implement engine interface for mlx and mflux

## Motivation

The bug-report presigned-URL endpoint
(`https://reports.exolabs.net/presigned-urls`) was injected at build
time from the `EXO_BUG_REPORT_PRESIGNED_URL_ENDPOINT` GitHub Actions
secret into `Info.plist`, then read at runtime by `BugReportService`. It
isn't actually a secret — the POST body is just `{"keys":[...]}` with no
credential (see `app/EXO/EXO/Services/BugReportService.swift:136-142`),
abuse prevention lives server-side on the lambda, and the URL is already
visible in every publicly-distributed DMG's `Info.plist`. Treating it as
a repo secret added plumbing with no security benefit and broke local
dev builds — hitting **Send Bug Report** on an uncustomised `just
build-app` raised "Bug report endpoint is invalid".

## Changes

- `app/EXO/EXO/Info.plist`: replace
`$(EXO_BUG_REPORT_PRESIGNED_URL_ENDPOINT)` with the literal URL.
- `.github/workflows/build-app.yml`: drop the
`EXO_BUG_REPORT_PRESIGNED_URL_ENDPOINT` job-level env var and the
xcodebuild build-setting passthrough. No other workflow changes.

Swift code is unchanged — `BugReportService` still reads from
`Info.plist`, which leaves an escape hatch if anyone ever needs to
override via `xcodebuild EXOBugReportPresignedUrlEndpoint=...` without
recompiling.

Follow-up: the `EXO_BUG_REPORT_PRESIGNED_URL_ENDPOINT` repo secret can
now be deleted in the GitHub Actions settings UI.

## Why It Works

`Info.plist` variable substitution turns `$(FOO)` into whatever build
setting `FOO` resolves to. CI was setting `FOO` via xcodebuild; local
dev wasn't, so the key resolved to an empty string, which
`BugReportService.fetchPresignedUploadUrls` rejects via the
`!trimmedEndpointString.isEmpty` guard at `BugReportService.swift:131`.
Hardcoding the literal string removes the substitution entirely, so
every build — local or CI — gets the right value.

## Test Plan

### Manual Testing
<!-- Hardware: MacBook Pro (macOS app build via Xcode) -->
- `just build-app` with no extra env vars (reproduces the failure path
on `main`).
- `/usr/libexec/PlistBuddy -c "Print :EXOBugReportPresignedUrlEndpoint"
app/EXO/build/Build/Products/Debug/EXO.app/Contents/Info.plist` →
returns `https://reports.exolabs.net/presigned-urls` (was empty before
this change).
- `open app/EXO/build/Build/Products/Debug/EXO.app` → menubar → **Debug
Info** → **Send Bug Report** → type a description → **Send** → upload
succeeds and the **Create GitHub Issue** button appears (was failing
with "Bug report endpoint is invalid" before).
- Cross-check on the Slack side that the uploaded `report.json` lands
under `reports/YYYY/MM/DD/<ts>/` as before.

### Automated Testing
<!-- Describe changes to automated tests, or how existing tests cover
this change -->
- No new tests. This is a single-string change to `Info.plist` plus a
workflow cleanup. `nix flake check` in CI verifies formatting/lint for
the rest of the tree.

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

Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

.cuda_typings/openai_harmony/__init__.pyi

@@ -1,20 +0,0 @@
-from enum import Enum
-
-class HarmonyEncodingName(Enum):
-    HARMONY_GPT_OSS = ...
-
-class HarmonyEncoding: ...
-class HarmonyError(Exception): ...
-
-class Role(Enum):
-    ASSISTANT = ...
-
-class StreamableParser:
-    last_content_delta: str
-    current_channel: str | None
-    current_recipient: str | None
-
-    def __init__(self, encoding: HarmonyEncoding, role: Role = ...) -> None: ...
-    def process(self, token_id: int) -> None: ...
-
-def load_harmony_encoding(name: HarmonyEncodingName) -> HarmonyEncoding: ...

.cuda_typings/pynvml/__init__.pyi

@@ -1,17 +0,0 @@
-class NvmlMemoryInfo:
-    used: int
-    total: int
-    free: int
-
-class NvmlUtilizationRates:
-    gpu: int
-    memory: int
-
-def nvmlInit() -> None: ...
-def nvmlShutdown() -> None: ...
-def nvmlDeviceGetCount() -> int: ...
-def nvmlDeviceGetHandleByIndex(index: int) -> object: ...
-def nvmlDeviceGetUtilizationRates(handle: object) -> NvmlUtilizationRates: ...
-def nvmlDeviceGetTemperature(handle: object, sensor_type: int) -> int: ...
-def nvmlDeviceGetPowerUsage(handle: object) -> int: ...
-def nvmlDeviceGetMemoryInfo(handle: object) -> NvmlMemoryInfo: ...

