testing macmon

.github/workflows/build-app.yml

@@ -32,6 +32,7 @@ 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 }}
@@ -158,7 +159,7 @@ jobs:
           fi
 
       - name: Install Homebrew packages
-        run: brew install just awscli
+        run: brew install just awscli macmon
 
       - name: Install UV
         uses: astral-sh/setup-uv@v6
@@ -238,92 +239,10 @@ 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
 
@@ -346,6 +265,7 @@ 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
@@ -378,41 +298,11 @@ 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
@@ -420,22 +310,12 @@ 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) || true
+              --wait --timeout 15m 2>&1)
             echo "$SUBMISSION_OUTPUT"
 
             SUBMISSION_ID=$(echo "$SUBMISSION_OUTPUT" | awk 'tolower($1)=="id:" && $2 ~ /^[0-9a-fA-F-]+$/ {print $2; exit}')
@@ -516,7 +396,7 @@ jobs:
           path: output/EXO-${{ env.RELEASE_VERSION }}.dmg
 
       - name: Upload to S3
-        if: env.SPARKLE_S3_BUCKET != ''
+        if: env.SPARKLE_S3_BUCKET != '' && github.ref_type == 'tag'
         env:
           AWS_ACCESS_KEY_ID: ${{ secrets.AWS_ACCESS_KEY_ID }}
           AWS_SECRET_ACCESS_KEY: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
@@ -532,12 +412,6 @@ jobs:
             PREFIX="${PREFIX}/"
           fi
           DMG_NAME="EXO-${RELEASE_VERSION}.dmg"
-
-          if [[ "${{ github.ref_type }}" != "tag" ]]; then
-            aws s3 cp "$DMG_NAME" "s3://${SPARKLE_S3_BUCKET}/${PREFIX}EXO-${GITHUB_SHA}.dmg"
-            exit 0
-          fi
-
           aws s3 cp "$DMG_NAME" "s3://${SPARKLE_S3_BUCKET}/${PREFIX}${DMG_NAME}"
           if [[ "$IS_ALPHA" != "true" ]]; then
             aws s3 cp "$DMG_NAME" "s3://${SPARKLE_S3_BUCKET}/${PREFIX}EXO-latest.dmg"

.github/workflows/pipeline.yml

@@ -8,6 +8,33 @@ on:
       - main
 
 jobs:
+  typecheck:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+        with:
+          lfs: false
+
+      - uses: cachix/install-nix-action@v31
+        with:
+          nix_path: nixpkgs=channel:nixos-unstable
+
+      - uses: cachix/cachix-action@v14
+        name: Configure Cachix
+        with:
+          name: exo
+          authToken: "${{ secrets.CACHIX_AUTH_TOKEN }}"
+
+      - name: Load nix develop environment
+        run: nix run github:nicknovitski/nix-develop/v1
+
+      - name: Sync dependencies
+        run: uv sync --all-packages
+
+      - name: Run type checker
+        run: uv run basedpyright --project pyproject.toml
+
   nix:
     name: Build and check (${{ matrix.system }})
     runs-on: ${{ matrix.runner }}
@@ -91,6 +118,9 @@ 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 '
@@ -112,6 +142,140 @@ jobs:
           # Run pytest outside sandbox (needs GPU access for MLX)
           export HOME="$RUNNER_TEMP"
           export EXO_TESTS=1
-          export EXO_DASHBOARD_DIR="$PWD/dashboard/" 
-          export EXO_RESOURCES_DIR="$PWD/resources" 
-          $TEST_ENV/bin/python -m pytest src -m "not slow" --import-mode=importlib
+          EXO_RESOURCES_DIR="$PWD/resources" $TEST_ENV/bin/python -m pytest src -m "not slow" --import-mode=importlib
+
+  dashboard-tests:
+    name: Dashboard E2E Tests
+    runs-on: macos-26
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+        with:
+          lfs: false
+
+      - uses: cachix/install-nix-action@v31
+        with:
+          nix_path: nixpkgs=channel:nixos-unstable
+
+      - uses: cachix/cachix-action@v14
+        name: Configure Cachix
+        with:
+          name: exo
+          authToken: "${{ secrets.CACHIX_AUTH_TOKEN }}"
+
+      - name: Build Metal packages
+        run: |
+          if nix build .#metal-toolchain 2>/dev/null; then
+            echo "metal-toolchain built successfully (likely cache hit)"
+          else
+            echo "metal-toolchain build failed, extracting from Xcode..."
+
+            NAR_HASH="sha256-ayR5mXN4sZAddwKEG2OszGRF93k9ZFc7H0yi2xbylQw="
+            NAR_NAME="metal-toolchain-17C48.nar"
+
+            WORK_DIR="${RUNNER_TEMP}/metal-work"
+            mkdir -p "$WORK_DIR"
+
+            xcodebuild -downloadComponent MetalToolchain
+
+            DMG_PATH=$(find /System/Library/AssetsV2/com_apple_MobileAsset_MetalToolchain -name '*.dmg' 2>/dev/null | head -1)
+            if [ -z "$DMG_PATH" ]; then
+              echo "Error: Could not find Metal toolchain DMG"
+              exit 1
+            fi
+
+            echo "Found DMG at: $DMG_PATH"
+            hdiutil attach "$DMG_PATH" -mountpoint "${WORK_DIR}/metal-dmg"
+
+            cp -R "${WORK_DIR}/metal-dmg/Metal.xctoolchain" "${WORK_DIR}/metal-export"
+            hdiutil detach "${WORK_DIR}/metal-dmg"
+
+            nix nar pack "${WORK_DIR}/metal-export" > "${WORK_DIR}/${NAR_NAME}"
+            STORE_PATH=$(nix store add --mode flat "${WORK_DIR}/${NAR_NAME}")
+            echo "Added NAR to store: $STORE_PATH"
+
+            rm -rf "$WORK_DIR"
+
+            nix build .#metal-toolchain
+          fi
+
+          nix build .#mlx
+
+      - name: Install macmon for hardware monitoring
+        run: brew install macmon
+
+      - name: Load nix develop environment
+        run: nix run github:nicknovitski/nix-develop/v1
+
+      - name: Sync Python dependencies
+        run: uv sync --all-packages
+
+      - name: Setup Node.js
+        uses: actions/setup-node@v4
+        with:
+          node-version: '20'
+          cache: 'npm'
+          cache-dependency-path: dashboard/package-lock.json
+
+      - name: Install dashboard dependencies
+        working-directory: dashboard
+        run: npm ci
+
+      - name: Install Playwright browsers
+        working-directory: dashboard
+        run: npx playwright install chromium --with-deps
+
+      - name: Build dashboard
+        working-directory: dashboard
+        run: npm run build
+
+      - name: Verify macmon is accessible
+        run: |
+          echo "PATH: $PATH"
+          which macmon || echo "macmon not in PATH"
+          macmon --version
+          # Test macmon actually works - capture stderr too
+          echo "Testing macmon pipe output (with stderr)..."
+          timeout 5 macmon pipe --interval 1000 2>&1 || echo "macmon pipe exit code: $?"
+          # Try running macmon raw (not pipe mode)
+          echo "Testing macmon raw output..."
+          macmon raw 2>&1 | head -5 || echo "macmon raw failed"
+
+      - name: Verify Python can find macmon
+        run: |
+          echo "Testing shutil.which from uv run python..."
+          uv run python -c "import shutil; print('Python shutil.which macmon:', shutil.which('macmon'))"
+
+      - name: Run Playwright tests
+        working-directory: dashboard
+        run: |
+          export PATH="/usr/sbin:/usr/bin:/opt/homebrew/bin:$PATH"
+          echo "Effective PATH: $PATH"
+          which macmon && echo "macmon found at $(which macmon)"
+          npm test
+        env:
+          CI: true
+
+      - name: Upload test results
+        uses: actions/upload-artifact@v4
+        if: always()
+        with:
+          name: playwright-report
+          path: dashboard/playwright-report/
+          retention-days: 30
+
+      - name: Upload video recordings
+        uses: actions/upload-artifact@v4
+        if: always()
+        with:
+          name: test-videos
+          path: dashboard/test-results/
+          retention-days: 30
+
+      - name: Upload snapshot diffs
+        uses: actions/upload-artifact@v4
+        if: failure()
+        with:
+          name: snapshot-diffs
+          path: dashboard/tests/**/*-snapshots/*-diff.png
+          retention-days: 30

.gitignore

@@ -29,14 +29,12 @@ dashboard/build/
 dashboard/node_modules/
 dashboard/.svelte-kit/
 
+# playwright
+dashboard/test-results/
+dashboard/playwright-report/
+dashboard/playwright/.cache/
+dashboard/tests/**/*-snapshots/*-actual.png
+dashboard/tests/**/*-snapshots/*-diff.png
+
 # host config snapshots
 hosts_*.json
-.swp
-
-# bench files
-bench/**/*.json
-
-# tmp
-tmp/models
-/build/exo
-/.claude/skills

.idea/exo-v2.iml

@@ -0,0 +1,31 @@
+<?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="al.aoli.intellijdirenv" />
+    <plugin id="systems.fehn.intellijdirenv" />
   </component>
 </project>

.idea/inspectionProfiles/Project_Default.xml

@@ -0,0 +1,14 @@
+<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

@@ -4,4 +4,7 @@
     <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/models/flux/variants/kontext/__init__.pyi

@@ -1,7 +0,0 @@
-"""
-This type stub file was generated by pyright.
-"""
-
-from mflux.models.flux.variants.kontext.flux_kontext import Flux1Kontext
-
-__all__ = ["Flux1Kontext"]

.mlx_typings/mflux/models/flux/variants/kontext/flux_kontext.pyi

@@ -1,49 +0,0 @@
-"""
-This type stub file was generated by pyright.
-"""
-
-from pathlib import Path
-from typing import Any
-
-from mlx import nn
-
-from mflux.models.common.config.model_config import ModelConfig
-from mflux.models.flux.model.flux_text_encoder.clip_encoder.clip_encoder import (
-    CLIPEncoder,
-)
-from mflux.models.flux.model.flux_text_encoder.t5_encoder.t5_encoder import T5Encoder
-from mflux.models.flux.model.flux_transformer.transformer import Transformer
-from mflux.models.flux.model.flux_vae.vae import VAE
-from mflux.utils.generated_image import GeneratedImage
-
-class Flux1Kontext(nn.Module):
-    vae: VAE
-    transformer: Transformer
-    t5_text_encoder: T5Encoder
-    clip_text_encoder: CLIPEncoder
-    bits: int | None
-    lora_paths: list[str] | None
-    lora_scales: list[float] | None
-    prompt_cache: dict[str, Any]
-    tokenizers: dict[str, Any]
-
-    def __init__(
-        self,
-        quantize: int | None = ...,
-        model_path: str | None = ...,
-        lora_paths: list[str] | None = ...,
-        lora_scales: list[float] | None = ...,
-        model_config: ModelConfig = ...,
-    ) -> None: ...
-    def generate_image(
-        self,
-        seed: int,
-        prompt: str,
-        num_inference_steps: int = ...,
-        height: int = ...,
-        width: int = ...,
-        guidance: float = ...,
-        image_path: Path | str | None = ...,
-        image_strength: float | None = ...,
-        scheduler: str = ...,
-    ) -> GeneratedImage: ...

