox="0 0 12 12"
-                  fill="currentColor"
-                >
-                  <circle cx="6" cy="6" r="5" />
-                </svg>
-              </span>
-            {/if}
-          {/if}
-
           <!-- Check mark if selected -->
           {#if isSelected}
             <svg
@@ -610,36 +490,7 @@
               />
             </svg>
           {/if}
-
-          <!-- Info button -->
-          <button
-            type="button"
-            class="p-1 rounded hover:bg-white/10 transition-colors flex-shrink-0"
-            onclick={(e) => {
-              e.stopPropagation();
-              onShowInfo({
-                id: variant.id,
-                name: variant.name || variant.id,
-                capabilities: group.capabilities,
-                family: group.family,
-                variants: [variant],
-                smallestVariant: variant,
-                hasMultipleVariants: false,
-              });
-            }}
-            title="View variant details"
-          >
-            <svg
-              class="w-4 h-4 text-white/30 hover:text-white/50"
-              viewBox="0 0 24 24"
-              fill="currentColor"
-            >
-              <path
-                d="M12 2C6.48 2 2 6.48 2 12s4.48 10 10 10 10-4.48 10-10S17.52 2 12 2zm1 15h-2v-6h2v6zm0-8h-2V7h2v2z"
-              />
-            </svg>
-          </button>
-        </div>
+        </button>
       {/each}
     </div>
   {/if}

dashboard/src/lib/components/ModelPickerModal.svelte

@@ -36,7 +36,6 @@
     capabilities: string[];
     sizeRange: { min: number; max: number } | null;
     downloadedOnly: boolean;
-    readyOnly: boolean;
   }
 
   interface HuggingFaceModel {
@@ -50,11 +49,6 @@
 
   type ModelFitStatus = "fits_now" | "fits_cluster_capacity" | "too_large";
 
-  export type InstanceStatus = {
-    status: string;
-    statusClass: string;
-  };
-
   type ModelPickerModalProps = {
     isOpen: boolean;
     models: ModelInfo[];
@@ -81,7 +75,6 @@
         macmon_info?: { memory?: { ram_total?: number } };
       }
     >;
-    instanceStatuses?: Record<string, InstanceStatus>;
   };
 
   let {
@@ -103,7 +96,6 @@
     usedMemoryGB,
     downloadsData,
     topologyNodes,
-    instanceStatuses = {},
   }: ModelPickerModalProps = $props();
 
   // Local state
@@ -115,7 +107,6 @@
     capabilities: [],
     sizeRange: null,
     downloadedOnly: false,
-    readyOnly: false,
   });
   let infoGroup = $state<ModelGroup | null>(null);
 
@@ -449,16 +440,6 @@
       );
     }
 
-    // Filter to ready/running models only
-    if (filters.readyOnly) {
-      result = result.filter((g) =>
-        g.variants.some((v) => {
-          const s = instanceStatuses[v.id];
-          return s && s.statusClass === "ready";
-        }),
-      );
-    }
-
     // Sort: fits-now first, then fits-cluster-capacity, then too-large
     result.sort((a, b) => {
       const getGroupFitRank = (group: ModelGroup): number => {
@@ -531,18 +512,6 @@
     );
   });
 
-  // Split filtered groups into recommended (fits_now) and others for visual separation
-  const recommendedGroups = $derived(
-    filteredGroups.filter((g) =>
-      g.variants.some((v) => getModelFitStatus(v.id) === "fits_now"),
-    ),
-  );
-  const otherGroups = $derived(
-    filteredGroups.filter(
-      (g) => !g.variants.some((v) => getModelFitStatus(v.id) === "fits_now"),
-    ),
-  );
-
   function toggleGroupExpanded(groupId: string) {
     const next = new Set(expandedGroups);
     if (next.has(groupId)) {
@@ -569,19 +538,13 @@
   }
 
   function clearFilters() {
-    filters = {
-      capabilities: [],
-      sizeRange: null,
-      downloadedOnly: false,
-      readyOnly: false,
-    };
+    filters = { capabilities: [], sizeRange: null, downloadedOnly: false };
   }
 
   const hasActiveFilters = $derived(
     filters.capabilities.length > 0 ||
       filters.sizeRange !== null ||
-      filters.downloadedOnly ||
-      filters.readyOnly,
+      filters.downloadedOnly,
   );
 </script>
 
@@ -850,7 +813,6 @@
                 onShowInfo={(g) => (infoGroup = g)}
                 downloadStatusMap={getVariantDownloadMap(group)}
                 launchedAt={recentTimestamps.get(group.variants[0]?.id ?? "")}
-                {instanceStatuses}
               />
             {/each}
           {/if}
@@ -878,34 +840,7 @@
             {/if}
           </div>
         {:else}
-          <!-- Recommended for your cluster -->
-          {#if recommendedGroups.length > 0 && otherGroups.length > 0 && !searchQuery.trim()}
-            <div
-              class="sticky top-0 z-10 flex items-center gap-2 px-3 py-2 bg-green-950/60 border-b border-green-500/20 backdrop-blur-sm"
-            >
-              <svg
-                class="w-3.5 h-3.5 text-green-400 flex-shrink-0"
-                fill="none"
-                viewBox="0 0 24 24"
-                stroke="currentColor"
-                stroke-width="2"
-              >
-                <path
-                  stroke-linecap="round"
-                  stroke-linejoin="round"
-                  d="M9 12.75L11.25 15 15 9.75M21 12a9 9 0 11-18 0 9 9 0 0118 0z"
-                />
-              </svg>
-              <span
-                class="text-xs font-mono text-green-400 tracking-wider uppercase"
-                >Recommended for your cluster</span
-              >
-              <span class="text-xs font-mono text-green-400/50"
-                >— fits in available memory</span
-              >
-            </div>
-          {/if}
-          {#each recommendedGroups as group}
+          {#each filteredGroups as group}
             <ModelPickerGroup
               {group}
               isExpanded={expandedGroups.has(group.id)}
@@ -918,34 +853,6 @@
               {onToggleFavorite}
               onShowInfo={(g) => (infoGroup = g)}
               downloadStatusMap={getVariantDownloadMap(group)}
-              {instanceStatuses}
-            />
-          {/each}
-          <!-- Other models -->
-          {#if otherGroups.length > 0 && recommendedGroups.length > 0 && !searchQuery.trim()}
-            <div
-              class="sticky top-0 z-10 flex items-center gap-2 px-3 py-2 bg-exo-dark-gray/80 border-y border-exo-medium-gray/20 backdrop-blur-sm"
-            >
-              <span
-                class="text-xs font-mono text-white/40 tracking-wider uppercase"
-                >Other models</span
-              >
-            </div>
-          {/if}
-          {#each otherGroups 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)}
-              {instanceStatuses}
             />
           {/each}
         {/if}
@@ -968,11 +875,6 @@
             >Downloaded</span
           >
         {/if}
-        {#if filters.readyOnly}
-          <span class="px-1.5 py-0.5 bg-green-500/20 text-green-400 rounded"
-            >Ready</span
-          >
-        {/if}
         {#if filters.sizeRange}
           <span class="px-1.5 py-0.5 bg-exo-yellow/20 text-exo-yellow rounded">
             {filters.sizeRange.min}GB - {filters.sizeRange.max}GB

dashboard/src/lib/components/PrefillProgressBar.svelte

@@ -1,70 +0,0 @@
-<script lang="ts">
-  import type { PrefillProgress } from "$lib/stores/app.svelte";
-
-  interface Props {
-    progress: PrefillProgress;
-    class?: string;
-  }
-
-  let { progress, class: className = "" }: Props = $props();
-
-  const percentage = $derived(
-    progress.total > 0
-      ? Math.round((progress.processed / progress.total) * 100)
-      : 0,
-  );
-
-  const etaText = $derived.by(() => {
-    if (progress.processed <= 0 || progress.total <= 0) return null;
-    const elapsedMs = performance.now() - progress.startedAt;
-    if (elapsedMs < 200) return null; // need a minimum sample window
-    const tokensPerMs = progress.processed / elapsedMs;
-    const remainingTokens = progress.total - progress.processed;
-    const remainingMs = remainingTokens / tokensPerMs;
-    const remainingSec = Math.ceil(remainingMs / 1000);
-    if (remainingSec <= 0) return null;
-    if (remainingSec < 60) return `~${remainingSec}s remaining`;
-    const mins = Math.floor(remainingSec / 60);
-    const secs = remainingSec % 60;
-    return `~${mins}m ${secs}s remaining`;
-  });
-
-  function formatTokenCount(count: number | undefined): string {
-    if (count == null) return "0";
-    if (count >= 1000) {
-      return `${(count / 1000).toFixed(1)}k`;
-    }
-    return count.toString();
-  }
-</script>
-
-<div class="prefill-progress {className}">
-  <div
-    class="flex items-center justify-between text-xs text-exo-light-gray mb-1"
-  >
-    <span>Processing prompt</span>
-    <span class="font-mono">
-      {formatTokenCount(progress.processed)} / {formatTokenCount(
-        progress.total,
-      )} tokens
-    </span>
-  </div>
-  <div class="h-1.5 bg-exo-black/60 rounded-full overflow-hidden">
-    <div
-      class="h-full bg-exo-yellow rounded-full transition-all duration-150 ease-out"
-      style="width: {percentage}%"
-    ></div>
-  </div>
-  <div
-    class="flex items-center justify-between text-xs text-exo-light-gray/70 mt-0.5 font-mono"
-  >
-    <span>{etaText ?? ""}</span>
-    <span>{percentage}%</span>
-  </div>
-</div>
-
-<style>
-  .prefill-progress {
-    width: 100%;
-  }
-</style>