.cuda_typings/torch/__init__.pyi

@@ -1,61 +0,0 @@
-from typing import Any, Sequence
-
-from torch import backends as backends
-from torch import cuda as cuda
-from torch import distributed as distributed
-
-__version__: str
-
-class version:
-    cuda: str
-
-class dtype: ...
-
-bfloat16: dtype
-float16: dtype
-float32: dtype
-int8: dtype
-int32: dtype
-int64: dtype
-long: dtype
-float8_e4m3fn: dtype
-
-class Tensor:
-    shape: Sequence[int]
-    dtype: dtype
-    def __getitem__(self, key: Any) -> Tensor: ...
-    def __setitem__(self, key: Any, value: Any) -> None: ...
-    def to(self, *args: Any, **kwargs: Any) -> Tensor: ...
-    def cpu(self) -> Tensor: ...
-    def detach(self) -> Tensor: ...
-    def clone(self) -> Tensor: ...
-    def flatten(self, start_dim: int = 0, end_dim: int = -1) -> Tensor: ...
-    def view(self, *shape: Any) -> Tensor: ...
-    def squeeze(self, dim: int = ...) -> Tensor: ...
-    def unsqueeze(self, dim: int) -> Tensor: ...
-    def permute(self, *dims: int) -> Tensor: ...
-    def float(self) -> Tensor: ...
-    def numpy(self) -> Any: ...
-    def numel(self) -> int: ...
-    def nelement(self) -> int: ...
-    @property
-    def is_cuda(self) -> bool: ...
-    @property
-    def device(self) -> device: ...
-    def __len__(self) -> int: ...
-    def data_ptr(self) -> int: ...
-    def tolist(self) -> Any: ...
-    def abs(self) -> Tensor: ...
-    def max(self) -> Tensor: ...
-    def mean(self) -> Tensor: ...
-    def sum(self, dim: int = ...) -> Tensor: ...
-    def item(self) -> float: ...
-
-def tensor(data: Any, dtype: dtype | None = None, device: Any = None) -> Tensor: ...
-def zeros(*size: Any, dtype: dtype | None = None, device: Any = None) -> Tensor: ...
-def empty(*size: Any, dtype: dtype | None = None, device: Any = None) -> Tensor: ...
-def from_numpy(ndarray: Any) -> Tensor: ...
-def inference_mode() -> Any: ...
-
-class device:
-    def __init__(self, type: str, index: int = ...) -> None: ...

.cuda_typings/torch/backends/__init__.pyi

@@ -1 +0,0 @@
-from torch.backends import cuda as cuda

.cuda_typings/torch/backends/cuda/__init__.pyi

@@ -1 +0,0 @@
-def is_built() -> bool: ...

.cuda_typings/torch/cuda/__init__.pyi

@@ -1,10 +0,0 @@
-class _DeviceProperties:
-    total_memory: int
-
-def is_available() -> bool: ...
-def get_device_name(device: int) -> str: ...
-def get_device_properties(device: int) -> _DeviceProperties: ...
-def empty_cache() -> None: ...
-def mem_get_info() -> tuple[int, int]: ...
-def synchronize() -> None: ...
-def max_memory_allocated() -> int: ...

.cuda_typings/torch/distributed/__init__.pyi

@@ -1,2 +0,0 @@
-def is_initialized() -> bool: ...
-def destroy_process_group() -> None: ...

.cuda_typings/vllm/__init__.pyi

@@ -1 +0,0 @@
-__version__: str

.cuda_typings/vllm/config.pyi

@@ -1,2 +0,0 @@
-class ModelConfig:
-    max_model_len: int

.cuda_typings/vllm/engine/arg_utils.pyi

@@ -1,18 +0,0 @@
-from dataclasses import dataclass
-
-@dataclass
-class EngineArgs:
-    model: str = ...
-    served_model_name: str | list[str] | None = ...
-    tokenizer: str | None = ...
-    trust_remote_code: bool = ...
-    dtype: str = ...
-    seed: int = ...
-    max_model_len: int | None = ...
-    gpu_memory_utilization: float = ...
-    enforce_eager: bool = ...
-    tensor_parallel_size: int = ...
-    pipeline_parallel_size: int = ...
-    quantization: str | None = ...
-    load_format: str = ...
-    enable_sleep_mode: bool = ...

.cuda_typings/vllm/outputs.pyi

@@ -1,17 +0,0 @@
-class CompletionOutput:
-    index: int
-    text: str
-    token_ids: list[int]
-    cumulative_logprob: float | None
-    logprobs: object | None
-    finish_reason: str | None
-    stop_reason: int | str | None
-
-    def finished(self) -> bool: ...
-
-class RequestOutput:
-    request_id: str
-    prompt: str | None
-    prompt_token_ids: list[int] | None
-    outputs: list[CompletionOutput]
-    finished: bool

.cuda_typings/vllm/sampling_params.pyi

@@ -1,11 +0,0 @@
-class SamplingParams:
-    n: int
-    temperature: float
-    top_p: float
-    top_k: int
-    min_p: float
-    seed: int | None
-    stop: str | list[str] | None
-    max_tokens: int | None
-    logprobs: int | None
-    repetition_penalty: float

.cuda_typings/vllm/tokenizers/__init__.pyi

@@ -1,3 +0,0 @@
-from vllm.tokenizers.protocol import TokenizerLike
-
-__all__ = ["TokenizerLike"]

.cuda_typings/vllm/tokenizers/protocol.pyi

@@ -1,15 +0,0 @@
-from typing import Protocol
-
-class TokenizerLike(Protocol):
-    @property
-    def eos_token_id(self) -> int: ...
-    @property
-    def vocab_size(self) -> int: ...
-    def encode(self, text: str, add_special_tokens: bool = ...) -> list[int]: ...
-    def decode(self, ids: list[int] | int, skip_special_tokens: bool = ...) -> str: ...
-    def apply_chat_template(
-        self,
-        messages: list[dict[str, str]],
-        tools: list[dict[str, object]] | None = ...,
-        **kwargs: object,
-    ) -> str | list[int]: ...