.mlx_typings/mflux/models/flux/variants/kontext/kontext_util.pyi

@@ -1,16 +0,0 @@
-"""
-This type stub file was generated by pyright.
-"""
-
-import mlx.core as mx
-
-from mflux.models.flux.model.flux_vae.vae import VAE
-
-class KontextUtil:
-    @staticmethod
-    def create_image_conditioning_latents(
-        vae: VAE,
-        height: int,
-        width: int,
-        image_path: str,
-    ) -> tuple[mx.array, mx.array]: ...

.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.
@@ -1155,7 +1139,7 @@ class array:
     ) -> array:
         """See :func:`flatten`."""
 
-    def reshape(self, *shape: int, stream: Stream | Device | None = ...) -> array:
+    def reshape(self, *shape, stream: Stream | Device | None = ...) -> array:
         """
         Equivalent to :func:`reshape` but the shape can be passed either as a
         :obj:`tuple` or as separate arguments.
@@ -1238,7 +1222,7 @@ class array:
     ) -> array:
         """See :func:`swapaxes`."""
 
-    def transpose(self, *axes: int, stream: Stream | Device | None = ...) -> array:
+    def transpose(self, *axes, stream: Stream | Device | None = ...) -> array:
         """
         Equivalent to :func:`transpose` but the axes can be passed either as
         a tuple or as separate arguments.
@@ -1767,12 +1751,12 @@ def clip(
         array: The clipped array.
     """
 
-def compile[F: Callable[..., object]](
-    fun: F,
+def compile(
+    fun: Callable,
     inputs: object | None = ...,
     outputs: object | None = ...,
     shapeless: bool = ...,
-) -> F:
+) -> Callable:
     """
     Returns a compiled function which produces the same output as ``fun``.
 
@@ -2382,7 +2366,7 @@ class custom_function:
 def default_device() -> Device:
     """Get the default device."""
 
-def default_stream(device: Device | DeviceType) -> Stream:
+def default_stream(device: Device) -> Stream:
     """Get the device's default stream."""
 
 def degrees(a: array, /, *, stream: Stream | Device | None = ...) -> array:
@@ -2396,7 +2380,7 @@ def degrees(a: array, /, *, stream: Stream | Device | None = ...) -> array:
         array: The angles in degrees.
     """
 
-def depends[T](inputs: T, dependencies: array | Sequence[array]) -> T:
+def depends(inputs: array | Sequence[array], dependencies: array | Sequence[array]):
     """
     Insert dependencies between arrays in the graph. The outputs are
     identical to ``inputs`` but with dependencies on ``dependencies``.
@@ -2915,8 +2899,8 @@ def gather_mm(
     a: array,
     b: array,
     /,
-    lhs_indices: array | None = ...,
-    rhs_indices: array | None = ...,
+    lhs_indices: array,
+    rhs_indices: array,
     *,
     sorted_indices: bool = ...,
     stream: Stream | Device | None = ...,
@@ -4707,7 +4691,6 @@ def softmax(
     /,
     axis: int | Sequence[int] | None = ...,
     *,
-    precise: bool = ...,
     stream: Stream | Device | None = ...,
 ) -> array:
     """

.mlx_typings/mlx/nn/__init__.pyi

@@ -1,5 +1,9 @@
-from .layers import *
-from .utils import *
+"""
+This type stub file was generated by pyright.
+"""
+
+from layers import *
+from utils import *
 
 from . import init as init
 from . import losses as losses

.mlx_typings/mlx/nn/layers/__init__.pyi

@@ -1,16 +1,20 @@
-from .activations import *
-from .base import *
-from .containers import *
-from .convolution import *
-from .convolution_transpose import *
-from .distributed import *
-from .dropout import *
-from .embedding import *
-from .linear import *
-from .normalization import *
-from .pooling import *
-from .positional_encoding import *
-from .quantized import *
-from .recurrent import *
-from .transformer import *
-from .upsample import *
+"""
+This type stub file was generated by pyright.
+"""
+
+from activations import *
+from base import *
+from containers import *
+from convolution import *
+from convolution_transpose import *
+from distributed import *
+from dropout import *
+from embedding import *
+from linear import *
+from normalization import *
+from pooling import *
+from positional_encoding import *
+from quantized import *
+from recurrent import *
+from transformer import *
+from upsample import *

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

@@ -53,14 +53,10 @@ class Module(dict):
         mx.eval(model.parameters())
     """
 
-    def __call__(self, *args: Any, **kwargs: Any) -> mx.array: ...
+    __call__: Callable
     def __init__(self) -> None:
         """Should be called by the subclasses of ``Module``."""
 
-    def __getitem__(self, key: str) -> mx.array | Module: ...
-    def get(
-        self, key: str, default: mx.array | Module | None = ...
-    ) -> mx.array | Module | None: ...
     @property
     def training(self):  # -> bool:
         """Boolean indicating if the model is in training mode."""
@@ -204,7 +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/nn/layers/convolution.pyi

@@ -30,10 +30,6 @@ class Conv1d(Module):
         bias (bool, optional): If ``True`` add a learnable bias to the output.
             Default: ``True``
     """
-
-    weight: mx.array
-    bias: mx.array | None
-    groups: int
     def __init__(
         self,
         in_channels: int,

.mlx_typings/mlx/nn/layers/linear.pyi

@@ -40,10 +40,6 @@ class Linear(Module):
         bias (bool, optional): If set to ``False`` then the layer will
           not use a bias. Default is ``True``.
     """
-
-    weight: mx.array
-    bias: mx.array | None
-
     def __init__(self, input_dims: int, output_dims: int, bias: bool = ...) -> None: ...
     def __call__(self, x: mx.array) -> mx.array: ...
     def to_quantized(

.mlx_typings/mlx/nn/layers/normalization.pyi

@@ -88,9 +88,6 @@ class RMSNorm(Module):
         dims (int): The feature dimension of the input to normalize over
         eps (float): A small additive constant for numerical stability
     """
-
-    weight: mx.array
-
     def __init__(self, dims: int, eps: float = ...) -> None: ...
     def __call__(self, x) -> mx.array: ...
 

.mlx_typings/mlx/nn/layers/quantized.pyi

@@ -2,7 +2,7 @@
 This type stub file was generated by pyright.
 """
 
-from typing import Any, Callable, Optional, Union
+from typing import Callable, Optional, Union
 
 import mlx.core as mx
 from base import Module
@@ -13,10 +13,8 @@ def quantize(
     bits: int = ...,
     *,
     mode: str = ...,
-    class_predicate: Optional[
-        Callable[[str, Module], Union[bool, dict[str, Any]]]
-    ] = ...,
-) -> None:
+    class_predicate: Optional[Callable[[str, Module], Union[bool, dict]]] = ...,
+):  # -> None:
     """Quantize the sub-modules of a module according to a predicate.
 
     By default all layers that define a ``to_quantized(group_size, bits)``

.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/_version.pyi

@@ -1,5 +0,0 @@
-"""
-This type stub file was generated by pyright.
-"""
-
-__version__ = ...

.mlx_typings/mlx_lm/generate.pyi

@@ -3,12 +3,13 @@ This type stub file was generated by pyright.
 """
 
 import contextlib
+from dataclasses import dataclass
+from typing import Any, Callable, Generator, List, Optional, Tuple, Union
+
 import mlx.core as mx
 import mlx.nn as nn
-from dataclasses import dataclass
-from collections import deque
-from typing import Any, Callable, Generator, List, Optional, Sequence, Tuple, Union
 from transformers import PreTrainedTokenizer
+
 from .tokenizer_utils import TokenizerWrapper
 
 DEFAULT_PROMPT = ...
@@ -28,9 +29,8 @@ def str2bool(string):  # -> bool:
     ...
 def setup_arg_parser():  # -> ArgumentParser:
     """Set up and return the argument parser."""
-    ...
 
-generation_stream: mx.Stream
+generation_stream = ...
 
 @contextlib.contextmanager
 def wired_limit(
@@ -43,7 +43,6 @@ def wired_limit(
     async eval could be running pass in the streams to synchronize with prior
     to exiting the context manager.
     """
-    ...
 @dataclass
 class GenerationResponse:
     """
@@ -74,11 +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,
@@ -92,7 +89,7 @@ def generate_step(
     kv_bits: Optional[int] = ...,
     kv_group_size: int = ...,
     quantized_kv_start: int = ...,
-    prompt_progress_callback: Optional[Callable[[int, int], None]] = ...,
+    prompt_progress_callback: Optional[Callable[[int], int]] = ...,
     input_embeddings: Optional[mx.array] = ...,
 ) -> Generator[Tuple[mx.array, mx.array], None, None]:
     """
@@ -118,7 +115,7 @@ def generate_step(
         kv_group_size (int): Group size for KV cache quantization. Default: ``64``.
         quantized_kv_start (int): Step to begin using a quantized KV cache.
            when ``kv_bits`` is non-None. Default: ``0``.
-        prompt_progress_callback (Callable[[int, int], None]): A call-back which takes the
+        prompt_progress_callback (Callable[[int], int]): A call-back which takes the
            prompt tokens processed so far and the total number of prompt tokens.
         input_embeddings (mx.array, optional): Input embeddings to use instead of or in
           conjunction with prompt tokens. Default: ``None``.
@@ -126,7 +123,6 @@ def generate_step(
     Yields:
         Tuple[mx.array, mx.array]: One token and a vector of log probabilities.
     """
-    ...
 
 def speculative_generate_step(
     prompt: mx.array,
@@ -172,7 +168,6 @@ def speculative_generate_step(
         Tuple[mx.array, mx.array, bool]: One token, a vector of log probabilities,
           and a bool indicating if the token was generated by the draft model
     """
-    ...
 
 def stream_generate(
     model: nn.Module,
@@ -180,7 +175,7 @@ def stream_generate(
     prompt: Union[str, mx.array, List[int]],
     max_tokens: int = ...,
     draft_model: Optional[nn.Module] = ...,
-    **kwargs: Any,
+    **kwargs: object,
 ) -> Generator[GenerationResponse, None, None]:
     """
     A generator producing text based on the given prompt from the model.
@@ -202,7 +197,6 @@ def stream_generate(
         GenerationResponse: An instance containing the generated text segment and
             associated metadata. See :class:`GenerationResponse` for details.
     """
-    ...
 
 def generate(
     model: nn.Module,
@@ -223,9 +217,6 @@ def generate(
        kwargs: The remaining options get passed to :func:`stream_generate`.
           See :func:`stream_generate` for more details.
     """
-    ...
-
-def _merge_caches(caches: List[List[Any]]) -> List[Any]: ...
 @dataclass
 class BatchStats:
     """
@@ -249,263 +240,10 @@ class BatchStats:
     generation_time: float = ...
     peak_memory: float = ...
 