dashboard/src/lib/components/ToastContainer.svelte

@@ -1,117 +0,0 @@
-<script lang="ts">
-  import { toasts, dismissToast, type Toast } from "$lib/stores/toast.svelte";
-  import { fly, fade } from "svelte/transition";
-  import { flip } from "svelte/animate";
-
-  const items = $derived(toasts());
-
-  const typeStyles: Record<
-    Toast["type"],
-    { border: string; icon: string; iconColor: string }
-  > = {
-    success: {
-      border: "border-l-green-500",
-      icon: "M9 12.75L11.25 15 15 9.75M21 12a9 9 0 11-18 0 9 9 0 0118 0z",
-      iconColor: "text-green-400",
-    },
-    error: {
-      border: "border-l-red-500",
-      icon: "M12 9v3.75m9-.75a9 9 0 11-18 0 9 9 0 0118 0zm-9 3.75h.008v.008H12v-.008z",
-      iconColor: "text-red-400",
-    },
-    warning: {
-      border: "border-l-yellow-500",
-      icon: "M12 9v3.75m-9.303 3.376c-.866 1.5.217 3.374 1.948 3.374h14.71c1.73 0 2.813-1.874 1.948-3.374L13.949 3.378c-.866-1.5-3.032-1.5-3.898 0L2.697 16.126z",
-      iconColor: "text-yellow-400",
-    },
-    info: {
-      border: "border-l-blue-500",
-      icon: "M11.25 11.25l.041-.02a.75.75 0 011.063.852l-.708 2.836a.75.75 0 001.063.853l.041-.021M21 12a9 9 0 11-18 0 9 9 0 0118 0zm-9-3.75h.008v.008H12V8.25z",
-      iconColor: "text-blue-400",
-    },
-  };
-</script>
-
-{#if items.length > 0}
-  <div
-    class="fixed bottom-6 right-6 z-[9999] flex flex-col gap-2 pointer-events-none"
-    role="log"
-    aria-live="polite"
-    aria-label="Notifications"
-  >
-    {#each items as toast (toast.id)}
-      {@const style = typeStyles[toast.type]}
-      <div
-        class="pointer-events-auto max-w-sm w-80 bg-exo-dark-gray/95 backdrop-blur-sm border border-exo-medium-gray/60 border-l-[3px] {style.border} rounded shadow-lg shadow-black/40"
-        in:fly={{ x: 80, duration: 250 }}
-        out:fade={{ duration: 150 }}
-        animate:flip={{ duration: 200 }}
-        role="alert"
-      >
-        <div class="flex items-start gap-3 px-4 py-3">
-          <!-- Icon -->
-          <svg
-            class="w-5 h-5 flex-shrink-0 mt-0.5 {style.iconColor}"
-            fill="none"
-            viewBox="0 0 24 24"
-            stroke-width="1.5"
-            stroke="currentColor"
-          >
-            <path
-              stroke-linecap="round"
-              stroke-linejoin="round"
-              d={style.icon}
-            />
-          </svg>
-
-          <!-- Message -->
-          <p class="flex-1 text-sm text-white/90 font-mono leading-snug">
-            {toast.message}
-          </p>
-
-          <!-- Dismiss button -->
-          <button
-            onclick={() => dismissToast(toast.id)}
-            class="flex-shrink-0 p-0.5 text-white/40 hover:text-white/80 transition-colors cursor-pointer"
-            aria-label="Dismiss notification"
-          >
-            <svg
-              class="w-4 h-4"
-              fill="none"
-              viewBox="0 0 24 24"
-              stroke-width="2"
-              stroke="currentColor"
-            >
-              <path
-                stroke-linecap="round"
-                stroke-linejoin="round"
-                d="M6 18L18 6M6 6l12 12"
-              />
-            </svg>
-          </button>
-        </div>
-
-        <!-- Auto-dismiss progress bar -->
-        {#if toast.duration > 0}
-          <div class="h-0.5 bg-white/5 rounded-b overflow-hidden">
-            <div
-              class="h-full {style.border.replace('border-l-', 'bg-')}/60"
-              style="animation: shrink {toast.duration}ms linear forwards"
-            ></div>
-          </div>
-        {/if}
-      </div>
-    {/each}
-  </div>
-{/if}
-
-<style>
-  @keyframes shrink {
-    from {
-      width: 100%;
-    }
-    to {
-      width: 0%;
-    }
-  }
-</style>

dashboard/src/lib/components/index.ts

@@ -12,4 +12,3 @@ export { default as HuggingFaceResultItem } from "./HuggingFaceResultItem.svelte
 export { default as ModelFilterPopover } from "./ModelFilterPopover.svelte";
 export { default as ModelPickerGroup } from "./ModelPickerGroup.svelte";
 export { default as ModelPickerModal } from "./ModelPickerModal.svelte";
-export { default as ChatModelSelector } from "./ChatModelSelector.svelte";

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

@@ -168,7 +168,7 @@ export interface ModelDownloadStatus {
 export interface PlacementPreview {
   model_id: string;
   sharding: "Pipeline" | "Tensor";
-  instance_meta: "MlxRing" | "MlxJaccl";
+  instance_meta: "MlxRing" | "MlxIbv" | "MlxJaccl";
   instance: unknown | null;
   memory_delta_by_node: Record<string, number> | null;
   error: string | null;
@@ -219,6 +219,7 @@ interface RawStateResponse {
     string,
     {
       MlxRingInstance?: Instance;
+      MlxIbvInstance?: Instance;
       MlxJacclInstance?: Instance;
     }
   >;
@@ -249,11 +250,6 @@ interface RawStateResponse {
   >;
   // Thunderbolt bridge cycles (nodes with bridge enabled forming loops)
   thunderboltBridgeCycles?: string[][];
-  // Disk usage per node
-  nodeDisk?: Record<
-    string,
-    { total: { inBytes: number }; available: { inBytes: number } }
-  >;
 }
 
 export interface MessageAttachment {
@@ -277,13 +273,6 @@ export interface TokenData {
   topLogprobs: TopLogprob[];
 }
 
-export interface PrefillProgress {
-  processed: number;
-  total: number;
-  /** Timestamp (performance.now()) when prefill started. */
-  startedAt: number;
-}
-
 export interface Message {
   id: string;
   role: "user" | "assistant" | "system";
@@ -317,14 +306,13 @@ const IMAGE_PARAMS_STORAGE_KEY = "exo-image-generation-params";
 export interface ImageGenerationParams {
   // Basic params
   size:
-    | "auto"
     | "512x512"
     | "768x768"
     | "1024x1024"
     | "1024x768"
     | "768x1024"
-    | "1024x1536"
-    | "1536x1024";
+    | "1024x1365"
+    | "1365x1024";
   quality: "low" | "medium" | "high";
   outputFormat: "png" | "jpeg";
   numImages: number;
@@ -348,7 +336,7 @@ export interface EditingImage {
 }
 
 const DEFAULT_IMAGE_PARAMS: ImageGenerationParams = {
-  size: "auto",
+  size: "1024x1024",
   quality: "medium",
   outputFormat: "png",
   numImages: 1,
@@ -531,10 +519,6 @@ class AppStore {
   ttftMs = $state<number | null>(null); // Time to first token in ms
   tps = $state<number | null>(null); // Tokens per second
   totalTokens = $state<number>(0); // Total tokens in current response
-  prefillProgress = $state<PrefillProgress | null>(null);
-
-  // Abort controller for stopping generation
-  private currentAbortController: AbortController | null = null;
 
   // Topology state
   topologyData = $state<TopologyData | null>(null);
@@ -589,12 +573,6 @@ class AppStore {
   // Image editing state
   editingImage = $state<EditingImage | null>(null);
 
-  /** True when the backend is reachable. */
-  isConnected = $state<boolean>(true);
-  /** Number of consecutive fetch failures. */
-  private consecutiveFailures = 0;
-  private static readonly CONNECTION_LOST_THRESHOLD = 3;
-
   private fetchInterval: ReturnType<typeof setInterval> | null = null;
   private previewsInterval: ReturnType<typeof setInterval> | null = null;
   private lastConversationPersistTs = 0;
@@ -847,10 +825,6 @@ class AppStore {
     this.thinkingEnabled = conversation.enableThinking ?? true;
     this.refreshConversationModelFromInstances();
 
-    // Sync global selection to the loaded conversation's model so reactive
-    // effects in +page.svelte can determine the correct chat launch state.
-    this.selectedChatModel = conversation.modelId || "";
-
     return true;
   }
 