.cuda_typings/vllm/v1/__init__.pyi

@@ -1 +0,0 @@
-

.cuda_typings/vllm/v1/core/__init__.pyi

@@ -1 +0,0 @@
-

.cuda_typings/vllm/v1/core/kv_cache_manager.pyi

@@ -1,24 +0,0 @@
-from collections.abc import Sequence
-
-from vllm.v1.core.kv_cache_utils import BlockPool, KVCacheBlock
-from vllm.v1.kv_cache_interface import KVCacheConfig
-
-class KVCacheBlocks:
-    blocks: tuple[Sequence[KVCacheBlock], ...]
-    def __init__(self, blocks: tuple[Sequence[KVCacheBlock], ...]) -> None: ...
-    def get_block_ids(self) -> tuple[list[int], ...]: ...
-
-class KVCacheManager:
-    block_pool: BlockPool
-    kv_cache_config: KVCacheConfig
-    enable_caching: bool
-    num_kv_cache_groups: int
-    coordinator: object
-    def __init__(self, *args: object, **kwargs: object) -> None: ...
-    def allocate_slots(
-        self, request: object, num_new_tokens: int, *args: object, **kwargs: object
-    ) -> KVCacheBlocks | None: ...
-    def get_computed_blocks(self, request: object) -> tuple[KVCacheBlocks, int]: ...
-    def create_kv_cache_blocks(
-        self, blocks: tuple[list[KVCacheBlock], ...]
-    ) -> KVCacheBlocks: ...

.cuda_typings/vllm/v1/core/kv_cache_utils.pyi

@@ -1,16 +0,0 @@
-class KVCacheBlock:
-    block_id: int
-    ref_cnt: int
-    def __init__(self, block_id: int) -> None: ...
-
-class FreeKVCacheBlockQueue:
-    def append_n(self, blocks: list[KVCacheBlock]) -> None: ...
-    def popleft_n(self, n: int) -> list[KVCacheBlock]: ...
-
-class BlockPool:
-    blocks: list[KVCacheBlock]
-    free_block_queue: FreeKVCacheBlockQueue
-    num_gpu_blocks: int
-    enable_caching: bool
-    def get_num_free_blocks(self) -> int: ...
-    def get_new_blocks(self, num_blocks: int) -> list[KVCacheBlock]: ...

.cuda_typings/vllm/v1/engine/llm_engine.pyi

@@ -1,22 +0,0 @@
-from vllm.config import ModelConfig
-from vllm.engine.arg_utils import EngineArgs
-from vllm.outputs import RequestOutput
-from vllm.sampling_params import SamplingParams
-from vllm.tokenizers import TokenizerLike
-
-class LLMEngine:
-    tokenizer: TokenizerLike | None
-    model_config: ModelConfig
-
-    @classmethod
-    def from_engine_args(cls, engine_args: EngineArgs) -> LLMEngine: ...
-    def add_request(
-        self,
-        request_id: str,
-        prompt: str,
-        params: SamplingParams,
-        arrival_time: float | None = ...,
-    ) -> None: ...
-    def step(self) -> list[RequestOutput]: ...
-    def has_unfinished_requests(self) -> bool: ...
-    def get_tokenizer(self) -> TokenizerLike: ...

.cuda_typings/vllm/v1/kv_cache_interface.pyi

@@ -1,23 +0,0 @@
-from dataclasses import dataclass
-
-@dataclass
-class KVCacheSpec:
-    block_size: int
-    num_kv_heads: int
-    head_size: int
-
-@dataclass
-class KVCacheGroupSpec:
-    layer_names: list[str]
-    kv_cache_spec: KVCacheSpec
-
-@dataclass
-class KVCacheTensorSpec:
-    shared_by: list[str]
-    size: int
-
-@dataclass
-class KVCacheConfig:
-    num_blocks: int
-    kv_cache_groups: list[KVCacheGroupSpec]
-    kv_cache_tensors: list[KVCacheTensorSpec]

.cuda_typings/vllm/v1/request.pyi

@@ -1,6 +0,0 @@
-class Request:
-    request_id: str
-    prompt_token_ids: list[int] | None
-    num_prompt_tokens: int
-    num_computed_tokens: int
-    num_tokens: int

.cuda_typings/vllm/v1/worker/__init__.pyi

@@ -1 +0,0 @@
-

.cuda_typings/vllm/v1/worker/gpu_model_runner.pyi

@@ -1,24 +0,0 @@
-import torch
-
-class _CompilationConfig:
-    static_forward_context: dict[str, object]
-
-class _ModelConfig:
-    hf_config: object
-
-class GPUModelRunner:
-    kv_caches: list[torch.Tensor]
-    compilation_config: _CompilationConfig
-    model_config: _ModelConfig | None
-    def _allocate_kv_cache_tensors(
-        self, kv_cache_config: object
-    ) -> dict[str, torch.Tensor]: ...
-    def initialize_kv_cache_tensors(
-        self, kv_cache_config: object, kernel_block_sizes: list[int]
-    ) -> dict[str, torch.Tensor]: ...
-    def _reshape_kv_cache_tensors(
-        self,
-        kv_cache_config: object,
-        raw_tensors: dict[str, torch.Tensor],
-        kernel_block_sizes: list[int],
-    ) -> dict[str, torch.Tensor]: ...

.cuda_typings/vllm/v1/worker/gpu_worker.pyi

@@ -1,6 +0,0 @@
-from vllm.v1.worker.gpu_model_runner import GPUModelRunner
-
-class Worker:
-    model_runner: GPUModelRunner
-    def determine_available_memory(self) -> int: ...
-    def initialize_from_config(self, kv_cache_config: object) -> None: ...