-class SequenceStateMachine:
-    """A state machine that uses one Aho-Corasick trie per state to efficiently
-    track state across a generated sequence.
-
-    The transitions are provided as state -> [(sequence, new_state)].
-
-    Example:
-
-        sm = SequenceStateMachine(
-            transitions={
-                "normal": [
-                    (think_start_tokens, "reasoning"),
-                    (tool_start_tokens, "tool"),
-                    (eos, None),
-                ],
-                "reasoning": [
-                    (think_end_tokens, "normal"),
-                    (eos, None),
-                ],
-                "tool": [
-                    (tool_end_tokens, None),
-                    (eos, None)
-                ],
-            },
-            initial="normal"
-        )
-    """
-    def __init__(self, transitions=..., initial=...) -> None: ...
-    def __deepcopy__(self, memo):  # -> SequenceStateMachine:
-        ...
-    def make_state(self):  # -> tuple[str, Any, dict[Any, Any]]:
-        ...
-    @staticmethod
-    def match(state, x):  # -> tuple[tuple[Any, Any | None, Any], Any | None, Any]:
-        ...
-
-class PromptProcessingBatch:
-    """
-    A batch processor for prompt tokens with support for incremental processing.
-
-    This class handles batched prompt processing, managing KV caches and preparing
-    tokens for generation. It supports extending, filtering, and splitting batches.
-    """
-    @dataclass
-    class Response:
-        uid: int
-        progress: tuple
-        end_of_segment: bool
-        end_of_prompt: bool
-        ...
-
-    def __init__(
-        self,
-        model: nn.Module,
-        uids: List[int],
-        caches: List[List[Any]],
-        tokens: Optional[List[List[int]]] = ...,
-        prefill_step_size: int = ...,
-        samplers: Optional[List[Callable[[mx.array], mx.array]]] = ...,
-        fallback_sampler: Optional[Callable[[mx.array], mx.array]] = ...,
-        logits_processors: Optional[
-            List[List[Callable[[mx.array, mx.array], mx.array]]]
-        ] = ...,
-        state_machines: Optional[List[SequenceStateMachine]] = ...,
-        max_tokens: Optional[List[int]] = ...,
-    ) -> None: ...
-    def __len__(self):  # -> int:
-        ...
-    def extract_cache(self, idx: int) -> List[Any]: ...
-    def extend(self, batch):  # -> None:
-        ...
-    def split(self, indices: List[int]):  # -> Self:
-        ...
-    def filter(self, keep: List[int]):  # -> None:
-        ...
-    def prompt(self, tokens: List[List[int]]):  # -> None:
-        """
-        Process prompt tokens through the model.
-
-        Args:
-            tokens: List of token sequences to process.
-        """
-        ...
-
-    def generate(self, tokens: List[List[int]]):  # -> GenerationBatch:
-        """
-        Transition from prompt processing to generation.
-
-        Args:
-            tokens: Final tokens for each sequence to start generation.
-
-        Returns:
-            A GenerationBatch ready for token generation.
-        """
-        ...
-
-    @classmethod
-    def empty(
-        cls,
-        model: nn.Module,
-        fallback_sampler: Callable[[mx.array], mx.array],
-        prefill_step_size: int = ...,
-    ):  # -> Self:
-        ...
-
-class GenerationBatch:
-    """
-    A batched token generator that manages multiple sequences in parallel.
-
-    This class handles the generation phase after prompt processing, managing
-    KV caches, sampling, and stop sequence detection for multiple sequences.
-    """
-    @dataclass
-    class Response:
-        uid: int
-        token: int
-        logprobs: mx.array
-        finish_reason: Optional[str]
-        current_state: Optional[str]
-        match_sequence: Optional[List[int]]
-        prompt_cache: Optional[List[Any]]
-        all_tokens: Optional[List[int]]
-        ...
-
-    model: nn.Module
-    uids: List[int]
-    prompt_cache: List[Any]
-    tokens: List[List[int]]
-    samplers: Optional[List[Callable[[mx.array], mx.array]]]
-    fallback_sampler: Callable[[mx.array], mx.array]
-    logits_processors: Optional[List[List[Callable[[mx.array, mx.array], mx.array]]]]
-    state_machines: List[SequenceStateMachine]
-    max_tokens: List[int]
-    _current_tokens: Optional[mx.array]
-    _current_logprobs: mx.array | List[mx.array]
-    _next_tokens: Optional[mx.array]
-    _next_logprobs: mx.array | List[mx.array]
-    _token_context: List[Any]
-    _num_tokens: List[int]
-    _matcher_states: List[Any]
-
-    def __init__(
-        self,
-        model: nn.Module,
-        uids: List[int],
-        inputs: mx.array,
-        prompt_cache: List[Any],
-        tokens: List[List[int]],
-        samplers: Optional[List[Callable[[mx.array], mx.array]]],
-        fallback_sampler: Callable[[mx.array], mx.array],
-        logits_processors: Optional[
-            List[List[Callable[[mx.array, mx.array], mx.array]]]
-        ],
-        state_machines: List[SequenceStateMachine],
-        max_tokens: List[int],
-    ) -> None: ...
-    def __len__(self) -> int: ...
-    def extend(self, batch: GenerationBatch) -> None: ...
-    def extract_cache(self, idx: int) -> List[Any]: ...
-    def filter(self, keep: List[int]) -> None: ...
-    def _step(self) -> Tuple[List[int], List[mx.array]]: ...
-    def next(self) -> List[Response]:
-        """
-        Generate the next batch of tokens.
-
-        Returns:
-            List of Response objects for each sequence in the batch.
-        """
-        ...
-
-    @classmethod
-    def empty(
-        cls, model: nn.Module, fallback_sampler: Callable[[mx.array], mx.array]
-    ):  # -> Self:
-        ...
-
-class BatchGenerator:
-    """
-    A batch generator implements continuous batching.
-
-    This class provides automatic management of prompt processing and generation
-    batches, handling the transition between the two.
-
-    It also allows for segmented prompt processing which guarantees that the
-    generator will stop at these boundaries when processing an input.
-    """
-    def __init__(
-        self,
-        model: nn.Module,
-        max_tokens: int = ...,
-        stop_tokens: Optional[Sequence[Sequence[int]]] = ...,
-        sampler: Optional[Callable[[mx.array], mx.array]] = ...,
-        logits_processors: Optional[
-            List[Callable[[mx.array, mx.array], mx.array]]
-        ] = ...,
-        completion_batch_size: int = ...,
-        prefill_batch_size: int = ...,
-        prefill_step_size: int = ...,
-    ) -> None: ...
-    def close(self) -> None: ...
-    def __del__(self):  # -> None:
-        ...
-    @contextlib.contextmanager
-    def stats(self, stats=...):  # -> Generator[Any | BatchStats, Any, None]:
-        ...
-    _unprocessed_sequences: deque[tuple[Any, ...]]
-    _prompt_batch: PromptProcessingBatch
-    _generation_batch: GenerationBatch
-    _currently_processing: list[Any]
-    _gen_tokens_counter: int
-    _steps_counter: int
-    def _next(
-        self,
-    ) -> tuple[
-        List[PromptProcessingBatch.Response], List[GenerationBatch.Response]
-    ]: ...
-    def insert(
-        self,
-        prompts: List[List[int]],
-        max_tokens: Optional[List[int]] = ...,
-        caches: Optional[List[List[Any]]] = ...,
-        all_tokens: Optional[List[List[int]]] = ...,
-        samplers: Optional[List[Callable[[mx.array], mx.array]]] = ...,
-        logits_processors: Optional[
-            List[List[Callable[[mx.array, mx.array], mx.array]]]
-        ] = ...,
-        state_machines: Optional[List[SequenceStateMachine]] = ...,
-    ) -> List[int]: ...
-    def insert_segments(
-        self,
-        segments: List[List[List[int]]],
-        max_tokens: Optional[List[int]] = ...,
-        caches: Optional[List[List[Any]]] = ...,
-        all_tokens: Optional[List[List[int]]] = ...,
-        samplers: Optional[List[Callable[[mx.array], mx.array]]] = ...,
-        logits_processors: Optional[
-            List[List[Callable[[mx.array, mx.array], mx.array]]]
-        ] = ...,
-        state_machines: Optional[List[SequenceStateMachine]] = ...,
-    ) -> List[int]: ...
-    def extract_cache(self, uids: List[int]) -> dict[int, Any]: ...
-    def remove(
-        self, uids: List[int], return_prompt_caches: bool = ...
-    ) -> dict[int, Any]: ...
-    @property
-    def prompt_cache_nbytes(self) -> int: ...
-    def next(
-        self,
-    ) -> tuple[
-        List[PromptProcessingBatch.Response], List[GenerationBatch.Response]
-    ]: ...
-    def next_generated(self) -> List[GenerationBatch.Response]: ...
-
 @dataclass
 class BatchResponse:
     """
-    A data object to hold a batch generation response.
+    An data object to hold a batch generation response.
 