@@ -921,7 +895,11 @@ class AppStore {
 
     let instanceType: string | null = null;
     if (instanceTag === "MlxRingInstance") instanceType = "MLX Ring";
-    else if (instanceTag === "MlxJacclInstance") instanceType = "MLX RDMA";
+    else if (
+      instanceTag === "MlxIbvInstance" ||
+      instanceTag === "MlxJacclInstance"
+    )
+      instanceType = "MLX RDMA";
 
     let sharding: string | null = null;
     const inst = instance as {
@@ -1300,19 +1278,7 @@ class AppStore {
       // Thunderbolt bridge status per node
       this.nodeThunderboltBridge = data.nodeThunderboltBridge ?? {};
       this.lastUpdate = Date.now();
-      // Connection recovered
-      if (!this.isConnected) {
-        this.isConnected = true;
-      }
-      this.consecutiveFailures = 0;
     } catch (error) {
-      this.consecutiveFailures++;
-      if (
-        this.consecutiveFailures >= AppStore.CONNECTION_LOST_THRESHOLD &&
-        this.isConnected
-      ) {
-        this.isConnected = false;
-      }
       console.error("Error fetching state:", error);
     }
   }
@@ -1676,12 +1642,11 @@ class AppStore {
       if (!reader) throw new Error("No response body");
 
       let fullContent = prefixText;
-      let streamedThinking = "";
       const collectedTokens: TokenData[] = [...tokensToKeep];
 
       interface ChatCompletionChunk {
         choices?: Array<{
-          delta?: { content?: string; reasoning_content?: string };
+          delta?: { content?: string };
           logprobs?: {
             content?: Array<{
               token: string;
@@ -1702,7 +1667,6 @@ class AppStore {
         (parsed) => {
           const choice = parsed.choices?.[0];
           const delta = choice?.delta?.content;
-          const thinkingDelta = choice?.delta?.reasoning_content;
 
           // Collect logprobs data
           const logprobsContent = choice?.logprobs?.content;
@@ -1721,11 +1685,7 @@ class AppStore {
             }
           }
 
-          if (thinkingDelta) {
-            streamedThinking += thinkingDelta;
-          }
-
-          if (delta || thinkingDelta) {
+          if (delta) {
             if (firstTokenTime === null) {
               firstTokenTime = performance.now();
               this.ttftMs = firstTokenTime - requestStartTime;
@@ -1739,14 +1699,9 @@ class AppStore {
               this.tps = ((tokenCount - tokensToKeep.length) / elapsed) * 1000;
             }
 
-            if (delta) {
-              fullContent += delta;
-            }
-            const { displayContent, thinkingContent: tagThinking } =
+            fullContent += delta;
+            const { displayContent, thinkingContent } =
               this.stripThinkingTags(fullContent);
-            const combinedThinking = [streamedThinking, tagThinking]
-              .filter(Boolean)
-              .join("\n\n");
 
             if (this.activeConversationId === targetConversationId) {
               this.currentResponse = displayContent;
@@ -1758,7 +1713,7 @@ class AppStore {
               messageId,
               (m) => {
                 m.content = displayContent;
-                m.thinking = combinedThinking || undefined;
+                m.thinking = thinkingContent || undefined;
                 m.tokens = [...collectedTokens];
               },
             );
@@ -1770,14 +1725,11 @@ class AppStore {
 
       // Final update
       if (this.conversationExists(targetConversationId)) {
-        const { displayContent, thinkingContent: tagThinking } =
+        const { displayContent, thinkingContent } =
           this.stripThinkingTags(fullContent);
-        const finalThinking = [streamedThinking, tagThinking]
-          .filter(Boolean)
-          .join("\n\n");
         this.updateConversationMessage(targetConversationId, messageId, (m) => {
           m.content = displayContent;
-          m.thinking = finalThinking || undefined;
+          m.thinking = thinkingContent || undefined;
           m.tokens = [...collectedTokens];
           if (this.ttftMs !== null) m.ttftMs = this.ttftMs;
           if (this.tps !== null) m.tps = this.tps;
@@ -1853,7 +1805,7 @@ class AppStore {
           assistantMessage.id,
           (msg) => {
             msg.content =
-              "No model is loaded yet. Select a model from the sidebar to get started — it will download and load automatically.";
+              "Error: No model available. Please launch an instance first.";
           },
         );
         this.syncActiveMessagesIfNeeded(targetConversationId);
@@ -1885,12 +1837,11 @@ class AppStore {
       }
 
       let streamedContent = "";
-      let streamedThinking = "";
       const collectedTokens: TokenData[] = [];
 
       interface ChatCompletionChunk {
         choices?: Array<{
-          delta?: { content?: string; reasoning_content?: string };
+          delta?: { content?: string };
           logprobs?: {
             content?: Array<{
               token: string;
@@ -1911,7 +1862,6 @@ class AppStore {
         (parsed) => {
           const choice = parsed.choices?.[0];
           const delta = choice?.delta?.content;
-          const thinkingDelta = choice?.delta?.reasoning_content;
 
           // Collect logprobs data
           const logprobsContent = choice?.logprobs?.content;
@@ -1930,19 +1880,10 @@ class AppStore {
             }
           }
 
-          if (thinkingDelta) {
-            streamedThinking += thinkingDelta;
-          }
-
-          if (delta || thinkingDelta) {
-            if (delta) {
-              streamedContent += delta;
-            }
-            const { displayContent, thinkingContent: tagThinking } =
+          if (delta) {
+            streamedContent += delta;
+            const { displayContent, thinkingContent } =
               this.stripThinkingTags(streamedContent);
-            const combinedThinking = [streamedThinking, tagThinking]
-              .filter(Boolean)
-              .join("\n\n");
 
             // Only update currentResponse if target conversation is active
             if (this.activeConversationId === targetConversationId) {
@@ -1955,7 +1896,7 @@ class AppStore {
               assistantMessage.id,
               (msg) => {
                 msg.content = displayContent;
-                msg.thinking = combinedThinking || undefined;
+                msg.thinking = thinkingContent || undefined;
                 msg.tokens = [...collectedTokens];
               },
             );
@@ -1967,17 +1908,14 @@ class AppStore {
 
       // Final cleanup of the message (if conversation still exists)
       if (this.conversationExists(targetConversationId)) {
-        const { displayContent, thinkingContent: tagThinking } =
+        const { displayContent, thinkingContent } =
           this.stripThinkingTags(streamedContent);
-        const finalThinking = [streamedThinking, tagThinking]
-          .filter(Boolean)
-          .join("\n\n");
         this.updateConversationMessage(
           targetConversationId,
           assistantMessage.id,
           (msg) => {
             msg.content = displayContent;
-            msg.thinking = finalThinking || undefined;
+            msg.thinking = thinkingContent || undefined;
             msg.tokens = [...collectedTokens];
           },
         );
@@ -2066,7 +2004,6 @@ class AppStore {
     reader: ReadableStreamDefaultReader<Uint8Array>,
     targetConversationId: string,
     onChunk: (parsed: T) => void,
-    onEvent?: Record<string, (data: unknown) => void>,
   ): Promise<void> {
     const decoder = new TextDecoder();
     let buffer = "";
@@ -2087,24 +2024,6 @@ class AppStore {
         const trimmed = line.trim();
         if (!trimmed) continue;
 
-        // Handle SSE comments (": key json") for prefill progress etc.
-        if (trimmed.startsWith(": ") && onEvent) {
-          const comment = trimmed.slice(2);
-          const spaceIdx = comment.indexOf(" ");
-          if (spaceIdx > 0) {
-            const key = comment.slice(0, spaceIdx);
-            if (onEvent[key]) {
-              try {
-                const parsed = JSON.parse(comment.slice(spaceIdx + 1));
-                onEvent[key](parsed);
-              } catch {
-                // Skip malformed JSON in comment
-              }
-            }
-          }
-          continue;
-        }
-
         if (trimmed.startsWith("data: ")) {
           const data = trimmed.slice(6);
           if (data === "[DONE]") continue;
@@ -2324,7 +2243,7 @@ class AppStore {
       const modelToUse = this.getModelForRequest();
       if (!modelToUse) {
         throw new Error(
-          "No model is loaded yet. Select a model from the sidebar to get started — it will download and load automatically.",
+          "No model selected and no running instances available. Please launch an instance first.",
         );
       }
 
@@ -2336,9 +2255,6 @@ class AppStore {
       let firstTokenTime: number | null = null;
       let tokenCount = 0;
 
-      const abortController = new AbortController();
-      this.currentAbortController = abortController;
-
       const response = await fetch("/v1/chat/completions", {
         method: "POST",
         headers: {
@@ -2355,7 +2271,6 @@ class AppStore {
             enable_thinking: enableThinking,
           }),
         }),
-        signal: abortController.signal,
       });
 
       if (!response.ok) {
@@ -2369,11 +2284,10 @@ class AppStore {
       }
 
       let streamedContent = "";
-      let streamedThinking = "";
 
       interface ChatCompletionChunk {
         choices?: Array<{
-          delta?: { content?: string; reasoning_content?: string };
+          delta?: { content?: string };
           logprobs?: {
             content?: Array<{
               token: string;
@@ -2394,14 +2308,8 @@ class AppStore {
         reader,
         targetConversationId,
         (parsed) => {
-          // Clear prefill progress when first token data arrives
-          if (this.prefillProgress) {
-            this.prefillProgress = null;
-          }
-
           const choice = parsed.choices?.[0];
           const tokenContent = choice?.delta?.content;
-          const thinkingContent = choice?.delta?.reasoning_content;
 