.cuda_typings/vllm/v1/worker/utils.pyi

@@ -1 +0,0 @@
-def extract_layer_index(layer_name: str, num_attn_module: int) -> int: ...

.envrc

@@ -1 +1,8 @@
 use flake
+
+# creates .venv if doesn't exist and loads its environment
+export VIRTUAL_ENV=".venv"
+if ! [ -d "./$VIRTUAL_ENV" ]; then
+  uv venv
+fi
+layout python

.github/workflows/build-app.yml

@@ -32,7 +32,6 @@ jobs:
       SPARKLE_ED25519_PRIVATE: ${{ secrets.SPARKLE_ED25519_PRIVATE }}
       SPARKLE_S3_BUCKET: ${{ secrets.SPARKLE_S3_BUCKET }}
       SPARKLE_S3_PREFIX: ${{ secrets.SPARKLE_S3_PREFIX }}
-      EXO_BUG_REPORT_PRESIGNED_URL_ENDPOINT: ${{ secrets.EXO_BUG_REPORT_PRESIGNED_URL_ENDPOINT }}
       AWS_REGION: ${{ secrets.AWS_REGION }}
       EXO_BUILD_NUMBER: ${{ github.run_number }}
       EXO_LIBP2P_NAMESPACE: ${{ github.ref_name }}
@@ -159,7 +158,7 @@ jobs:
           fi
 
       - name: Install Homebrew packages
-        run: brew install just awscli macmon
+        run: brew install just awscli
 
       - name: Install UV
         uses: astral-sh/setup-uv@v6
@@ -239,10 +238,92 @@ jobs:
           # Export keychain path for other steps
           echo "BUILD_KEYCHAIN_PATH=$KEYCHAIN_PATH" >> $GITHUB_ENV
 
+      # ============================================================
+      # Pre-flight credential / profile validation
+      # Runs BEFORE the ~16 min build so auth/expiry failures surface in <1 min.
+      # ============================================================
+
+      - name: Validate Apple notarization credentials
+        env:
+          APPLE_NOTARIZATION_USERNAME: ${{ secrets.APPLE_NOTARIZATION_USERNAME }}
+          APPLE_NOTARIZATION_PASSWORD: ${{ secrets.APPLE_NOTARIZATION_PASSWORD }}
+          APPLE_NOTARIZATION_TEAM: ${{ secrets.APPLE_NOTARIZATION_TEAM }}
+        run: |
+          # All-or-nothing: either all three creds are set, or none are.
+          CRED_COUNT=0
+          for v in "$APPLE_NOTARIZATION_USERNAME" "$APPLE_NOTARIZATION_PASSWORD" "$APPLE_NOTARIZATION_TEAM"; do
+            [[ -n "$v" ]] && CRED_COUNT=$((CRED_COUNT + 1))
+          done
+          if [[ "$CRED_COUNT" -eq 0 ]]; then
+            echo "No notarization credentials configured — skipping notarization for this build."
+            exit 0
+          fi
+          if [[ "$CRED_COUNT" -ne 3 ]]; then
+            echo "ERROR: partial notarization credentials set ($CRED_COUNT/3). Aborting before build."
+            exit 1
+          fi
+          # Cheap, ~5s, auth-only call. Fails instantly with a clear message if
+          # the app-specific password is stale, wrong team-id, etc.
+          echo "Verifying Apple notarization credentials via notarytool history..."
+          if ! xcrun notarytool history \
+            --apple-id "$APPLE_NOTARIZATION_USERNAME" \
+            --password "$APPLE_NOTARIZATION_PASSWORD" \
+            --team-id "$APPLE_NOTARIZATION_TEAM" >/dev/null; then
+            echo "ERROR: notarytool rejected the provided credentials. Fix before rerunning."
+            echo "Common causes: app-specific password expired/revoked, wrong team-id,"
+            echo "Apple ID not on the team, or 2FA not configured for this Apple ID."
+            exit 1
+          fi
+          echo "Apple notarization credentials OK."
+
+      - name: Validate provisioning profile expiry
+        run: |
+          PROFILE="$HOME/Library/Developer/Xcode/UserData/Provisioning Profiles/EXO.provisionprofile"
+          if [[ ! -f "$PROFILE" ]]; then
+            echo "ERROR: provisioning profile not found at $PROFILE"
+            exit 1
+          fi
+          EXPIRY=$(security cms -D -i "$PROFILE" | plutil -extract ExpirationDate raw -o - - 2>/dev/null || true)
+          if [[ -z "$EXPIRY" ]]; then
+            echo "WARNING: could not read ExpirationDate from provisioning profile; skipping expiry check."
+            exit 0
+          fi
+          # Try a couple of known plutil date formats. If none parse, skip the check rather
+          # than risk a false-positive "expired" block on a format we didn't anticipate.
+          EXPIRY_EPOCH=""
+          for fmt in "%Y-%m-%dT%H:%M:%SZ" "%Y-%m-%d %H:%M:%S %z" "%Y-%m-%d %H:%M:%S +0000"; do
+            if parsed=$(date -j -f "$fmt" "$EXPIRY" +%s 2>/dev/null); then
+              EXPIRY_EPOCH="$parsed"
+              break
+            fi
+          done
+          if [[ -z "$EXPIRY_EPOCH" ]]; then
+            echo "WARNING: could not parse ExpirationDate '$EXPIRY'; skipping expiry check."
+            exit 0
+          fi
+          NOW_EPOCH=$(date +%s)
+          if [[ "$EXPIRY_EPOCH" -le "$NOW_EPOCH" ]]; then
+            echo "ERROR: provisioning profile expired on $EXPIRY. Regenerate it before rerunning."
+            exit 1
+          fi
+          DAYS_LEFT=$(( (EXPIRY_EPOCH - NOW_EPOCH) / 86400 ))
+          echo "Provisioning profile valid until $EXPIRY ($DAYS_LEFT days remaining)."
+          if [[ "$DAYS_LEFT" -lt 14 ]]; then
+            echo "WARNING: profile expires in under 14 days — regenerate soon."
+          fi
+
       # ============================================================
       # Build the bundle
       # ============================================================
 