     Args:
         texts: (List[str]): The generated text for each prompt.
@@ -514,18 +252,55 @@ class BatchResponse:
 
     texts: List[str]
     stats: BatchStats
-    caches: Optional[List[List[Any]]]
-    ...
+
+@dataclass
+class Batch:
+    uids: List[int]
+    y: mx.array
+    logprobs: mx.array
+    max_tokens: List[int]
+    num_tokens: List[int]
+    cache: List[Any]
+    def __len__(self):  # -> int:
+        ...
+    def filter(self, keep_idx: List[int]):  # -> None:
+        ...
+    def extend(self, other):  # -> None:
+        ...
+
+class BatchGenerator:
+    @dataclass
+    class Response:
+        uid: int
+        token: int
+        logprobs: mx.array
+        finish_reason: Optional[str]
+
+    def __init__(
+        self,
+        model,
+        max_tokens: int = ...,
+        stop_tokens: Optional[set] = ...,
+        sampler: Optional[Callable[[mx.array], mx.array]] = ...,
+        completion_batch_size: int = ...,
+        prefill_batch_size: int = ...,
+        prefill_step_size: int = ...,
+    ) -> None: ...
+    def insert(
+        self, prompts, max_tokens: Union[List[int], int, None] = ...
+    ):  # -> list[Any]:
+        ...
+    def stats(self):  # -> BatchStats:
+        ...
+    def next(self):  # -> list[Any]:
+        ...
 
 def batch_generate(
     model,
     tokenizer,
-    prompts: List[List[int]],
-    prompt_caches: Optional[List[List[Any]]] = ...,
+    prompts: List[int],
     max_tokens: Union[int, List[int]] = ...,
     verbose: bool = ...,
-    return_prompt_caches: bool = ...,
-    logits_processors: Optional[List[Callable[[mx.array, mx.array], mx.array]]] = ...,
     **kwargs,
 ) -> BatchResponse:
     """
@@ -534,22 +309,14 @@ def batch_generate(
     Args:
        model (nn.Module): The language model.
        tokenizer (PreTrainedTokenizer): The tokenizer.
-       prompts (List[List[int]]): The input prompts.
-       prompt_caches (List[List[Any]], optional): Pre-computed prompt-caches
-          for each input prompt. Note, unlike ``generate_step``, the caches
-          won't be updated in-place.
+       prompt (List[List[int]]): The input prompts.
        verbose (bool): If ``True``, print tokens and timing information.
           Default: ``False``.
        max_tokens (Union[int, List[int]): Maximum number of output tokens. This
           can be per prompt if a list is provided.
-       return_prompt_caches (bool): Return the prompt caches in the batch
-          responses. Default: ``False``.
-       logits_processors (List[Callable[[mx.array, mx.array], mx.array]], optional):
-          A list of functions that take tokens and logits and return the processed logits. Default: ``None``.
        kwargs: The remaining options get passed to :obj:`BatchGenerator`.
           See :obj:`BatchGenerator` for more details.
     """
-    ...
 
 def main():  # -> None:
     ...

.mlx_typings/mlx_lm/models/activations.pyi

@@ -1,19 +0,0 @@
-"""
-This type stub file was generated by pyright.
-"""
-
-import mlx.core as mx
-import mlx.nn as nn
-from functools import partial
-
-@partial(mx.compile, shapeless=True)
-def swiglu(gate, x): ...
-@partial(mx.compile, shapeless=True)
-def xielu(x, alpha_p, alpha_n, beta, eps):  # -> array:
-    ...
-
-class XieLU(nn.Module):
-    def __init__(
-        self, alpha_p_init=..., alpha_n_init=..., beta=..., eps=...
-    ) -> None: ...
-    def __call__(self, x: mx.array) -> mx.array: ...

.mlx_typings/mlx_lm/models/base.pyi

@@ -3,7 +3,7 @@ This type stub file was generated by pyright.
 """
 
 from dataclasses import dataclass
-from typing import Any, Optional
+from typing import Optional
 
 import mlx.core as mx
 
@@ -37,10 +37,10 @@ def quantized_scaled_dot_product_attention(
     bits: int = ...,
 ) -> mx.array: ...
 def scaled_dot_product_attention(
-    queries: mx.array,
-    keys: mx.array,
-    values: mx.array,
-    cache: Optional[Any],
+    queries,
+    keys,
+    values,
+    cache,
     scale: float,
     mask: Optional[mx.array],
     sinks: Optional[mx.array] = ...,

.mlx_typings/mlx_lm/models/cache.pyi

@@ -11,12 +11,9 @@ import mlx.core as mx
 class Cache(Protocol):
     keys: mx.array
     values: mx.array
-    offset: int
-    def update_and_fetch(
-        self, keys: mx.array, values: mx.array
-    ) -> tuple[mx.array, mx.array]: ...
+    def update_and_fetch(self, keys: mx.array, values: mx.array) -> None: ...
     @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: ...
 
@@ -88,18 +85,16 @@ def create_attention_mask(
 ) -> array | Literal["causal"] | None: ...
 
 class _BaseCache(Cache):
-    keys: mx.array | None
-    values: mx.array | None
-    offset: int
+    keys: mx.array
+    values: 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: ...
     @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 +110,15 @@ 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 +128,10 @@ 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 +143,8 @@ 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:
         ...
 
@@ -155,30 +156,22 @@ 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 = ...
-    keys: mx.array | None
-    values: mx.array | None
-    keep: int
-    max_size: int
-    _idx: int
     def __init__(self, max_size, keep=...) -> None: ...
-    def _trim(
-        self, trim_size: int, v: mx.array, append: mx.array | None = ...
-    ) -> mx.array: ...
     def update_and_fetch(
         self, keys, values
     ):  # -> tuple[array | Any, array | Any] | tuple[array | Any, array | Any | None]:
@@ -186,16 +179,21 @@ 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:
         ...
     @property
-    def meta_state(self) -> tuple[str, ...]: ...
+    def meta_state(self):  # -> tuple[str, ...]:
+        ...
     @meta_state.setter
-    def meta_state(self, v: tuple[str, ...]) -> None: ...
-    def is_trimmable(self) -> bool: ...
-    def trim(self, n: int) -> int: ...
+    def meta_state(self, v):  # -> None:
+        ...
+    def is_trimmable(self):  # -> bool:
+        ...
+    def trim(self, n):  # -> int:
+        ...
     def to_quantized(
         self, group_size: int = ..., bits: int = ...
     ) -> QuantizedKVCache: ...
@@ -210,7 +208,8 @@ 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:
         ...
@@ -224,7 +223,8 @@ 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: ...
@@ -235,7 +235,8 @@ 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, ...]:
         ...
@@ -248,9 +249,10 @@ 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:
         ...
@@ -265,14 +267,29 @@ class CacheList(_BaseCache):
         """
 
 class BatchKVCache(_BaseCache):
-    step: int
-    keys: array | None
-    values: array | None
-    offset: array
-    left_padding: array
-    _idx: int
-    def __init__(self, left_padding: List[int]) -> None: ...
-    def update_and_fetch(self, keys: array, values: array) -> tuple[array, array]: ...
+    step = ...
+    def __init__(self, left_padding: List[int]) -> None:
+        """
+        The BatchKV cache expects inputs to be left-padded.
+
+        E.g. the following prompts:
+
+            [1, 3, 5]
+            [7]
+            [2, 6, 8, 9]
+
+        Should be padded like so:
+
+            [0, 1, 3, 5]
+            [0, 0, 0, 7]
+            [2, 6, 8, 9]
+
+        And ``left_padding`` specifies the amount of padding for each.
+        In this case, ``left_padding = [1, 3, 0]``.
+        """
+
+    def update_and_fetch(self, keys, values):  # -> tuple[array | Any, array | Any]:
+        ...
     @property
     def state(
         self,
@@ -298,21 +315,12 @@ class BatchKVCache(_BaseCache):
         """
 
 class BatchRotatingKVCache(_BaseCache):
-    step: int
-    keys: array | None
-    values: array | None
-    offset: array
-    left_padding: array
-    max_size: int
-    _idx: int
-    _offset: int
-    rotated: bool
-    _lengths: array | None
-    def __init__(self, max_size: int, left_padding: List[int]) -> None: ...
-    def _trim(self, trim_size: int, v: array, append: array | None = ...) -> array: ...
-    def _update_in_place(self, keys: array, values: array) -> tuple[array, array]: ...
-    def _update_concat(self, keys: array, values: array) -> tuple[array, array]: ...
-    def update_and_fetch(self, keys: array, values: array) -> tuple[array, array]: ...
+    step = ...
+    def __init__(self, max_size, left_padding: List[int]) -> None: ...
+    def update_and_fetch(
+        self, keys, values
+    ):  # -> tuple[array | Any, array | Any] | tuple[array | Any, array | Any | None]:
+        ...
     @property
     def state(
         self,

.mlx_typings/mlx_lm/models/deepseek_v3.pyi

@@ -5,7 +5,6 @@ from typing import Any, Dict, Optional
 
 import mlx.core as mx
 import mlx.nn as nn
-from mlx_lm.models.mla import MultiLinear
 
 from .base import BaseModelArgs
 from .switch_layers import SwitchGLU
@@ -61,10 +60,7 @@ class DeepseekV3Attention(nn.Module):
     q_b_proj: nn.Linear
     kv_a_proj_with_mqa: nn.Linear
     kv_a_layernorm: nn.RMSNorm
-    # kv_b_proj: nn.Linear
-    embed_q: MultiLinear
-    unembed_out: MultiLinear
-
+    kv_b_proj: nn.Linear
     o_proj: nn.Linear
     rope: Any
 