           // Collect logprobs data
           const logprobsContent = choice?.logprobs?.content;
@@ -2420,11 +2328,7 @@ class AppStore {
             }
           }
 
-          if (thinkingContent) {
-            streamedThinking += thinkingContent;
-          }
-
-          if (tokenContent || thinkingContent) {
+          if (tokenContent) {
             // Track first token for TTFT
             if (firstTokenTime === null) {
               firstTokenTime = performance.now();
@@ -2441,16 +2345,11 @@ class AppStore {
               this.tps = (tokenCount / elapsed) * 1000;
             }
 
-            if (tokenContent) {
-              streamedContent += tokenContent;
-            }
+            streamedContent += tokenContent;
 
-            // Use stripThinkingTags as fallback for any <think> tags still in content
-            const { displayContent, thinkingContent: tagThinking } =
+            // Strip thinking tags for display and extract thinking content
+            const { displayContent, thinkingContent } =
               this.stripThinkingTags(streamedContent);
-            const combinedThinking = [streamedThinking, tagThinking]
-              .filter(Boolean)
-              .join("\n\n");
 
             // Only update currentResponse if target conversation is active
             if (this.activeConversationId === targetConversationId) {
@@ -2463,7 +2362,7 @@ class AppStore {
               assistantMessage.id,
               (msg) => {
                 msg.content = displayContent;
-                msg.thinking = combinedThinking || undefined;
+                msg.thinking = thinkingContent || undefined;
                 msg.tokens = [...collectedTokens];
               },
             );
@@ -2471,27 +2370,8 @@ class AppStore {
             this.persistConversation(targetConversationId);
           }
         },
-        {
-          prefill_progress: (data) => {
-            // TaggedModel wraps as {"PrefillProgressChunk": {...}}
-            // model_dump_json() uses snake_case (by_alias defaults to False)
-            const raw = data as Record<string, unknown>;
-            const inner = (raw["PrefillProgressChunk"] ?? raw) as {
-              processed_tokens: number;
-              total_tokens: number;
-            };
-            this.prefillProgress = {
-              processed: inner.processed_tokens,
-              total: inner.total_tokens,
-              startedAt: this.prefillProgress?.startedAt ?? performance.now(),
-            };
-          },
-        },
       );
 
-      // Clear prefill progress after stream ends
-      this.prefillProgress = null;
-
       // Calculate final TPS
       if (firstTokenTime !== null && tokenCount > 1) {
         const totalGenerationTime = performance.now() - firstTokenTime;
@@ -2500,17 +2380,14 @@ class AppStore {
 
       // Final cleanup of the message (if conversation still exists)
       if (this.conversationExists(targetConversationId)) {
-        const { displayContent, thinkingContent: tagThinking } =
+        const { displayContent, thinkingContent } =
           this.stripThinkingTags(streamedContent);
-        const finalThinking = [streamedThinking, tagThinking]
-          .filter(Boolean)
-          .join("\n\n");
         this.updateConversationMessage(
           targetConversationId,
           assistantMessage.id,
           (msg) => {
             msg.content = displayContent;
-            msg.thinking = finalThinking || undefined;
+            msg.thinking = thinkingContent || undefined;
             msg.tokens = [...collectedTokens];
             // Store performance metrics on the message
             if (this.ttftMs !== null) {
@@ -2525,31 +2402,20 @@ class AppStore {
         this.persistConversation(targetConversationId);
       }
     } catch (error) {
-      if (error instanceof DOMException && error.name === "AbortError") {
-        // User stopped generation — not an error
-      } else {
-        console.error("Error sending message:", error);
-        this.handleStreamingError(
-          error,
-          targetConversationId,
-          assistantMessage.id,
-          "Failed to get response",
-        );
-      }
+      console.error("Error sending message:", error);
+      this.handleStreamingError(
+        error,
+        targetConversationId,
+        assistantMessage.id,
+        "Failed to get response",
+      );
     } finally {
-      this.currentAbortController = null;
-      this.prefillProgress = null;
       this.isLoading = false;
       this.currentResponse = "";
       this.saveConversationsToStorage();
     }
   }
 
-  stopGeneration(): void {
-    this.currentAbortController?.abort();
-    this.currentAbortController = null;
-  }
-
   /**
    * Generate an image using the image generation API
    */
@@ -3158,23 +3024,6 @@ class AppStore {
     return (await response.json()) as TraceStatsResponse;
   }
 
-  /**
-   * Delete traces by task IDs
-   */
-  async deleteTraces(
-    taskIds: string[],
-  ): Promise<{ deleted: string[]; notFound: string[] }> {
-    const response = await fetch("/v1/traces/delete", {
-      method: "POST",
-      headers: { "Content-Type": "application/json" },
-      body: JSON.stringify({ taskIds }),
-    });
-    if (!response.ok) {
-      throw new Error(`Failed to delete traces: ${response.status}`);
-    }
-    return await response.json();
-  }
-
   /**
    * Get the URL for the raw trace file (for Perfetto)
    */
@@ -3193,7 +3042,6 @@ export const isLoading = () => appStore.isLoading;
 export const ttftMs = () => appStore.ttftMs;
 export const tps = () => appStore.tps;
 export const totalTokens = () => appStore.totalTokens;
-export const prefillProgress = () => appStore.prefillProgress;
 export const topologyData = () => appStore.topologyData;
 export const instances = () => appStore.instances;
 export const runners = () => appStore.runners;
@@ -3211,7 +3059,6 @@ export const topologyOnlyMode = () => appStore.getTopologyOnlyMode();
 export const chatSidebarVisible = () => appStore.getChatSidebarVisible();
 
 // Actions
-export const stopGeneration = () => appStore.stopGeneration();
 export const startChat = () => appStore.startChat();
 export const sendMessage = (
   content: string,
@@ -3284,9 +3131,6 @@ export const setChatSidebarVisible = (visible: boolean) =>
   appStore.setChatSidebarVisible(visible);
 export const refreshState = () => appStore.fetchState();
 
-// Connection status
-export const isConnected = () => appStore.isConnected;
-
 // Node identities (for OS version mismatch detection)
 export const nodeIdentities = () => appStore.nodeIdentities;
 
@@ -3318,5 +3162,3 @@ export const fetchTraceStats = (taskId: string) =>
   appStore.fetchTraceStats(taskId);
 export const getTraceRawUrl = (taskId: string) =>
   appStore.getTraceRawUrl(taskId);
-export const deleteTraces = (taskIds: string[]) =>
-  appStore.deleteTraces(taskIds);

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

@@ -1,87 +0,0 @@
-/**
- * Toast notification store - Global notification system for the EXO dashboard.
- *
- * Usage:
- *   import { addToast, dismissToast, toasts } from "$lib/stores/toast.svelte";
- *   addToast({ type: "success", message: "Model launched" });
- *   addToast({ type: "error", message: "Connection lost", persistent: true });
- */
-
-type ToastType = "success" | "error" | "warning" | "info";
-
-export interface Toast {
-  id: string;
-  type: ToastType;
-  message: string;
-  /** Auto-dismiss after this many ms. 0 = persistent (must be dismissed manually). */
-  duration: number;
-  createdAt: number;
-}
-
-interface ToastInput {
-  type: ToastType;
-  message: string;
-  /** If true, toast stays until manually dismissed. Default: false. */
-  persistent?: boolean;
-  /** Auto-dismiss duration in ms. Default: 4000 for success/info, 6000 for error/warning. */
-  duration?: number;
-}
-
-const DEFAULT_DURATIONS: Record<ToastType, number> = {
-  success: 4000,
-  info: 4000,
-  warning: 6000,
-  error: 6000,
-};
-
-let toastList = $state<Toast[]>([]);
-const timers = new Map<string, ReturnType<typeof setTimeout>>();
-
-function generateId(): string {
-  return `toast-${Date.now()}-${Math.random().toString(36).slice(2, 8)}`;
-}
-
-export function addToast(input: ToastInput): string {
-  const id = generateId();
-  const duration = input.persistent
-    ? 0
-    : (input.duration ?? DEFAULT_DURATIONS[input.type]);
-
-  const toast: Toast = {
-    id,
-    type: input.type,
-    message: input.message,
-    duration,
-    createdAt: Date.now(),
-  };
-
-  toastList = [...toastList, toast];
-
-  if (duration > 0) {
-    const timer = setTimeout(() => dismissToast(id), duration);
-    timers.set(id, timer);
-  }
-
-  return id;
-}
-
-export function dismissToast(id: string): void {
-  const timer = timers.get(id);
-  if (timer) {
-    clearTimeout(timer);
-    timers.delete(id);
-  }
-  toastList = toastList.filter((t) => t.id !== id);
-}
-
-/** Dismiss all toasts matching a message (useful for dedup). */
-export function dismissByMessage(message: string): void {
-  const matching = toastList.filter((t) => t.message === message);
-  for (const t of matching) {
-    dismissToast(t.id);
-  }
-}
-
-export function toasts(): Toast[] {
-  return toastList;
-}

dashboard/src/routes/+layout.svelte

@@ -1,7 +1,5 @@
 <script lang="ts">
   import "../app.css";
-  import ToastContainer from "$lib/components/ToastContainer.svelte";
-  import ConnectionBanner from "$lib/components/ConnectionBanner.svelte";
 
   let { children } = $props();
 </script>
@@ -12,7 +10,5 @@
 </svelte:head>
 
 <div class="min-h-screen bg-background text-foreground">
-  <ConnectionBanner />
   {@render children?.()}
-  <ToastContainer />
 </div>