+      - name: Add pinned macmon to PATH
+        run: |
+          MACMON_DIR=$(nix develop --command sh -c 'dirname $(which macmon)')
+          echo "Using macmon from: $MACMON_DIR"
+          echo "$MACMON_DIR" >> $GITHUB_PATH
+          # Remove any Homebrew macmon so PyInstaller can't accidentally pick it up
+          brew uninstall macmon 2>/dev/null || true
+
       - name: Build PyInstaller bundle
         run: uv run pyinstaller packaging/pyinstaller/exo.spec
 
@@ -265,7 +346,6 @@ jobs:
             EXO_BUILD_COMMIT="$GITHUB_SHA" \
             SPARKLE_FEED_URL="$SPARKLE_FEED_URL" \
             SPARKLE_ED25519_PUBLIC="$SPARKLE_ED25519_PUBLIC" \
-            EXO_BUG_REPORT_PRESIGNED_URL_ENDPOINT="$EXO_BUG_REPORT_PRESIGNED_URL_ENDPOINT" \
             CODE_SIGNING_IDENTITY="$SIGNING_IDENTITY" \
             CODE_SIGN_INJECT_BASE_ENTITLEMENTS=YES
           mkdir -p ../../output
@@ -298,11 +378,41 @@ jobs:
           APPLE_NOTARIZATION_PASSWORD: ${{ secrets.APPLE_NOTARIZATION_PASSWORD }}
           APPLE_NOTARIZATION_TEAM: ${{ secrets.APPLE_NOTARIZATION_TEAM }}
         run: |
+          set -o pipefail
           cd output
           security unlock-keychain -p "$MACOS_CERTIFICATE_PASSWORD" "$BUILD_KEYCHAIN_PATH"
           SIGNING_IDENTITY=$(security find-identity -v -p codesigning "$BUILD_KEYCHAIN_PATH" | awk -F '"' '{print $2}')
+
+          # Fail fast if notarization creds are partial. All-or-nothing.
+          CRED_COUNT=0
+          for v in "$APPLE_NOTARIZATION_USERNAME" "$APPLE_NOTARIZATION_PASSWORD" "$APPLE_NOTARIZATION_TEAM"; do
+            [[ -n "$v" ]] && CRED_COUNT=$((CRED_COUNT + 1))
+          done
+          if [[ "$CRED_COUNT" -ne 0 && "$CRED_COUNT" -ne 3 ]]; then
+            echo "ERROR: partial Apple notarization credentials set ($CRED_COUNT/3). Aborting."
+            exit 1
+          fi
+
           /usr/bin/codesign --deep --force --timestamp --options runtime \
             --sign "$SIGNING_IDENTITY" EXO.app
+
+          # Pre-flight: verify the signed app BEFORE building DMG and submitting to Apple.
+          # If this fails, notarization will fail too — cheap way to fail in seconds, not 15 minutes.
+          echo "===== codesign --verify EXO.app ====="
+          if ! /usr/bin/codesign --verify --deep --strict --verbose=2 EXO.app; then
+            echo "ERROR: EXO.app failed codesign verification. Dumping signing status of every executable:"
+            find EXO.app -type f \( -perm -111 -o -name "*.dylib" -o -name "*.so" -o -name "*.framework" \) -print0 |
+              while IFS= read -r -d '' f; do
+                printf -- '--- %s\n' "$f"
+                /usr/bin/codesign -dv --verbose=2 "$f" 2>&1 | sed 's/^/    /' || true
+              done
+            exit 1
+          fi
+
+          # Gatekeeper assessment. A failure here strongly predicts notarization rejection.
+          echo "===== spctl assessment (predicts notarization outcome) ====="
+          /usr/bin/spctl -a -vvv -t install EXO.app || echo "WARNING: spctl assessment failed — notarization is likely to fail too."
+
           mkdir -p dmg-root
           cp -R EXO.app dmg-root/
           ln -s /Applications dmg-root/Applications
@@ -310,12 +420,22 @@ jobs:
           hdiutil create -volname "EXO" -srcfolder dmg-root -ov -format UDZO "$DMG_NAME"
           /usr/bin/codesign --force --timestamp --options runtime \
             --sign "$SIGNING_IDENTITY" "$DMG_NAME"
+
+          echo "===== codesign --verify DMG ====="
+          if ! /usr/bin/codesign --verify --verbose=2 "$DMG_NAME"; then
+            echo "ERROR: DMG failed codesign verification."
+            exit 1
+          fi
+
           if [[ -n "$APPLE_NOTARIZATION_USERNAME" ]]; then
+            echo "===== notarytool submit ====="
+            # `|| true` so set -e doesn't abort before we can echo output / fetch the log.
+            # We rely on the parsed STATUS below to decide pass/fail.
             SUBMISSION_OUTPUT=$(xcrun notarytool submit "$DMG_NAME" \
               --apple-id "$APPLE_NOTARIZATION_USERNAME" \
               --password "$APPLE_NOTARIZATION_PASSWORD" \
               --team-id "$APPLE_NOTARIZATION_TEAM" \
-              --wait --timeout 15m 2>&1)
+              --wait --timeout 15m 2>&1) || true
             echo "$SUBMISSION_OUTPUT"
 