.mlx_typings/mlx_lm/models/deepseek_v4.pyi

@@ -1,280 +0,0 @@
-"""Type stubs for mlx_lm.models.deepseek_v4"""
-
-from dataclasses import dataclass
-from typing import Any, Dict, List, Optional
-
-import mlx.core as mx
-import mlx.nn as nn
-
-from .base import BaseModelArgs
-from .cache import ArraysCache, RotatingKVCache
-from .switch_layers import SwitchGLU
-
-@dataclass
-class ModelArgs(BaseModelArgs):
-    model_type: str
-    vocab_size: int
-    hidden_size: 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: int
-    num_experts_per_tok: int
-    head_dim: int
-    qk_rope_head_dim: int
-    q_lora_rank: int
-    o_lora_rank: int
-    o_groups: int
-    sliding_window: int
-    hc_mult: int
-    hc_sinkhorn_iters: int
-    hc_eps: float
-    compress_ratios: Optional[List[int]]
-    compress_rope_theta: float
-    rope_theta: float
-    rope_scaling: Optional[Dict[str, Any]]
-    rms_norm_eps: float
-    swiglu_limit: float
-    attention_bias: bool
-    max_position_embeddings: int
-
-class DeepseekV4RoPE(nn.Module):
-    dims: int
-    freqs: mx.array
-
-    def __init__(
-        self,
-        dims: int,
-        base: float,
-        scaling_config: Optional[Dict[str, Any]] = None,
-    ) -> None: ...
-    def __call__(
-        self,
-        x: mx.array,
-        offset: int = 0,
-        inverse: bool = False,
-    ) -> mx.array: ...
-
-class HyperConnection(nn.Module):
-    dim: int
-    hc_mult: int
-    norm_eps: float
-
-    def __init__(
-        self,
-        dim: int,
-        hc_mult: int,
-        norm_eps: float,
-        sinkhorn_iters: int,
-        hc_eps: float,
-    ) -> None: ...
-
-class HyperHead(nn.Module):
-    dim: int
-    hc_mult: int
-
-    def __init__(
-        self,
-        dim: int,
-        hc_mult: int,
-        norm_eps: float,
-        hc_eps: float,
-    ) -> None: ...
-    def __call__(self, x: mx.array) -> mx.array: ...
-
-class Compressor(nn.Module):
-    dim: int
-    head_dim: int
-    rope_head_dim: int
-    compress_ratio: int
-    overlap: bool
-    wkv_gate: nn.Linear
-    ape: mx.array
-    norm: nn.RMSNorm
-    rope: DeepseekV4RoPE
-
-    def __init__(
-        self,
-        dim: int,
-        compress_ratio: int,
-        head_dim: int,
-        rope_head_dim: int,
-        rms_norm_eps: float,
-        rope: DeepseekV4RoPE,
-    ) -> None: ...
-    def __call__(
-        self,
-        x: mx.array,
-        cache: "DeepseekV4Cache",
-        offset: Any,
-        key: str = ...,
-    ) -> mx.array: ...
-
-class Indexer(nn.Module):
-    def __init__(
-        self,
-        args: ModelArgs,
-        compress_ratio: int,
-        rope: DeepseekV4RoPE,
-    ) -> None: ...
-
-class _CompressorBranch:
-    buffer_kv: Optional[mx.array]
-    buffer_gate: Optional[mx.array]
-    prev_kv: Optional[mx.array]
-    prev_gate: Optional[mx.array]
-    pool: Optional[mx.array]
-    buffer_lengths: Optional[List[int]]
-    pool_lengths: Optional[List[int]]
-    buffer_count: int
-    _new_pool_lengths: Optional[List[int]]
-
-    def __init__(self) -> None: ...
-
-class DeepseekV4Cache:
-    local: RotatingKVCache
-    offset: int
-    keys: Optional[mx.array]
-    values: Optional[mx.array]
-    state: Any
-    meta_state: Any
-    nbytes: int
-    _branches: Dict[str, _CompressorBranch]
-    _pending_lengths: Optional[List[int]]
-
-    def __init__(self, sliding_window: int) -> None: ...
-    def update_and_fetch(
-        self, keys: mx.array, values: mx.array
-    ) -> tuple[mx.array, mx.array]: ...
-    def is_trimmable(self) -> bool: ...
-    def trim(self, n: int) -> int: ...
-    def empty(self) -> bool: ...
-    def size(self) -> int: ...
-    def prepare(
-        self,
-        *,
-        left_padding: Optional[List[int]] = None,
-        lengths: Optional[List[int]] = None,
-        right_padding: Optional[List[int]] = None,
-    ) -> None: ...
-    def finalize(self) -> None: ...
-    def filter(self, batch_indices: mx.array) -> None: ...
-    def extend(self, other: "DeepseekV4Cache") -> None: ...
-    def extract(self, idx: int) -> "DeepseekV4Cache": ...
-    @classmethod
-    def merge(cls, caches: List["DeepseekV4Cache"]) -> "DeepseekV4Cache": ...
-
-class V4Attention(nn.Module):
-    args: ModelArgs
-    layer_id: int
-    dim: int
-    n_heads: int
-    head_dim: int
-    rope_head_dim: int
-    nope_head_dim: int
-    n_groups: int
-    q_lora_rank: int
-    o_lora_rank: int
-    window: int
-    eps: float
-    scale: float
-    compress_ratio: int
-    wqkv_a: nn.Linear
-    q_norm: nn.RMSNorm
-    wq_b: nn.Linear
-    kv_norm: nn.RMSNorm
-    attn_sink: mx.array
-    wo_a: nn.Linear
-    wo_b: nn.Linear
-    rope: DeepseekV4RoPE
-    compressor: Compressor
-    indexer: Indexer
-
-    def __init__(self, args: ModelArgs, layer_id: int) -> None: ...
-    def __call__(
-        self,
-        x: mx.array,
-        mask: Optional[mx.array] = None,
-        cache: Optional[Any] = None,
-    ) -> mx.array: ...
-
-class DeepseekV4MLP(nn.Module):
-    gate_proj: nn.Linear
-    up_proj: nn.Linear
-    down_proj: nn.Linear
-
-    def __init__(
-        self,
-        hidden_size: int,
-        intermediate_size: int,
-        swiglu_limit: float = 0.0,
-    ) -> None: ...
-    def __call__(self, x: mx.array) -> mx.array: ...
-
-class MoEGate(nn.Module):
-    weight: mx.array
-
-    def __init__(self, args: ModelArgs, layer_id: int) -> None: ...
-    def __call__(
-        self, x: mx.array, input_ids: mx.array
-    ) -> tuple[mx.array, mx.array]: ...
-
-class DeepseekV4MoE(nn.Module):
-    num_experts_per_tok: int
-    switch_mlp: SwitchGLU
-    gate: MoEGate
-    shared_experts: DeepseekV4MLP
-
-    def __init__(self, args: ModelArgs, layer_id: int) -> None: ...
-    def __call__(self, x: mx.array, input_ids: mx.array) -> mx.array: ...
-
-class DeepseekV4Block(nn.Module):
-    attn_norm: nn.RMSNorm
-    attn: V4Attention
-    hc_attn: HyperConnection
-    ffn_norm: nn.RMSNorm
-    ffn: DeepseekV4MoE
-    hc_ffn: HyperConnection
-
-    def __init__(self, args: ModelArgs, layer_id: int) -> None: ...
-    def __call__(
-        self,
-        h: mx.array,
-        cache: Optional[Any],
-        input_ids: mx.array,
-    ) -> mx.array: ...
-
-class DeepseekV4Model(nn.Module):
-    args: ModelArgs
-    vocab_size: int
-    embed_tokens: nn.Embedding
-    layers: list[DeepseekV4Block]
-    norm: nn.RMSNorm
-    hc_head: HyperHead
-
-    def __init__(self, args: ModelArgs) -> None: ...
-    def __call__(
-        self,
-        inputs: mx.array,
-        cache: Optional[List[Any]] = None,
-    ) -> mx.array: ...
-
-class Model(nn.Module):
-    args: ModelArgs
-    model_type: str
-    model: DeepseekV4Model
-    lm_head: nn.Linear
-
-    def __init__(self, args: ModelArgs) -> None: ...
-    def __call__(
-        self,
-        inputs: mx.array,
-        cache: Optional[List[Any]] = None,
-    ) -> mx.array: ...
-    def sanitize(self, weights: dict[str, Any]) -> dict[str, Any]: ...
-    def make_cache(self) -> list[RotatingKVCache | DeepseekV4Cache]: ...
-    @property
-    def layers(self) -> list[DeepseekV4Block]: ...

.mlx_typings/mlx_lm/models/gated_delta.pyi

@@ -1,35 +0,0 @@
-from typing import Optional
-
-import mlx.core as mx
-
-def compute_g(A_log: mx.array, a: mx.array, dt_bias: mx.array) -> mx.array: ...
-def gated_delta_update(
-    q: mx.array,
-    k: mx.array,
-    v: mx.array,
-    a: mx.array,
-    b: mx.array,
-    A_log: mx.array,
-    dt_bias: mx.array,
-    state: Optional[mx.array] = ...,
-    mask: Optional[mx.array] = ...,
-    use_kernel: bool = ...,
-) -> tuple[mx.array, mx.array]: ...
-def gated_delta_ops(
-    q: mx.array,
-    k: mx.array,
-    v: mx.array,
-    g: mx.array,
-    beta: mx.array,
-    state: Optional[mx.array] = ...,
-    mask: Optional[mx.array] = ...,
-) -> tuple[mx.array, mx.array]: ...
-def gated_delta_kernel(
-    q: mx.array,
-    k: mx.array,
-    v: mx.array,
-    g: mx.array,
-    beta: mx.array,
-    state: mx.array,
-    mask: Optional[mx.array] = ...,
-) -> tuple[mx.array, mx.array]: ...

.mlx_typings/mlx_lm/models/gemma4.pyi

@@ -1,31 +0,0 @@
-from dataclasses import dataclass
-from typing import Any, Optional
-
-import mlx.core as mx
-import mlx.nn as nn
-
-from . import gemma4_text
-from .base import BaseModelArgs
-from .cache import KVCache, RotatingKVCache
-
-@dataclass
-class ModelArgs(BaseModelArgs):
-    model_type: str
-    text_config: Optional[dict[str, Any]]
-    vocab_size: int
-
-    def __post_init__(self) -> None: ...
-
-class Model(nn.Module):
-    args: ModelArgs
-    model_type: str
-    language_model: gemma4_text.Model
-
-    def __init__(self, args: ModelArgs) -> None: ...
-    def __call__(self, *args: Any, **kwargs: Any) -> mx.array: ...
-    def sanitize(self, weights: dict[str, Any]) -> dict[str, Any]: ...
-    @property
-    def layers(self) -> list[gemma4_text.DecoderLayer]: ...
-    @property
-    def quant_predicate(self) -> Any: ...
-    def make_cache(self) -> list[KVCache | RotatingKVCache]: ...