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

@@ -3,7 +3,6 @@
   import {
     listTraces,
     getTraceRawUrl,
-    deleteTraces,
     type TraceListItem,
   } from "$lib/stores/app.svelte";
   import HeaderNav from "$lib/components/HeaderNav.svelte";
@@ -11,51 +10,6 @@
   let traces = $state<TraceListItem[]>([]);
   let loading = $state(true);
   let error = $state<string | null>(null);
-  let selectedIds = $state<Set<string>>(new Set());
-  let deleting = $state(false);
-
-  let allSelected = $derived(
-    traces.length > 0 && selectedIds.size === traces.length,
-  );
-
-  function toggleSelect(taskId: string) {
-    const next = new Set(selectedIds);
-    if (next.has(taskId)) {
-      next.delete(taskId);
-    } else {
-      next.add(taskId);
-    }
-    selectedIds = next;
-  }
-
-  function toggleSelectAll() {
-    if (allSelected) {
-      selectedIds = new Set();
-    } else {
-      selectedIds = new Set(traces.map((t) => t.taskId));
-    }
-  }
-
-  async function handleDelete() {
-    if (selectedIds.size === 0) return;
-    const count = selectedIds.size;
-    if (
-      !confirm(
-        `Delete ${count} trace${count === 1 ? "" : "s"}? This cannot be undone.`,
-      )
-    )
-      return;
-    deleting = true;
-    try {
-      await deleteTraces([...selectedIds]);
-      selectedIds = new Set();
-      await refresh();
-    } catch (e) {
-      error = e instanceof Error ? e.message : "Failed to delete traces";
-    } finally {
-      deleting = false;
-    }
-  }
 
   function formatBytes(bytes: number): string {
     if (!bytes || bytes <= 0) return "0B";
@@ -155,16 +109,6 @@
         </h1>
       </div>
       <div class="flex items-center gap-3">
-        {#if selectedIds.size > 0}
-          <button
-            type="button"
-            class="text-xs font-mono text-red-400 hover:text-red-300 transition-colors uppercase border border-red-500/40 px-2 py-1 rounded"
-            onclick={handleDelete}
-            disabled={deleting}
-          >
-            {deleting ? "Deleting..." : `Delete (${selectedIds.size})`}
-          </button>
-        {/if}
         <button
           type="button"
           class="text-xs font-mono text-exo-light-gray hover:text-exo-yellow transition-colors uppercase border border-exo-medium-gray/40 px-2 py-1 rounded"
@@ -199,41 +143,14 @@
       </div>
     {:else}
       <div class="space-y-3">
-        <div class="flex items-center gap-2 px-1">
-          <button
-            type="button"
-            class="text-xs font-mono uppercase transition-colors {allSelected
-              ? 'text-exo-yellow'
-              : 'text-exo-light-gray hover:text-exo-yellow'}"
-            onclick={toggleSelectAll}
-          >
-            {allSelected ? "Deselect all" : "Select all"}
-          </button>
-        </div>
         {#each traces as trace}
-          {@const isSelected = selectedIds.has(trace.taskId)}
-          <!-- svelte-ignore a11y_no_static_element_interactions -->
           <div
-            role="button"
-            tabindex="0"
-            class="w-full text-left rounded border-l-2 border-r border-t border-b transition-all p-4 flex items-center justify-between gap-4 cursor-pointer {isSelected
-              ? 'bg-exo-yellow/10 border-l-exo-yellow border-r-exo-medium-gray/30 border-t-exo-medium-gray/30 border-b-exo-medium-gray/30'
-              : 'bg-exo-black/30 border-l-transparent border-r-exo-medium-gray/30 border-t-exo-medium-gray/30 border-b-exo-medium-gray/30 hover:bg-white/[0.03]'}"
-            onclick={() => toggleSelect(trace.taskId)}
-            onkeydown={(e) => {
-              if (e.key === "Enter" || e.key === " ") {
-                e.preventDefault();
-                toggleSelect(trace.taskId);
-              }
-            }}
+            class="rounded border border-exo-medium-gray/30 bg-exo-black/30 p-4 flex items-center justify-between gap-4"
           >
             <div class="min-w-0 flex-1">
               <a
                 href="#/traces/{trace.taskId}"
-                class="text-sm font-mono transition-colors truncate block {isSelected
-                  ? 'text-exo-yellow'
-                  : 'text-white hover:text-exo-yellow'}"
-                onclick={(e) => e.stopPropagation()}
+                class="text-sm font-mono text-white hover:text-exo-yellow transition-colors truncate block"
               >
                 {trace.taskId}
               </a>
@@ -243,11 +160,7 @@
                 )}
               </div>
             </div>
-            <!-- svelte-ignore a11y_click_events_have_key_events -->
-            <div
-              class="flex items-center gap-2 shrink-0"
-              onclick={(e) => e.stopPropagation()}
-            >
+            <div class="flex items-center gap-2 shrink-0">
               <a
                 href="#/traces/{trace.taskId}"
                 class="text-xs font-mono text-exo-light-gray hover:text-exo-yellow transition-colors uppercase border border-exo-medium-gray/40 px-2 py-1 rounded"

docs/api.md

@@ -183,27 +183,6 @@ Same schema as `/v1/chat/completions`.
 **Response:**
 Chat completion plus benchmarking metrics.
 
-### Cancel Command
-
-**POST** `/v1/cancel/{command_id}`
-
-Cancels an active generation command (text or image). Notifies workers and closes the stream.
-
-**Path parameters:**
-
-* `command_id`: string, ID of the command to cancel
-
-**Response (example):**
-
-```json
-{
-  "message": "Command cancelled.",
-  "command_id": "cmd-abc-123"
-}
-```
-
-Returns 404 if the command is not found or already completed.
-
 ## 5. Image Generation & Editing
 
 ### Image Generation
@@ -287,7 +266,6 @@ GET     /v1/models
 
 POST    /v1/chat/completions
 POST    /bench/chat/completions
-POST    /v1/cancel/{command_id}
 
 POST    /v1/images/generations
 POST    /bench/images/generations

e2e/Dockerfile

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

e2e/conftest.py

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

e2e/docker-compose.yml

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

e2e/run_all.py

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

e2e/snapshot.py

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

e2e/test_cluster_formation.py

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

e2e/test_inference_snapshot.py

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

e2e/test_no_internet.py

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

e2e/test_runner_chaos.py

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

e2e/test_snapshot_code_gen.py

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

e2e/test_snapshot_edge.py

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

e2e/test_snapshot_long_output.py

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

e2e/test_snapshot_multi_model.py

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

e2e/test_snapshot_reasoning.py

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

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

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

flake.nix

@@ -74,6 +74,7 @@
       perSystem =
         { config, self', inputs', pkgs, lib, system, ... }:
         let
+          fenixToolchain = inputs'.fenix.packages.complete;
           # Use pinned nixpkgs for swift-format (swift is broken on x86_64-linux in newer nixpkgs)
           pkgsSwift = import inputs.nixpkgs-swift { inherit system; };
         in
@@ -108,14 +109,13 @@
                 package = pkgsSwift.swiftPackages.swift-format;
               };
               shfmt.enable = true;
-              taplo.enable = true;
             };
           };
 
           packages = lib.optionalAttrs pkgs.stdenv.hostPlatform.isDarwin (
             let
               uvLock = builtins.fromTOML (builtins.readFile ./uv.lock);
-              mlxPackage = builtins.head (builtins.filter (p: p.name == "mlx" && p.source ? git) uvLock.package);
+              mlxPackage = builtins.head (builtins.filter (p: p.name == "mlx") uvLock.package);
               uvLockMlxVersion = mlxPackage.version;
             in
             {

nix/mlx.nix

@@ -41,16 +41,16 @@ let
 
   mlx = stdenv.mkDerivation rec {
     pname = "mlx";
-    version = let v = "0.30.7.dev20260225+257d5692"; in
+    version = let v = "0.30.6"; 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;
 
     src = fetchFromGitHub {
-      owner = "rltakashige";
-      repo = "mlx-jaccl-fix-small-recv";
-      rev = "257d5692fc7af6bba3b8afaeb63c549b7d1e43d5";
-      hash = "sha256-GosFIWxIB48Egb1MqJrR3xhsUsQeWdRk5rV93USY6wQ=";
+      owner = "ml-explore";
+      repo = "mlx";
+      tag = "v${version}";
+      hash = "sha256-avD5EGhwgmPdXLAyQSqTO6AXk/W3ziH+f6AetjK3Sdo=";
     };
 