             SUBMISSION_ID=$(echo "$SUBMISSION_OUTPUT" | awk 'tolower($1)=="id:" && $2 ~ /^[0-9a-fA-F-]+$/ {print $2; exit}')

.github/workflows/pipeline.yml

@@ -91,9 +91,6 @@ jobs:
             nix build .#metal-toolchain
           fi
 
-          # Build mlx (depends on metal-toolchain)
-          nix build .#mlx
-
       - name: Build all Nix outputs
         run: |
           nix flake show --json | jq -r '

.gitignore

@@ -38,3 +38,5 @@ bench/**/*.json
 
 # tmp
 tmp/models
+/build/exo
+/.claude/skills

.idea/exo-v2.iml

@@ -1,31 +0,0 @@
-<?xml version="1.0" encoding="UTF-8"?>
-<module type="EMPTY_MODULE" version="4">
-  <component name="FacetManager">
-    <facet type="Python" name="Python facet">
-      <configuration sdkName="Python 3.13 virtualenv at ~/Desktop/exo/.venv" />
-    </facet>
-  </component>
-  <component name="Go" enabled="true" />
-  <component name="NewModuleRootManager">
-    <content url="file://$MODULE_DIR$">
-      <sourceFolder url="file://$MODULE_DIR$/scripts/src" isTestSource="false" />
-      <sourceFolder url="file://$MODULE_DIR$/src" isTestSource="false" />
-      <sourceFolder url="file://$MODULE_DIR$/rust/exo_pyo3_bindings/src" isTestSource="false" />
-      <sourceFolder url="file://$MODULE_DIR$/rust/exo_pyo3_bindings/tests" isTestSource="true" />
-      <sourceFolder url="file://$MODULE_DIR$/rust/util/src" isTestSource="false" />
-      <sourceFolder url="file://$MODULE_DIR$/rust/networking/examples" isTestSource="false" />
-      <sourceFolder url="file://$MODULE_DIR$/rust/networking/src" isTestSource="false" />
-      <sourceFolder url="file://$MODULE_DIR$/rust/networking/tests" isTestSource="true" />
-      <sourceFolder url="file://$MODULE_DIR$/rust/system_custodian/src" isTestSource="false" />
-      <excludeFolder url="file://$MODULE_DIR$/.venv" />
-      <excludeFolder url="file://$MODULE_DIR$/.direnv" />
-      <excludeFolder url="file://$MODULE_DIR$/build" />
-      <excludeFolder url="file://$MODULE_DIR$/dist" />
-      <excludeFolder url="file://$MODULE_DIR$/.go_cache" />
-      <excludeFolder url="file://$MODULE_DIR$/rust/target" />
-    </content>
-    <orderEntry type="jdk" jdkName="Python 3.13 (exo)" jdkType="Python SDK" />
-    <orderEntry type="sourceFolder" forTests="false" />
-    <orderEntry type="library" name="Python 3.13 virtualenv at ~/Desktop/exo/.venv interpreter library" level="application" />
-  </component>
-</module>

.idea/externalDependencies.xml

@@ -1,6 +1,6 @@
 <?xml version="1.0" encoding="UTF-8"?>
 <project version="4">
   <component name="ExternalDependencies">
-    <plugin id="systems.fehn.intellijdirenv" />
+    <plugin id="al.aoli.intellijdirenv" />
   </component>
 </project>

.idea/inspectionProfiles/Project_Default.xml

@@ -1,14 +0,0 @@
-<component name="InspectionProjectProfileManager">
-  <profile version="1.0">
-    <option name="myName" value="Project Default" />
-    <inspection_tool class="PyCompatibilityInspection" enabled="true" level="WARNING" enabled_by_default="true">
-      <option name="ourVersions">
-        <value>
-          <list size="1">
-            <item index="0" class="java.lang.String" itemvalue="3.14" />
-          </list>
-        </value>
-      </option>
-    </inspection_tool>
-  </profile>
-</component>

.idea/misc.xml

@@ -4,7 +4,4 @@
     <option name="sdkName" value="Python 3.13 (exo)" />
   </component>
   <component name="ProjectRootManager" version="2" project-jdk-name="Python 3.13 (exo)" project-jdk-type="Python SDK" />
-  <component name="PythonCompatibilityInspectionAdvertiser">
-    <option name="version" value="3" />
-  </component>
 </project>

.mlx_typings/mflux/callbacks/callback.pyi

@@ -2,11 +2,10 @@
 This type stub file was generated by pyright.
 """
 
-from typing import Protocol
-
 import mlx.core as mx
 import PIL.Image
 import tqdm
+from typing import Protocol
 from mflux.models.common.config.config import Config
 
 class BeforeLoopCallback(Protocol):

.mlx_typings/mflux/callbacks/callback_registry.pyi

@@ -3,7 +3,6 @@ This type stub file was generated by pyright.
 """
 
 from typing import TYPE_CHECKING
-
 from mflux.callbacks.callback import (
     AfterLoopCallback,
     BeforeLoopCallback,