.mlx_typings/mlx_lm/models/gemma4_text.pyi

@@ -1,179 +0,0 @@
-from dataclasses import dataclass
-from typing import Any, Dict, List, Optional
-
-import mlx.core as mx
-import mlx.nn as nn
-
-from .base import BaseModelArgs
-from .cache import KVCache, RotatingKVCache
-from .switch_layers import SwitchGLU
-
-@dataclass
-class ModelArgs(BaseModelArgs):
-    model_type: str
-    hidden_size: int
-    num_hidden_layers: int
-    intermediate_size: int
-    num_attention_heads: int
-    head_dim: int
-    global_head_dim: int
-    global_partial_rotary_factor: float
-    rms_norm_eps: float
-    vocab_size: int
-    vocab_size_per_layer_input: int
-    num_key_value_heads: int
-    num_global_key_value_heads: Optional[int]
-    num_kv_shared_layers: int
-    pad_token_id: int
-    hidden_size_per_layer_input: int
-    rope_traditional: bool
-    partial_rotary_factor: float
-    rope_parameters: Optional[Dict[str, Any]]
-    sliding_window: int
-    sliding_window_pattern: int
-    max_position_embeddings: int
-    attention_k_eq_v: bool
-    final_logit_softcapping: float
-    use_double_wide_mlp: bool
-    enable_moe_block: bool
-    num_experts: Optional[int]
-    top_k_experts: Optional[int]
-    moe_intermediate_size: Optional[int]
-    layer_types: Optional[List[str]]
-    tie_word_embeddings: bool
-
-    def __post_init__(self) -> None: ...
-
-class MLP(nn.Module):
-    gate_proj: nn.Linear
-    down_proj: nn.Linear
-    up_proj: nn.Linear
-
-    def __init__(self, config: ModelArgs, layer_idx: int = 0) -> None: ...
-    def __call__(self, x: mx.array) -> mx.array: ...
-
-class Router(nn.Module):
-    proj: nn.Linear
-    scale: mx.array
-    per_expert_scale: mx.array
-
-    def __init__(self, config: ModelArgs) -> None: ...
-    def __call__(self, x: mx.array) -> tuple[mx.array, mx.array]: ...
-
-class Experts(nn.Module):
-    switch_glu: SwitchGLU
-
-    def __init__(self, config: ModelArgs) -> None: ...
-    def __call__(
-        self, x: mx.array, top_k_indices: mx.array, top_k_weights: mx.array
-    ) -> mx.array: ...
-
-class Attention(nn.Module):
-    layer_idx: int
-    layer_type: str
-    is_sliding: bool
-    head_dim: int
-    n_heads: int
-    n_kv_heads: int
-    use_k_eq_v: bool
-    scale: float
-    q_proj: nn.Linear
-    k_proj: nn.Linear
-    v_proj: nn.Linear
-    o_proj: nn.Linear
-    q_norm: nn.Module
-    k_norm: nn.Module
-    v_norm: nn.Module
-    rope: nn.Module
-
-    def __init__(self, config: ModelArgs, layer_idx: int) -> None: ...
-    def __call__(self, *args: Any, **kwargs: Any) -> Any: ...
-
-class DecoderLayer(nn.Module):
-    layer_idx: int
-    layer_type: str
-    self_attn: Attention
-    mlp: MLP
-    enable_moe: bool
-    router: Router
-    experts: Experts
-    input_layernorm: nn.Module
-    post_attention_layernorm: nn.Module
-    pre_feedforward_layernorm: nn.Module
-    post_feedforward_layernorm: nn.Module
-    post_feedforward_layernorm_1: nn.Module
-    post_feedforward_layernorm_2: nn.Module
-    pre_feedforward_layernorm_2: nn.Module
-    hidden_size_per_layer_input: int
-    per_layer_input_gate: Optional[nn.Linear]
-    per_layer_projection: Optional[nn.Linear]
-    post_per_layer_input_norm: Optional[nn.Module]
-    layer_scalar: mx.array
-
-    def __init__(self, config: ModelArgs, layer_idx: int) -> None: ...
-    def __call__(
-        self,
-        x: mx.array,
-        mask: Optional[mx.array] = ...,
-        cache: Optional[Any] = ...,
-        per_layer_input: Optional[mx.array] = ...,
-        shared_kv: Optional[tuple[mx.array, mx.array]] = ...,
-        offset: Optional[mx.array] = ...,
-    ) -> tuple[mx.array, tuple[mx.array, mx.array], mx.array]: ...
-
-class Gemma4TextModel(nn.Module):
-    config: ModelArgs
-    vocab_size: int
-    window_size: int
-    sliding_window_pattern: int
-    num_hidden_layers: int
-    embed_tokens: nn.Embedding
-    embed_scale: float
-    layers: list[DecoderLayer]
-    norm: nn.Module
-    hidden_size_per_layer_input: int
-    embed_tokens_per_layer: Optional[nn.Embedding]
-    per_layer_model_projection: Optional[nn.Linear]
-    per_layer_projection_norm: Optional[nn.Module]
-    previous_kvs: list[int]
-
-    def __init__(self, config: ModelArgs) -> None: ...
-    def __call__(
-        self,
-        inputs: Optional[mx.array] = ...,
-        cache: Optional[list[Any]] = ...,
-        input_embeddings: Optional[mx.array] = ...,
-        per_layer_inputs: Optional[mx.array] = ...,
-    ) -> mx.array: ...
-    def _get_per_layer_inputs(
-        self,
-        input_ids: Optional[mx.array],
-        input_embeddings: Optional[mx.array] = ...,
-    ) -> mx.array: ...
-    def _project_per_layer_inputs(
-        self,
-        input_embeddings: mx.array,
-        per_layer_inputs: Optional[mx.array] = ...,
-    ) -> mx.array: ...
-    def _make_masks(self, h: mx.array, cache: list[Any]) -> list[Any]: ...
-
-class Model(nn.Module):
-    args: ModelArgs
-    model_type: str
-    model: Gemma4TextModel
-    final_logit_softcapping: float
-    tie_word_embeddings: bool
-    lm_head: nn.Linear
-
-    def __init__(self, args: ModelArgs) -> None: ...
-    def __call__(self, *args: Any, **kwargs: Any) -> mx.array: ...
-    def sanitize(self, weights: dict[str, Any]) -> dict[str, Any]: ...
-    @property
-    def layers(self) -> list[DecoderLayer]: ...
-    @property
-    def head_dim(self) -> int: ...
-    @property
-    def n_kv_heads(self) -> int: ...
-    @property
-    def quant_predicate(self) -> Any: ...
-    def make_cache(self) -> list[KVCache | RotatingKVCache]: ...

.mlx_typings/mlx_lm/models/glm4_moe.pyi

@@ -1,153 +0,0 @@
-from dataclasses import dataclass
-from typing import Any, Dict, Optional
-
-import mlx.core as mx
-import mlx.nn as nn
-
-from .base import BaseModelArgs
-from .switch_layers import SwitchGLU
-
-@dataclass
-class ModelArgs(BaseModelArgs):
-    model_type: str
-    vocab_size: int
-    hidden_size: int
-    intermediate_size: int
-    max_position_embeddings: int
-    moe_intermediate_size: int
-    norm_topk_prob: bool
-    num_attention_heads: int
-    n_group: int
-    head_dim: int
-    topk_group: int
-    n_shared_experts: int
-    n_routed_experts: int
-    routed_scaling_factor: float
-    num_experts_per_tok: int
-    first_k_dense_replace: int
-    num_hidden_layers: int
-    num_key_value_heads: int
-    rms_norm_eps: float
-    rope_theta: float
-    rope_scaling: Optional[Dict[str, Any]]
-    use_qk_norm: bool
-    tie_word_embeddings: bool
-    attention_bias: bool
-    partial_rotary_factor: float
-    scoring_func: str
-    topk_method: str
-
-class Attention(nn.Module):
-    n_heads: int
-    n_kv_heads: int
-    scale: float
-    q_proj: nn.Linear
-    k_proj: nn.Linear
-    v_proj: nn.Linear
-    o_proj: nn.Linear
-    use_qk_norm: bool
-    q_norm: nn.RMSNorm
-    k_norm: nn.RMSNorm
-    rope: nn.RoPE
-
-    def __init__(self, args: ModelArgs) -> None: ...
-    def __call__(
-        self,
-        x: mx.array,
-        mask: Optional[mx.array] = None,
-        cache: Optional[Any] = None,
-    ) -> mx.array: ...
-
-class MLP(nn.Module):
-    config: ModelArgs
-    hidden_size: int
-    intermediate_size: int
-    gate_proj: nn.Linear
-    up_proj: nn.Linear
-    down_proj: nn.Linear
-
-    def __init__(
-        self,
-        config: ModelArgs,
-        hidden_size: Optional[int] = None,
-        intermediate_size: Optional[int] = None,
-    ) -> None: ...
-    def __call__(self, x: mx.array) -> mx.array: ...
-
-class MoEGate(nn.Module):
-    config: ModelArgs
-    top_k: int
-    norm_topk_prob: bool
-    n_routed_experts: int
-    routed_scaling_factor: float
-    n_group: int
-    topk_group: int
-    weight: mx.array
-    e_score_correction_bias: mx.array
-
-    def __init__(self, config: ModelArgs) -> None: ...
-    def __call__(self, x: mx.array) -> tuple[mx.array, mx.array]: ...
-
-class MoE(nn.Module):
-    config: ModelArgs
-    num_experts_per_tok: int
-    switch_mlp: SwitchGLU
-    gate: MoEGate
-    shared_experts: MLP
-    sharding_group: Optional[mx.distributed.Group]
-
-    def __init__(self, config: ModelArgs) -> None: ...
-    def __call__(self, x: mx.array) -> mx.array: ...
-
-class DecoderLayer(nn.Module):
-    self_attn: Attention
-    mlp: MLP | MoE
-    input_layernorm: nn.RMSNorm
-    post_attention_layernorm: nn.RMSNorm
-
-    def __init__(self, config: ModelArgs, layer_idx: int) -> None: ...
-    def __call__(
-        self,
-        x: mx.array,
-        mask: Optional[mx.array] = None,
-        cache: Optional[Any] = None,
-    ) -> mx.array: ...
-
-class LanguageModel(nn.Module):
-    vocab_size: int
-    embed_tokens: nn.Embedding
-    layers: list[DecoderLayer]
-    norm: nn.RMSNorm
-    pipeline_rank: int
-    pipeline_size: int
-    start_idx: int
-    end_idx: Optional[int]
-    num_layers: int
-
-    def __init__(self, config: ModelArgs) -> None: ...
-    def __call__(
-        self,
-        x: mx.array,
-        cache: Optional[Any] = None,
-    ) -> mx.array: ...
-    @property
-    def pipeline_layers(self) -> list[DecoderLayer]: ...
-
-class Model(nn.Module):
-    args: ModelArgs
-    model_type: str
-    model: LanguageModel
-    lm_head: nn.Linear
-
-    def __init__(self, config: ModelArgs) -> None: ...
-    def __call__(
-        self,
-        inputs: mx.array,
-        cache: Optional[Any] = None,
-    ) -> mx.array: ...
-    def sanitize(self, weights: dict[str, Any]) -> dict[str, Any]: ...
-    def shard(self, group: Optional[mx.distributed.Group] = None) -> None: ...
-    @property
-    def layers(self) -> list[DecoderLayer]: ...
-    @property
-    def cast_predicate(self) -> Any: ...