     patches = [

packaging/dmg/create-dmg.sh

@@ -1,112 +0,0 @@
-#!/usr/bin/env bash
-# create-dmg.sh — Build a polished macOS DMG installer for EXO
-#
-# Usage:
-#   ./packaging/dmg/create-dmg.sh <app-path> <output-dmg> [volume-name]
-#
-# Example:
-#   ./packaging/dmg/create-dmg.sh output/EXO.app EXO-1.0.0.dmg "EXO"
-#
-# Creates a DMG with:
-#   - Custom background image with drag-to-Applications arrow
-#   - App icon on left, Applications alias on right
-#   - Proper window size and icon positioning
-set -euo pipefail
-
-APP_PATH="${1:?Usage: create-dmg.sh <app-path> <output-dmg> [volume-name]}"
-OUTPUT_DMG="${2:?Usage: create-dmg.sh <app-path> <output-dmg> [volume-name]}"
-VOLUME_NAME="${3:-EXO}"
-
-SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
-BACKGROUND_SCRIPT="${SCRIPT_DIR}/generate-background.py"
-TEMP_DIR="$(mktemp -d)"
-DMG_STAGING="${TEMP_DIR}/dmg-root"
-TEMP_DMG="${TEMP_DIR}/temp.dmg"
-BACKGROUND_PNG="${TEMP_DIR}/background.png"
-
-cleanup() { rm -rf "$TEMP_DIR"; }
-trap cleanup EXIT
-
-echo "==> Creating DMG installer for ${VOLUME_NAME}"
-
-# ── Step 1: Generate background image ────────────────────────────────────────
-if command -v python3 &>/dev/null; then
-  python3 "$BACKGROUND_SCRIPT" "$BACKGROUND_PNG"
-  echo "    Background image generated"
-else
-  echo "    Warning: python3 not found, skipping custom background"
-  BACKGROUND_PNG=""
-fi
-
-# ── Step 2: Prepare staging directory ─────────────────────────────────────────
-mkdir -p "$DMG_STAGING"
-cp -R "$APP_PATH" "$DMG_STAGING/"
-ln -s /Applications "$DMG_STAGING/Applications"
-
-# ── Step 3: Create writable DMG ──────────────────────────────────────────────
-# Calculate required size (app size + 20MB headroom)
-APP_SIZE_KB=$(du -sk "$APP_PATH" | cut -f1)
-DMG_SIZE_KB=$((APP_SIZE_KB + 20480))
-
-hdiutil create \
-  -volname "$VOLUME_NAME" \
-  -size "${DMG_SIZE_KB}k" \
-  -fs HFS+ \
-  -layout SPUD \
-  "$TEMP_DMG"
-
-# ── Step 4: Mount and configure ──────────────────────────────────────────────
-MOUNT_DIR=$(hdiutil attach "$TEMP_DMG" -readwrite -noverify | awk -F'\t' '/Apple_HFS/ {gsub(/^[[:space:]]+|[[:space:]]+$/, "", $NF); print $NF}')
-echo "    Mounted at: $MOUNT_DIR"
-
-# Copy contents
-cp -R "$DMG_STAGING/"* "$MOUNT_DIR/"
-
-# Add background image
-if [[ -n $BACKGROUND_PNG && -f $BACKGROUND_PNG ]]; then
-  mkdir -p "$MOUNT_DIR/.background"
-  cp "$BACKGROUND_PNG" "$MOUNT_DIR/.background/background.png"
-fi
-
-# ── Step 5: Configure window appearance via AppleScript ──────────────────────
-# Window: 800×400, app icon on left, Applications on right (matches Ollama layout)
-# Background image is 1600×740 (2× retina for 800×400 logical window).
-APP_NAME="$(basename "$APP_PATH")"
-
-osascript <<APPLESCRIPT
-tell application "Finder"
-    tell disk "$VOLUME_NAME"
-        open
-        set current view of container window to icon view
-        set toolbar visible of container window to false
-        set statusbar visible of container window to false
-        set bounds of container window to {200, 120, 1000, 520}
-        set opts to icon view options of container window
-        set icon size of opts to 128
-        set text size of opts to 12
-        set arrangement of opts to not arranged
-        if exists file ".background:background.png" then
-            set background picture of opts to file ".background:background.png"
-        end if
-        set position of item "$APP_NAME" of container window to {200, 190}
-        set position of item "Applications" of container window to {600, 190}
-        close
-        open
-        update without registering applications
-        delay 1
-        close
-    end tell
-end tell
-APPLESCRIPT
-
-echo "    Window layout configured"
-
-# Ensure Finder updates are flushed
-sync
-
-# ── Step 6: Finalise ─────────────────────────────────────────────────────────
-hdiutil detach "$MOUNT_DIR" -quiet
-hdiutil convert "$TEMP_DMG" -format UDZO -imagekey zlib-level=9 -o "$OUTPUT_DMG"
-
-echo "==> DMG created: $OUTPUT_DMG"
-echo "    Size: $(du -h "$OUTPUT_DMG" | cut -f1)"

packaging/dmg/generate-background.py

@@ -1,91 +0,0 @@
-#!/usr/bin/env python3
-"""Generate the DMG background image with a centered drag-to-Applications arrow.
-
-The output is a 1600×740 retina PNG (2× for 800×400 logical window).
-Icons are positioned at (200, 190) and (600, 190) in logical coordinates;
-the arrow is drawn centered between them.
-
-Usage:
-    python3 generate-background.py [output.png]
-
-If no output path is given, overwrites the bundled background.png in-place.
-"""
-
-from __future__ import annotations
-
-import math
-import sys
-from pathlib import Path
-
-from PIL import Image, ImageDraw
-
-# Retina dimensions (2× logical 800×400)
-WIDTH = 1600
-HEIGHT = 740
-
-# Icon positions in logical coords → retina coords
-# App icon at (200, 190), Applications at (600, 190)
-APP_X = 200 * 2  # 400
-APPS_X = 600 * 2  # 1200
-ICON_Y = 190 * 2  # 380
-
-# Arrow drawn between icons, slightly above icon center
-ARROW_START_X = APP_X + 160  # past the icon
-ARROW_END_X = APPS_X - 160  # before the Applications icon
-ARROW_Y = ICON_Y  # same height as icons
-ARROW_RISE = 120  # upward arc height
-
-
-def draw_arrow(draw: ImageDraw.ImageDraw) -> None:
-    """Draw a hand-drawn-style curved arrow from app icon toward Applications."""
-    color = (30, 30, 30)
-    line_width = 8
-
-    # Compute bezier curve points for a gentle upward arc
-    points: list[tuple[float, float]] = []
-    steps = 80
-    for i in range(steps + 1):
-        t = i / steps
-        # Quadratic bezier: start → control → end
-        cx = (ARROW_START_X + ARROW_END_X) / 2
-        cy = ARROW_Y - ARROW_RISE
-        x = (1 - t) ** 2 * ARROW_START_X + 2 * (1 - t) * t * cx + t**2 * ARROW_END_X
-        y = (1 - t) ** 2 * ARROW_Y + 2 * (1 - t) * t * cy + t**2 * ARROW_Y
-        points.append((x, y))
-
-    # Draw the curve as connected line segments
-    for i in range(len(points) - 1):
-        draw.line([points[i], points[i + 1]], fill=color, width=line_width)
-
-    # Arrowhead at the end
-    end_x, end_y = points[-1]
-    # Direction from second-to-last to last point
-    prev_x, prev_y = points[-3]
-    angle = math.atan2(end_y - prev_y, end_x - prev_x)
-    head_len = 36
-    head_angle = math.radians(25)
-
-    left_x = end_x - head_len * math.cos(angle - head_angle)
-    left_y = end_y - head_len * math.sin(angle - head_angle)
-    right_x = end_x - head_len * math.cos(angle + head_angle)
-    right_y = end_y - head_len * math.sin(angle + head_angle)
-
-    draw.polygon(
-        [(end_x, end_y), (left_x, left_y), (right_x, right_y)],
-        fill=color,
-    )
-
-
-def generate_background(output_path: str) -> None:
-    """Generate a white DMG background with a centered arrow."""
-    img = Image.new("RGBA", (WIDTH, HEIGHT), (255, 255, 255, 255))
-    draw = ImageDraw.Draw(img)
-    draw_arrow(draw)
-    img.save(output_path, "PNG")
-
-
-if __name__ == "__main__":
-    default_output = str(Path(__file__).parent / "background.png")
-    out = sys.argv[1] if len(sys.argv) >= 2 else default_output
-    generate_background(out)
-    print(f"Background image written to {out}")