.mlx_typings/mflux/callbacks/generation_context.pyi

@@ -2,11 +2,10 @@
 This type stub file was generated by pyright.
 """
 
-from typing import TYPE_CHECKING
-
 import mlx.core as mx
 import PIL.Image
 import tqdm
+from typing import TYPE_CHECKING
 from mflux.callbacks.callback_registry import CallbackRegistry
 from mflux.models.common.config.config import Config
 

.mlx_typings/mflux/models/common/config/config.pyi

@@ -2,12 +2,11 @@
 This type stub file was generated by pyright.
 """
 
+import mlx.core as mx
 from pathlib import Path
 from typing import Any
-
-import mlx.core as mx
-from mflux.models.common.config.model_config import ModelConfig
 from tqdm import tqdm
+from mflux.models.common.config.model_config import ModelConfig
 
 logger = ...
 

.mlx_typings/mflux/models/common/config/model_config.pyi

@@ -2,11 +2,10 @@
 This type stub file was generated by pyright.
 """
 
+import mlx.core as mx
 from functools import lru_cache
 from typing import Literal
 
-import mlx.core as mx
-
 class ModelConfig:
     precision: mx.Dtype = ...
     def __init__(

.mlx_typings/mflux/models/common/latent_creator/latent_creator.pyi

@@ -2,10 +2,10 @@
 This type stub file was generated by pyright.
 """
 
+import mlx.core as mx
 from pathlib import Path
 from typing import TYPE_CHECKING, TypeAlias
-
-import mlx.core as mx
+from mlx import nn
 from mflux.models.common.vae.tiling_config import TilingConfig
 from mflux.models.fibo.latent_creator.fibo_latent_creator import FiboLatentCreator
 from mflux.models.flux.latent_creator.flux_latent_creator import FluxLatentCreator
@@ -13,7 +13,6 @@ from mflux.models.qwen.latent_creator.qwen_latent_creator import QwenLatentCreat
 from mflux.models.z_image.latent_creator.z_image_latent_creator import (
     ZImageLatentCreator,
 )
-from mlx import nn
 
 if TYPE_CHECKING:
     LatentCreatorType: TypeAlias = type[

.mlx_typings/mflux/models/common/lora/layer/fused_linear_lora_layer.pyi

@@ -2,8 +2,8 @@
 This type stub file was generated by pyright.
 """
 
-from mflux.models.common.lora.layer.linear_lora_layer import LoRALinear
 from mlx import nn
+from mflux.models.common.lora.layer.linear_lora_layer import LoRALinear
 
 class FusedLoRALinear(nn.Module):
     def __init__(

.mlx_typings/mflux/models/common/lora/mapping/lora_loader.pyi

@@ -2,11 +2,10 @@
 This type stub file was generated by pyright.
 """
 
-from collections.abc import Callable
-from dataclasses import dataclass
-
 import mlx.core as mx
 import mlx.nn as nn
+from collections.abc import Callable
+from dataclasses import dataclass
 from mflux.models.common.lora.mapping.lora_mapping import LoRATarget
 
 @dataclass

.mlx_typings/mflux/models/common/lora/mapping/lora_mapping.pyi

@@ -2,12 +2,11 @@
 This type stub file was generated by pyright.
 """
 
+import mlx.core as mx
 from collections.abc import Callable
 from dataclasses import dataclass
 from typing import List, Protocol
 
-import mlx.core as mx
-
 @dataclass
 class LoRATarget:
     model_path: str

.mlx_typings/mflux/models/common/resolution/actions.pyi

@@ -36,3 +36,4 @@ class Rule(NamedTuple):
     name: str
     check: str
     action: QuantizationAction | PathAction | LoraAction | ConfigAction
+    ...

.mlx_typings/mflux/models/common/resolution/config_resolution.pyi

@@ -3,7 +3,6 @@ This type stub file was generated by pyright.
 """
 
 from typing import TYPE_CHECKING
-
 from mflux.models.common.config.model_config import ModelConfig
 
 if TYPE_CHECKING: ...

.mlx_typings/mflux/models/common/schedulers/base_scheduler.pyi

@@ -2,9 +2,8 @@
 This type stub file was generated by pyright.
 """
 
-from abc import ABC, abstractmethod
-
 import mlx.core as mx
+from abc import ABC, abstractmethod
 
 class BaseScheduler(ABC):
     @property

.mlx_typings/mflux/models/common/schedulers/flow_match_euler_discrete_scheduler.pyi

@@ -2,9 +2,8 @@
 This type stub file was generated by pyright.
 """
 
-from typing import TYPE_CHECKING
-
 import mlx.core as mx
+from typing import TYPE_CHECKING
 from mflux.models.common.config.config import Config
 from mflux.models.common.schedulers.base_scheduler import BaseScheduler
 

.mlx_typings/mflux/models/common/schedulers/linear_scheduler.pyi

@@ -2,9 +2,8 @@
 This type stub file was generated by pyright.
 """
 
-from typing import TYPE_CHECKING
-
 import mlx.core as mx
+from typing import TYPE_CHECKING
 from mflux.models.common.config.config import Config
 from mflux.models.common.schedulers.base_scheduler import BaseScheduler
 

.mlx_typings/mflux/models/common/schedulers/seedvr2_euler_scheduler.pyi

@@ -2,9 +2,8 @@
 This type stub file was generated by pyright.
 """
 
-from typing import TYPE_CHECKING
-
 import mlx.core as mx
+from typing import TYPE_CHECKING
 from mflux.models.common.config.config import Config
 from mflux.models.common.schedulers.base_scheduler import BaseScheduler
 

.mlx_typings/mflux/models/common/tokenizer/tokenizer.pyi

@@ -4,10 +4,9 @@ This type stub file was generated by pyright.
 
 from abc import ABC, abstractmethod
 from typing import Protocol, runtime_checkable
-
-from mflux.models.common.tokenizer.tokenizer_output import TokenizerOutput
 from PIL import Image
 from transformers import PreTrainedTokenizer
+from mflux.models.common.tokenizer.tokenizer_output import TokenizerOutput
 
 """
 This type stub file was generated by pyright.