.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/gpt_oss.pyi

@@ -1,103 +0,0 @@
-"""Type stubs for mlx_lm.models.gpt_oss"""
-
-from dataclasses import dataclass
-from typing import Any, List, Optional
-
-import mlx.core as mx
-import mlx.nn as nn
-
-from .base import BaseModelArgs
-from .cache import KVCache
-from .switch_layers import SwitchGLU
-
-@dataclass
-class ModelArgs(BaseModelArgs):
-    model_type: str
-    hidden_size: int
-    intermediate_size: int
-    num_hidden_layers: int
-    num_attention_heads: int
-    num_key_value_heads: int
-    num_local_experts: int
-    num_experts_per_tok: int
-    vocab_size: int
-    rms_norm_eps: float
-    sliding_window: int
-    layer_types: Optional[List[str]]
-
-def mlx_topk(a: mx.array, k: int, axis: int = -1) -> tuple[mx.array, mx.array]: ...
-
-class AttentionBlock(nn.Module):
-    head_dim: int
-    num_attention_heads: int
-    num_key_value_heads: int
-    num_key_value_groups: int
-    sinks: mx.array
-    q_proj: nn.Linear
-    k_proj: nn.Linear
-    v_proj: nn.Linear
-    o_proj: nn.Linear
-    sm_scale: float
-    rope: nn.Module
-
-    def __init__(self, config: ModelArgs) -> None: ...
-    def __call__(
-        self,
-        x: mx.array,
-        mask: Optional[mx.array] = None,
-        cache: Optional[Any] = None,
-    ) -> mx.array: ...
-
-class TransformerBlock(nn.Module):
-    self_attn: AttentionBlock
-    mlp: MLPBlock
-
-    def __init__(self, config: ModelArgs) -> None: ...
-    def __call__(
-        self,
-        x: mx.array,
-        mask: Optional[mx.array] = None,
-        cache: Optional[Any] = None,
-    ) -> mx.array: ...
-
-class MLPBlock(nn.Module):
-    hidden_size: int
-    num_local_experts: int
-    num_experts_per_tok: int
-    experts: SwitchGLU
-    router: nn.Linear
-    sharding_group: Optional[mx.distributed.Group]
-
-    def __init__(self, config: ModelArgs) -> None: ...
-    def __call__(self, x: mx.array) -> mx.array: ...
-
-class GptOssMoeModel(nn.Module):
-    embed_tokens: nn.Embedding
-    norm: nn.RMSNorm
-    layer_types: List[str]
-    layers: list[TransformerBlock]
-    window_size: int
-    swa_idx: int
-    ga_idx: int
-
-    def __init__(self, args: ModelArgs) -> None: ...
-    def __call__(
-        self,
-        inputs: mx.array,
-        cache: Optional[Any] = None,
-    ) -> mx.array: ...
-
-class Model(nn.Module):
-    model_type: str
-    model: GptOssMoeModel
-    lm_head: nn.Linear
-
-    def __init__(self, args: ModelArgs) -> None: ...
-    def __call__(
-        self,
-        inputs: mx.array,
-        cache: Optional[Any] = None,
-    ) -> mx.array: ...
-    @property
-    def layers(self) -> list[nn.Module]: ...
-    def make_cache(self) -> list[KVCache]: ...

.mlx_typings/mlx_lm/models/minimax.pyi

@@ -1,94 +0,0 @@
-"""Type stubs for mlx_lm.models.minimax"""
-
-from dataclasses import dataclass
-from typing import Any, Optional
-
-import mlx.core as mx
-import mlx.nn as nn
-
-from .base import BaseModelArgs
-from .switch_layers import SwitchGLU
-
-@dataclass
-class ModelArgs(BaseModelArgs):
-    model_type: str
-    hidden_size: int
-    intermediate_size: int
-    num_hidden_layers: int
-    num_attention_heads: int
-    num_key_value_heads: int
-    num_local_experts: int
-    num_experts_per_tok: int
-    max_position_embeddings: int
-
-class MiniMaxAttention(nn.Module):
-    num_heads: int
-    num_attention_heads: int
-    num_key_value_heads: int
-    head_dim: int
-    scale: float
-    q_proj: nn.Linear
-    k_proj: nn.Linear
-    v_proj: nn.Linear
-    o_proj: nn.Linear
-    q_norm: nn.Module
-    k_norm: nn.Module
-    rope: nn.Module
-
-    def __init__(self, args: ModelArgs) -> None: ...
-    def __call__(
-        self,
-        x: mx.array,
-        mask: Optional[mx.array] = None,
-        cache: Optional[Any] = None,
-    ) -> mx.array: ...
-
-class MiniMaxSparseMoeBlock(nn.Module):
-    num_experts_per_tok: int
-    gate: nn.Linear
-    switch_mlp: SwitchGLU
-    e_score_correction_bias: mx.array
-    sharding_group: Optional[mx.distributed.Group]
-
-    def __init__(self, args: ModelArgs) -> None: ...
-    def __call__(self, x: mx.array) -> mx.array: ...
-
-class MiniMaxDecoderLayer(nn.Module):
-    self_attn: MiniMaxAttention
-    block_sparse_moe: MiniMaxSparseMoeBlock
-    input_layernorm: nn.RMSNorm
-    post_attention_layernorm: nn.RMSNorm
-
-    def __init__(self, args: ModelArgs) -> None: ...
-    def __call__(
-        self,
-        x: mx.array,
-        mask: Optional[mx.array] = None,
-        cache: Optional[Any] = None,
-    ) -> mx.array: ...
-
-class MiniMaxModel(nn.Module):
-    embed_tokens: nn.Embedding
-    layers: list[MiniMaxDecoderLayer]
-    norm: nn.RMSNorm
-
-    def __init__(self, args: ModelArgs) -> None: ...
-    def __call__(
-        self,
-        inputs: mx.array,
-        cache: Optional[Any] = None,
-    ) -> mx.array: ...
-
-class Model(nn.Module):
-    model_type: str
-    model: MiniMaxModel
-    lm_head: nn.Linear
-
-    def __init__(self, args: ModelArgs) -> None: ...
-    def __call__(
-        self,
-        inputs: mx.array,
-        cache: Optional[Any] = None,
-    ) -> mx.array: ...
-    @property
-    def layers(self) -> list[MiniMaxDecoderLayer]: ...

.mlx_typings/mlx_lm/models/nemotron_h.pyi

@@ -1,168 +0,0 @@
-from dataclasses import dataclass
-from typing import Any, List, Optional, Tuple
-
-import mlx.core as mx
-import mlx.nn as nn
-
-from .cache import ArraysCache, KVCache
-from .switch_layers import SwitchMLP
-
-@dataclass
-class ModelArgs:
-    model_type: str
-    vocab_size: int
-    hidden_size: int
-    intermediate_size: int
-    num_hidden_layers: int
-    max_position_embeddings: int
-    num_attention_heads: int
-    num_key_value_heads: int
-    attention_bias: bool
-    mamba_num_heads: int
-    mamba_head_dim: int
-    mamba_proj_bias: bool
-    ssm_state_size: int
-    conv_kernel: int
-    n_groups: int
-    mlp_bias: bool
-    layer_norm_epsilon: float
-    use_bias: bool
-    use_conv_bias: bool
-    hybrid_override_pattern: List[str]
-    head_dim: Optional[int]
-    moe_intermediate_size: Optional[int]
-    moe_shared_expert_intermediate_size: Optional[int]
-    n_group: Optional[int]
-    n_routed_experts: Optional[int]
-    n_shared_experts: Optional[int]
-    topk_group: Optional[int]
-    num_experts_per_tok: Optional[int]
-    norm_topk_prob: Optional[bool]
-    routed_scaling_factor: Optional[float]
-    time_step_limit: Optional[Tuple[float, float]]
-    time_step_min: Optional[float]
-    time_step_max: Optional[float]
-
-    @classmethod
-    def from_dict(cls, params: dict[str, Any]) -> ModelArgs: ...
-    def __post_init__(self) -> None: ...
-
-class NemotronHMamba2Mixer(nn.Module):
-    num_heads: int
-    hidden_size: int
-    ssm_state_size: int
-    conv_kernel_size: int
-    intermediate_size: int
-    n_groups: int
-    head_dim: int
-    conv_dim: int
-    conv1d: nn.Conv1d
-    in_proj: nn.Linear
-    dt_bias: mx.array
-    A_log: mx.array
-    D: mx.array
-    norm: nn.RMSNorm
-    heads_per_group: int
-    out_proj: nn.Linear
-
-    def __init__(self, args: ModelArgs) -> None: ...
-    def __call__(
-        self,
-        hidden_states: mx.array,
-        mask: Optional[mx.array],
-        cache: Optional[ArraysCache] = None,
-    ) -> mx.array: ...
-
-class NemotronHAttention(nn.Module):
-    hidden_size: int
-    num_heads: int
-    head_dim: int
-    num_key_value_heads: int
-    scale: float
-    q_proj: nn.Linear
-    k_proj: nn.Linear
-    v_proj: nn.Linear
-    o_proj: nn.Linear
-
-    def __init__(self, args: ModelArgs) -> None: ...
-    def __call__(
-        self,
-        x: mx.array,
-        mask: Optional[mx.array] = None,
-        cache: Optional[KVCache] = None,
-    ) -> mx.array: ...
-
-class MoEGate(nn.Module):
-    config: ModelArgs
-    top_k: int
-    norm_topk_prob: bool
-    weight: mx.array
-
-    def __init__(self, config: ModelArgs) -> None: ...
-    def __call__(self, x: mx.array) -> tuple[mx.array, mx.array]: ...
-
-class NemotronHMLP(nn.Module):
-    up_proj: nn.Linear
-    down_proj: nn.Linear
-
-    def __init__(
-        self, args: ModelArgs, intermediate_size: Optional[int] = None
-    ) -> None: ...
-    def __call__(self, x: mx.array) -> mx.array: ...
-
-class NemotronHMoE(nn.Module):
-    config: ModelArgs
-    num_experts_per_tok: int
-    moe_latent_size: Optional[int]
-    switch_mlp: SwitchMLP
-    gate: MoEGate
-    shared_experts: NemotronHMLP
-    fc1_latent_proj: nn.Linear
-    fc2_latent_proj: nn.Linear
-
-    def __init__(self, config: ModelArgs) -> None: ...
-    def __call__(self, x: mx.array) -> mx.array: ...
-
-class NemotronHBlock(nn.Module):
-    block_type: str
-    norm: nn.RMSNorm
-    mixer: NemotronHMamba2Mixer | NemotronHAttention | NemotronHMLP | NemotronHMoE
-
-    def __init__(self, args: ModelArgs, block_type: str) -> None: ...
-    def __call__(
-        self,
-        x: mx.array,
-        mask: Optional[mx.array] = None,
-        cache: Optional[Any] = None,
-    ) -> mx.array: ...
-
-class NemotronHModel(nn.Module):
-    embeddings: nn.Embedding
-    layers: list[NemotronHBlock]
-    norm_f: nn.RMSNorm
-    fa_idx: int
-    ssm_idx: int
-
-    def __init__(self, args: ModelArgs) -> None: ...
-    def __call__(
-        self,
-        inputs: mx.array,
-        cache: Optional[Any] = None,
-    ) -> mx.array: ...
-
-class Model(nn.Module):
-    args: ModelArgs
-    backbone: NemotronHModel
-    lm_head: nn.Linear
-    model_type: str
-
-    def __init__(self, args: ModelArgs) -> None: ...
-    def __call__(
-        self,
-        inputs: mx.array,
-        cache: Optional[Any] = None,
-    ) -> mx.array: ...
-    @property
-    def layers(self) -> list[NemotronHBlock]: ...
-    def make_cache(self) -> list[ArraysCache | KVCache]: ...
-    def sanitize(self, weights: dict[str, Any]) -> dict[str, Any]: ...