pyproject.toml

@@ -1,35 +1,35 @@
 [project]
 name = "exo"
-version = "0.3.68"
+version = "0.3.0"
 description = "Exo"
 readme = "README.md"
 requires-python = ">=3.13"
 dependencies = [
-  "aiofiles>=24.1.0",
-  "aiohttp>=3.12.14",
-  "types-aiofiles>=24.1.0.20250708",
-  "pydantic>=2.11.7",
-  "fastapi>=0.116.1",
-  "filelock>=3.18.0",
-  "rustworkx>=0.17.1",
-  "huggingface-hub>=0.33.4",
-  "psutil>=7.0.0",
-  "loguru>=0.7.3",
-  "exo_pyo3_bindings",                         # rust bindings
-  "anyio==4.11.0",
-  "mlx; sys_platform == 'darwin'",
-  "mlx[cpu]==0.30.6; sys_platform == 'linux'",
-  "mlx-lm",
-  "tiktoken>=0.12.0",                          # required for kimi k2 tokenizer
-  "hypercorn>=0.18.0",
-  "openai-harmony>=0.0.8",
-  "httpx>=0.28.1",
-  "tomlkit>=0.14.0",
-  "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",
+    "aiofiles>=24.1.0",
+    "aiohttp>=3.12.14",
+    "types-aiofiles>=24.1.0.20250708",
+    "pydantic>=2.11.7",
+    "fastapi>=0.116.1",
+    "filelock>=3.18.0",
+    "rustworkx>=0.17.1",
+    "huggingface-hub>=0.33.4",
+    "psutil>=7.0.0",
+    "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-lm==0.30.6",
+    "tiktoken>=0.12.0", # required for kimi k2 tokenizer
+    "hypercorn>=0.18.0",
+    "openai-harmony>=0.0.8",
+    "httpx>=0.28.1",
+    "tomlkit>=0.14.0",
+    "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]
@@ -38,12 +38,12 @@ exo = "exo.main:main"
 # dependencies only required for development
 [dependency-groups]
 dev = [
-  "basedpyright>=1.29.0",
-  "pyinstaller>=6.17.0",
-  "pytest>=8.4.0",
-  "pytest-asyncio>=1.0.0",
-  "pytest-env",
-  "ruff>=0.11.13",
+    "basedpyright>=1.29.0",
+    "pyinstaller>=6.17.0",
+    "pytest>=8.4.0",
+    "pytest-asyncio>=1.0.0",
+    "pytest-env",
+    "ruff>=0.11.13",
 ]
 
 # mlx[cuda] requires a newer version of mlx. the ideal on linux is: default to mlx[cpu] unless[cuda] specified.
@@ -57,12 +57,14 @@ dev = [
 ###
 
 [tool.uv.workspace]
-members = ["rust/exo_pyo3_bindings", "bench"]
+members = [
+    "rust/exo_pyo3_bindings",
+    "bench",
+]
 
 [tool.uv.sources]
 exo_pyo3_bindings = { workspace = true }
-mlx = { git = "https://github.com/rltakashige/mlx-jaccl-fix-small-recv.git", branch = "address-rdma-gpu-locks", marker = "sys_platform == 'darwin'" }
-mlx-lm = { git = "https://github.com/ml-explore/mlx-lm", rev = "834fac934c4e04de9b3d723e2b9287a2c60cfd4a" }
+#mlx-lm = { git = "https://github.com/davidmcc73/mlx-lm", branch = "stable" }
 # Uncomment to use local mlx/mlx-lm development versions:
 # mlx = { path = "/Users/Shared/mlx", editable=true }
 # mlx-lm = { path = "/Users/Shared/mlx-lm", editable=true }
@@ -92,15 +94,7 @@ reportUnnecessaryTypeIgnoreComment = "error"
 pythonVersion = "3.13"
 pythonPlatform = "Darwin"
 
-exclude = [
-  "**/.venv",
-  "**/venv",
-  "**/__pycache__",
-  "**/exo_scripts",
-  "**/.direnv",
-  "**/rust",
-  "**/.github",
-]
+exclude = ["**/.venv", "**/venv", "**/__pycache__", "**/exo_scripts", "**/.direnv", "**/rust", "**/.github"]
 stubPath = ".mlx_typings"
 
 [[tool.basedpyright.executionEnvironments]]
@@ -114,18 +108,17 @@ root = "src"
 [tool.uv]
 required-version = ">=0.8.6"
 prerelease = "allow"
-environments = ["sys_platform == 'darwin'", "sys_platform == 'linux'"]
+environments = [
+    "sys_platform == 'darwin'",
+    "sys_platform == 'linux'",
+]
 
 ###
 # ruff configuration
 ###
 
 [tool.ruff]
-extend-exclude = [
-  "shared/protobufs/**",
-  "*mlx_typings/**",
-  "rust/exo_pyo3_bindings/**",
-]
+extend-exclude = ["shared/protobufs/**", "*mlx_typings/**", "rust/exo_pyo3_bindings/**"]
 
 [tool.ruff.lint]
 extend-select = ["I", "N", "B", "A", "PIE", "SIM"]
@@ -133,7 +126,13 @@ extend-select = ["I", "N", "B", "A", "PIE", "SIM"]
 [tool.pytest.ini_options]
 pythonpath = "."
 asyncio_mode = "auto"
-markers = ["slow: marks tests as slow (deselected by default)"]
-env = ["EXO_TESTS=1"]
-addopts = "-m 'not slow' --ignore=tests/start_distributed_test.py"
-filterwarnings = ["ignore:builtin type Swig:DeprecationWarning"]
+markers = [
+    "slow: marks tests as slow (deselected by default)"
+]
+env = [
+  "EXO_TESTS=1"
+]
+addopts = "-m 'not slow'"
+filterwarnings = [
+    "ignore:builtin type Swig:DeprecationWarning",
+]

python/parts.nix

@@ -58,21 +58,6 @@
         lib.optionalAttrs pkgs.stdenv.hostPlatform.isLinux (
           (lib.mapAttrs (_: ignoreMissing) nvidiaPackages) // {
             mlx = ignoreMissing prev.mlx;
-            mlx-cuda-13 = prev.mlx-cuda-13.overrideAttrs (old: {
-              buildInputs = (old.buildInputs or [ ]) ++ [
-                final.nvidia-cublas
-                final.nvidia-cuda-nvrtc
-                final.nvidia-cudnn-cu13
-                final.nvidia-nccl-cu13
-              ];
-              preFixup = ''
-                addAutoPatchelfSearchPath ${final.nvidia-cublas}
-                addAutoPatchelfSearchPath ${final.nvidia-cuda-nvrtc}
-                addAutoPatchelfSearchPath ${final.nvidia-cudnn-cu13}
-                addAutoPatchelfSearchPath ${final.nvidia-nccl-cu13}
-              '';
-              autoPatchelfIgnoreMissingDeps = [ "libcuda.so.1" ];
-            });
             torch = ignoreMissing prev.torch;
             triton = ignoreMissing prev.triton;
           }
@@ -89,25 +74,14 @@
           linuxOverlay
         ]
       );
-      # mlx-cpu and mlx-cuda-13 both ship mlx/ site-packages files; keep first.
-      # mlx-cpu/mlx-cuda-13 and nvidia-cudnn-cu12/cu13 ship overlapping files.
-      venvCollisionPaths = lib.optionals pkgs.stdenv.hostPlatform.isLinux [
-        "lib/python3.13/site-packages/mlx*"
-        "lib/python3.13/site-packages/nvidia*"
-      ];
-
-      exoVenv = (pythonSet.mkVirtualEnv "exo-env" workspace.deps.default).overrideAttrs {
-        venvIgnoreCollisions = venvCollisionPaths;
-      };
+      exoVenv = pythonSet.mkVirtualEnv "exo-env" workspace.deps.default;
 
       # Virtual environment with dev dependencies for testing
-      testVenv = (pythonSet.mkVirtualEnv "exo-test-env" (
+      testVenv = pythonSet.mkVirtualEnv "exo-test-env" (
         workspace.deps.default // {
           exo = [ "dev" ]; # Include pytest, pytest-asyncio, pytest-env
         }
-      )).overrideAttrs {
-        venvIgnoreCollisions = venvCollisionPaths;
-      };
+      );
 
       mkPythonScript = name: path: pkgs.writeShellApplication {
         inherit name;
@@ -158,7 +132,6 @@
           exo-test-env = testVenv;
         } // {
         exo-bench = mkBenchScript "exo-bench" (inputs.self + /bench/exo_bench.py);
-        exo-eval-tool-calls = mkBenchScript "exo-eval-tool-calls" (inputs.self + /bench/eval_tool_calls.py);
         exo-get-all-models-on-cluster = mkSimplePythonScript "exo-get-all-models-on-cluster" (inputs.self + /tests/get_all_models_on_cluster.py);
       };
 

resources/inference_model_cards/mlx-community--DeepSeek-V3.1-4bit.toml

@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
 family = "deepseek"
 quantization = "4bit"
 base_model = "DeepSeek V3.1"
-capabilities = ["text", "thinking", "thinking_toggle"]
+capabilities = ["text", "thinking"]
 