.mlx_typings/mflux/models/common/tokenizer/tokenizer_loader.pyi

@@ -3,7 +3,6 @@ This type stub file was generated by pyright.
 """
 
 from typing import TYPE_CHECKING
-
 from mflux.models.common.tokenizer.tokenizer import BaseTokenizer
 from mflux.models.common.weights.loading.weight_definition import TokenizerDefinition
 

.mlx_typings/mflux/models/common/tokenizer/tokenizer_output.pyi

@@ -2,9 +2,8 @@
 This type stub file was generated by pyright.
 """
 
-from dataclasses import dataclass
-
 import mlx.core as mx
+from dataclasses import dataclass
 
 """
 This type stub file was generated by pyright.

.mlx_typings/mflux/models/common/vae/vae_tiler.pyi

@@ -2,9 +2,8 @@
 This type stub file was generated by pyright.
 """
 
-from typing import Callable
-
 import mlx.core as mx
+from typing import Callable
 
 class VAETiler:
     @staticmethod

.mlx_typings/mflux/models/common/vae/vae_util.pyi

@@ -3,8 +3,8 @@ This type stub file was generated by pyright.
 """
 
 import mlx.core as mx
-from mflux.models.common.vae.tiling_config import TilingConfig
 from mlx import nn
+from mflux.models.common.vae.tiling_config import TilingConfig
 
 class VAEUtil:
     @staticmethod

.mlx_typings/mflux/models/common/weights/loading/weight_applier.pyi

@@ -2,9 +2,8 @@
 This type stub file was generated by pyright.
 """
 
-from typing import TYPE_CHECKING
-
 import mlx.nn as nn
+from typing import TYPE_CHECKING
 from mflux.models.common.weights.loading.loaded_weights import LoadedWeights
 from mflux.models.common.weights.loading.weight_definition import (
     ComponentDefinition,

.mlx_typings/mflux/models/common/weights/loading/weight_definition.pyi

@@ -2,12 +2,11 @@
 This type stub file was generated by pyright.
 """
 
-from dataclasses import dataclass
-from typing import TYPE_CHECKING, Callable, List, TypeAlias
-
 import mlx.core as mx
-from mflux.models.common.tokenizer.tokenizer import BaseTokenizer
+from dataclasses import dataclass
+from typing import Callable, List, TYPE_CHECKING, TypeAlias
 from mflux.models.common.weights.mapping.weight_mapping import WeightTarget
+from mflux.models.common.tokenizer.tokenizer import BaseTokenizer
 from mflux.models.depth_pro.weights.depth_pro_weight_definition import (
     DepthProWeightDefinition,
 )

.mlx_typings/mflux/models/common/weights/loading/weight_loader.pyi

@@ -3,7 +3,6 @@ This type stub file was generated by pyright.
 """
 
 from typing import TYPE_CHECKING
-
 from mflux.models.common.weights.loading.loaded_weights import LoadedWeights
 from mflux.models.common.weights.loading.weight_definition import (
     ComponentDefinition,

.mlx_typings/mflux/models/common/weights/mapping/weight_mapper.pyi

@@ -2,9 +2,8 @@
 This type stub file was generated by pyright.
 """
 
-from typing import Dict, List, Optional
-
 import mlx.core as mx
+from typing import Dict, List, Optional
 from mflux.models.common.weights.mapping.weight_mapping import WeightTarget
 
 class WeightMapper:

.mlx_typings/mflux/models/common/weights/mapping/weight_mapping.pyi

@@ -2,11 +2,10 @@
 This type stub file was generated by pyright.
 """
 
+import mlx.core as mx
 from dataclasses import dataclass
 from typing import Callable, List, Optional, Protocol
 
-import mlx.core as mx
-
 """
 This type stub file was generated by pyright.
 """

.mlx_typings/mflux/models/common/weights/saving/model_saver.pyi

@@ -2,8 +2,7 @@
 This type stub file was generated by pyright.
 """
 
-from typing import TYPE_CHECKING, Any
-
+from typing import Any, TYPE_CHECKING
 from mflux.models.common.weights.loading.weight_definition import WeightDefinitionType
 
 if TYPE_CHECKING: ...

.mlx_typings/mflux/models/depth_pro/model/depth_pro.pyi

@@ -2,10 +2,9 @@
 This type stub file was generated by pyright.
 """
 
+import mlx.core as mx
 from dataclasses import dataclass
 from pathlib import Path
-
-import mlx.core as mx
 from PIL import Image
 
 @dataclass
@@ -14,6 +13,7 @@ class DepthResult:
     depth_array: mx.array
     min_depth: float
     max_depth: float
+    ...
 
 class DepthPro:
     def __init__(self, quantize: int | None = ...) -> None: ...