 [storage_size]
 in_bytes = 405874409472

resources/inference_model_cards/mlx-community--DeepSeek-V3.1-8bit.toml

@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
 family = "deepseek"
 quantization = "8bit"
 base_model = "DeepSeek V3.1"
-capabilities = ["text", "thinking", "thinking_toggle"]
+capabilities = ["text", "thinking"]
 
 [storage_size]
 in_bytes = 765577920512

resources/inference_model_cards/mlx-community--GLM-4.5-Air-8bit.toml

@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
 family = "glm"
 quantization = "8bit"
 base_model = "GLM 4.5 Air"
-capabilities = ["text", "thinking", "thinking_toggle"]
+capabilities = ["text", "thinking"]
 
 [storage_size]
 in_bytes = 122406567936

resources/inference_model_cards/mlx-community--GLM-4.5-Air-bf16.toml

@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
 family = "glm"
 quantization = "bf16"
 base_model = "GLM 4.5 Air"
-capabilities = ["text", "thinking", "thinking_toggle"]
+capabilities = ["text", "thinking"]
 
 [storage_size]
 in_bytes = 229780750336

resources/inference_model_cards/mlx-community--GLM-4.7-4bit.toml

@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
 family = "glm"
 quantization = "4bit"
 base_model = "GLM 4.7"
-capabilities = ["text", "thinking", "thinking_toggle"]
+capabilities = ["text", "thinking"]
 
 [storage_size]
 in_bytes = 198556925568

resources/inference_model_cards/mlx-community--GLM-4.7-6bit.toml

@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
 family = "glm"
 quantization = "6bit"
 base_model = "GLM 4.7"
-capabilities = ["text", "thinking", "thinking_toggle"]
+capabilities = ["text", "thinking"]
 
 [storage_size]
 in_bytes = 286737579648

resources/inference_model_cards/mlx-community--GLM-4.7-8bit-gs32.toml

@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
 family = "glm"
 quantization = "8bit"
 base_model = "GLM 4.7"
-capabilities = ["text", "thinking", "thinking_toggle"]
+capabilities = ["text", "thinking"]
 
 [storage_size]
 in_bytes = 396963397248

resources/inference_model_cards/mlx-community--GLM-4.7-Flash-4bit.toml

@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
 family = "glm"
 quantization = "4bit"
 base_model = "GLM 4.7 Flash"
-capabilities = ["text", "thinking", "thinking_toggle"]
+capabilities = ["text", "thinking"]
 
 [storage_size]
 in_bytes = 19327352832

resources/inference_model_cards/mlx-community--GLM-4.7-Flash-5bit.toml

@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
 family = "glm"
 quantization = "5bit"
 base_model = "GLM 4.7 Flash"
-capabilities = ["text", "thinking", "thinking_toggle"]
+capabilities = ["text", "thinking"]
 
 [storage_size]
 in_bytes = 22548578304

resources/inference_model_cards/mlx-community--GLM-4.7-Flash-6bit.toml

@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
 family = "glm"
 quantization = "6bit"
 base_model = "GLM 4.7 Flash"
-capabilities = ["text", "thinking", "thinking_toggle"]
+capabilities = ["text", "thinking"]
 
 [storage_size]
 in_bytes = 26843545600

resources/inference_model_cards/mlx-community--GLM-4.7-Flash-8bit.toml

@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
 family = "glm"
 quantization = "8bit"
 base_model = "GLM 4.7 Flash"
-capabilities = ["text", "thinking", "thinking_toggle"]
+capabilities = ["text", "thinking"]
 
 [storage_size]
 in_bytes = 34359738368

resources/inference_model_cards/mlx-community--GLM-5-8bit.toml

@@ -1,12 +0,0 @@
-model_id = "mlx-community/GLM-5-8bit-MXFP8"
-n_layers = 78
-hidden_size = 6144
-supports_tensor = true
-tasks = ["TextGeneration"]
-family = "glm"
-quantization = "8bit"
-base_model = "GLM-5"
-capabilities = ["text", "thinking"]
-
-[storage_size]
-in_bytes = 790517400864

resources/inference_model_cards/mlx-community--GLM-5-MXFP4-Q8.toml

@@ -1,12 +0,0 @@
-model_id = "mlx-community/GLM-5-MXFP4-Q8"
-n_layers = 78
-hidden_size = 6144
-supports_tensor = true
-tasks = ["TextGeneration"]
-family = "glm"
-quantization = "MXFP4-Q8"
-base_model = "GLM-5"
-capabilities = ["text", "thinking"]
-
-[storage_size]
-in_bytes = 405478939008

resources/inference_model_cards/mlx-community--GLM-5-bf16.toml

@@ -1,12 +0,0 @@
-model_id = "mlx-community/GLM-5"
-n_layers = 78
-hidden_size = 6144
-supports_tensor = true
-tasks = ["TextGeneration"]
-family = "glm"
-quantization = "bf16"
-base_model = "GLM-5"
-capabilities = ["text", "thinking"]
-
-[storage_size]
-in_bytes = 1487822475264

resources/inference_model_cards/mlx-community--Kimi-K2-Thinking.toml

@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
 family = "kimi"
 quantization = ""
 base_model = "Kimi K2"
-capabilities = ["text", "thinking", "thinking_toggle"]
+capabilities = ["text", "thinking"]
 
 [storage_size]
 in_bytes = 706522120192

resources/inference_model_cards/mlx-community--Kimi-K2.5.toml

@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
 family = "kimi"
 quantization = ""
 base_model = "Kimi K2.5"
-capabilities = ["text", "thinking", "thinking_toggle"]
+capabilities = ["text", "thinking"]
 
 [storage_size]
 in_bytes = 662498705408

resources/inference_model_cards/mlx-community--MiniMax-M2.1-3bit.toml

@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
 family = "minimax"
 quantization = "3bit"
 base_model = "MiniMax M2.1"
-capabilities = ["text", "thinking", "thinking_toggle"]
+capabilities = ["text", "thinking"]
 
 [storage_size]
 in_bytes = 100086644736

resources/inference_model_cards/mlx-community--MiniMax-M2.1-8bit.toml

@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
 family = "minimax"
 quantization = "8bit"
 base_model = "MiniMax M2.1"
-capabilities = ["text", "thinking", "thinking_toggle"]
+capabilities = ["text", "thinking"]
 
 [storage_size]
 in_bytes = 242986745856

resources/inference_model_cards/mlx-community--MiniMax-M2.5-4bit.toml

@@ -1,12 +0,0 @@
-model_id = "mlx-community/MiniMax-M2.5-4bit"
-n_layers = 62
-hidden_size = 3072
-supports_tensor = true
-tasks = ["TextGeneration"]
-family = "minimax"
-quantization = "4bit"
-base_model = "MiniMax M2.5"
-capabilities = ["text", "thinking"]
-
-[storage_size]
-in_bytes = 128666664960

resources/inference_model_cards/mlx-community--MiniMax-M2.5-6bit.toml

@@ -1,12 +0,0 @@
-model_id = "mlx-community/MiniMax-M2.5-6bit"
-n_layers = 62
-hidden_size = 3072
-supports_tensor = true
-tasks = ["TextGeneration"]
-family = "minimax"
-quantization = "6bit"
-base_model = "MiniMax M2.5"
-capabilities = ["text", "thinking"]
-
-[storage_size]
-in_bytes = 185826705408

resources/inference_model_cards/mlx-community--MiniMax-M2.5-8bit.toml

@@ -1,12 +0,0 @@
-model_id = "mlx-community/MiniMax-M2.5-8bit"
-n_layers = 62
-hidden_size = 3072
-supports_tensor = true
-tasks = ["TextGeneration"]
-family = "minimax"
-quantization = "8bit"
-base_model = "MiniMax M2.5"
-capabilities = ["text", "thinking"]
-
-[storage_size]
-in_bytes = 242986745856

resources/inference_model_cards/mlx-community--Qwen3-0.6B-4bit.toml

@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
 family = "qwen"
 quantization = "4bit"
 base_model = "Qwen3 0.6B"
-capabilities = ["text", "thinking", "thinking_toggle"]
+capabilities = ["text", "thinking"]
 
 [storage_size]
 in_bytes = 342884352

resources/inference_model_cards/mlx-community--Qwen3-0.6B-8bit.toml

@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
 family = "qwen"
 quantization = "8bit"
 base_model = "Qwen3 0.6B"
-capabilities = ["text", "thinking", "thinking_toggle"]
+capabilities = ["text", "thinking"]
 
 [storage_size]
 in_bytes = 698351616

resources/inference_model_cards/mlx-community--Qwen3-235B-A22B-Instruct-2507-4bit.toml

@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
 family = "qwen"
 quantization = "4bit"
 base_model = "Qwen3 235B"
-capabilities = ["text", "thinking", "thinking_toggle"]
+capabilities = ["text", "thinking"]
 
 [storage_size]
 in_bytes = 141733920768

resources/inference_model_cards/mlx-community--Qwen3-235B-A22B-Instruct-2507-8bit.toml

@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
 family = "qwen"
 quantization = "8bit"
 base_model = "Qwen3 235B"
-capabilities = ["text", "thinking", "thinking_toggle"]
+capabilities = ["text", "thinking"]
 
 [storage_size]
 in_bytes = 268435456000