.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

@@ -1,128 +0,0 @@
-"""Type stubs for mlx_lm.models.qwen3_next"""
-
-from typing import Any, Optional
-
-import mlx.core as mx
-import mlx.nn as nn
-
-from .cache import ArraysCache, KVCache
-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
-    up_proj: nn.Linear
-
-    def __init__(self, dim: int, hidden_dim: int) -> None: ...
-    def __call__(self, x: mx.array) -> mx.array: ...
-
-class Qwen3NextGatedDeltaNet(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_qkvz: nn.Linear
-    in_proj_ba: nn.Linear
-    dt_bias: mx.array
-    A_log: mx.array
-    out_proj: nn.Linear
-
-    def __init__(self, config: Any) -> None: ...
-    def __call__(
-        self,
-        inputs: mx.array,
-        mask: Optional[mx.array] = None,
-        cache: Optional[Any] = None,
-    ) -> mx.array: ...
-
-class Qwen3NextAttention(nn.Module):
-    num_attention_heads: int
-    num_key_value_heads: int
-    head_dim: int
-    scale: float
-    q_proj: nn.Linear
-    k_proj: nn.Linear
-    v_proj: nn.Linear
-    o_proj: nn.Linear
-
-    def __init__(self, args: Any) -> None: ...
-    def __call__(
-        self,
-        x: mx.array,
-        mask: Optional[mx.array] = None,
-        cache: Optional[Any] = None,
-    ) -> mx.array: ...
-
-class Qwen3NextSparseMoeBlock(nn.Module):
-    norm_topk_prob: bool
-    num_experts: int
-    num_experts_per_tok: int
-    top_k: int
-    gate: nn.Linear
-    switch_mlp: SwitchGLU
-    shared_expert: Qwen3NextMLP
-    shared_expert_gate: nn.Linear
-
-    def __init__(self, args: Any) -> None: ...
-    def __call__(self, x: mx.array) -> mx.array: ...
-
-class Qwen3NextDecoderLayer(nn.Module):
-    is_linear: bool
-    linear_attn: Qwen3NextGatedDeltaNet
-    self_attn: Qwen3NextAttention
-    input_layernorm: nn.RMSNorm
-    post_attention_layernorm: nn.RMSNorm
-    mlp: Qwen3NextMLP | Qwen3NextSparseMoeBlock
-
-    def __init__(self, args: Any, layer_idx: int) -> None: ...
-    def __call__(
-        self,
-        x: mx.array,
-        mask: Optional[mx.array] = None,
-        cache: Optional[Any] = None,
-    ) -> mx.array: ...
-
-class Qwen3NextModel(nn.Module):
-    embed_tokens: nn.Embedding
-    layers: list[Qwen3NextDecoderLayer]
-    norm: nn.RMSNorm
-    ssm_idx: int
-    fa_idx: int
-
-    def __init__(self, args: Any) -> None: ...
-    def __call__(
-        self,
-        inputs: mx.array,
-        cache: Optional[Any] = None,
-    ) -> mx.array: ...
-
-class Model(nn.Module):
-    model_type: str
-    model: Qwen3NextModel
-    lm_head: nn.Linear
-
-    def __init__(self, args: Any) -> None: ...
-    def __call__(
-        self,
-        inputs: mx.array,
-        cache: Optional[Any] = None,
-    ) -> mx.array: ...
-    def sanitize(self, weights: dict[str, Any]) -> dict[str, Any]: ...
-    @property
-    def layers(self) -> list[Qwen3NextDecoderLayer]: ...
-    def make_cache(self) -> list[ArraysCache | KVCache]: ...

.mlx_typings/mlx_lm/models/rope_utils.pyi

@@ -1,51 +0,0 @@
-from typing import Any, Optional
-
-import mlx.nn as nn
-
-class YarnRoPE(nn.Module):
-    def __init__(
-        self,
-        dims: int,
-        traditional: bool = ...,
-        max_position_embeddings: int = ...,
-        base: float = ...,
-        scaling_factor: float = ...,
-        original_max_position_embeddings: int = ...,
-        beta_fast: float = ...,
-        beta_slow: float = ...,
-        mscale: float = ...,
-        mscale_all_dim: float = ...,
-    ) -> None: ...
-
-class Llama3RoPE(nn.Module):
-    def __init__(
-        self,
-        dims: int,
-        traditional: bool = ...,
-        max_position_embeddings: int = ...,
-        base: float = ...,
-        scaling_factor: float = ...,
-        original_max_position_embeddings: int = ...,
-        low_freq_factor: float = ...,
-        high_freq_factor: float = ...,
-    ) -> None: ...
-
-class SuScaledRoPE(nn.Module):
-    def __init__(
-        self,
-        dims: int,
-        traditional: bool = ...,
-        max_position_embeddings: int = ...,
-        base: float = ...,
-        short_factor: Any = ...,
-        long_factor: Any = ...,
-        original_max_position_embeddings: int = ...,
-    ) -> None: ...
-
-def initialize_rope(
-    dims: int,
-    base: float = ...,
-    traditional: bool = ...,
-    scaling_config: Optional[dict[str, Any]] = ...,
-    max_position_embeddings: Optional[int] = ...,
-) -> nn.Module: ...

.mlx_typings/mlx_lm/models/step3p5.pyi

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

.mlx_typings/mlx_lm/models/switch_layers.pyi

@@ -73,9 +73,6 @@ class SwitchGLU(nn.Module):
     def __call__(self, x, indices) -> mx.array: ...
 
 class SwitchMLP(nn.Module):
-    fc1: SwitchLinear
-    fc2: SwitchLinear
-
     def __init__(
         self,
         input_dims: int,

.mlx_typings/mlx_lm/sample_utils.pyi

@@ -48,11 +48,7 @@ def make_logits_processors(
     logit_bias: Optional[Dict[int, float]] = ...,
     repetition_penalty: Optional[float] = ...,
     repetition_context_size: Optional[int] = ...,
-    presence_penalty: Optional[float] = ...,
-    presence_context_size: Optional[int] = ...,
-    frequency_penalty: Optional[float] = ...,
-    frequency_context_size: Optional[int] = ...,
-) -> list[Callable[[mx.array, mx.array], mx.array]]:
+):  # -> list[Any]:
     """
     Make logits processors for use with ``generate_step``.
 

.mlx_typings/mlx_lm/tokenizer_utils.pyi

@@ -39,11 +39,11 @@ class StreamingDetokenizer:
     """
 
     __slots__ = ...
-    def reset(self) -> None: ...
-    def add_token(self, token: int) -> None: ...
-    def finalize(self) -> None: ...
+    def reset(self): ...
+    def add_token(self, token): ...
+    def finalize(self): ...
     @property
-    def last_segment(self) -> str:
+    def last_segment(self):
         """Return the last segment of readable text since last time this property was accessed."""
 
 class NaiveStreamingDetokenizer(StreamingDetokenizer):
@@ -108,23 +108,16 @@ class TokenizerWrapper:
     _tokenizer: PreTrainedTokenizerFast
     eos_token_id: int | None
     eos_token: str | None
-    eos_token_ids: list[int] | set[int] | None
     bos_token_id: int | None
     bos_token: str | None
     vocab_size: int
     all_special_tokens: list[str]
-    think_start: str | None
-    think_end: str | None
-    think_start_id: int | None
-    think_end_id: int | None
-    think_start_tokens: list[int] | None
-    think_end_tokens: list[int] | None
 
     def __init__(
         self,
         tokenizer: Any,
         detokenizer_class: Any = ...,
-        eos_token_ids: list[int] | set[int] | None = ...,
+        eos_token_ids: list[int] | None = ...,
         chat_template: Any = ...,
         tool_parser: Any = ...,
         tool_call_start: str | None = ...,

.mlx_typings/mlx_lm/tuner/dora.pyi

@@ -1,50 +0,0 @@
-"""
-This type stub file was generated by pyright.
-"""
-
-import mlx.nn as nn
-
-class DoRALinear(nn.Module):
-    @staticmethod
-    def from_base(
-        linear: nn.Linear, r: int = ..., dropout: float = ..., scale: float = ...
-    ):  # -> DoRALinear:
-        ...
-    def fuse(self, dequantize: bool = ...):  # -> QuantizedLinear | Linear:
-        ...
-    def __init__(
-        self,
-        input_dims: int,
-        output_dims: int,
-        r: int = ...,
-        dropout: float = ...,
-        scale: float = ...,
-        bias: bool = ...,
-    ) -> None: ...
-    def set_linear(self, linear):  # -> None:
-        """
-        Set the self.linear layer and recompute self.m.
-        """
-        ...
-
-    def __call__(self, x): ...
-
-class DoRAEmbedding(nn.Module):
-    def from_base(
-        embedding: nn.Embedding, r: int = ..., dropout: float = ..., scale: float = ...
-    ):  # -> DoRAEmbedding:
-        ...
-    def fuse(self, dequantize: bool = ...):  # -> Embedding:
-        ...
-    def __init__(
-        self,
-        num_embeddings: int,
-        dims: int,
-        r: int = ...,
-        dropout: float = ...,
-        scale: float = ...,
-    ) -> None: ...
-    def set_embedding(self, embedding: nn.Module):  # -> None:
-        ...
-    def __call__(self, x): ...
-    def as_linear(self, x): ...

.mlx_typings/mlx_lm/tuner/lora.pyi

@@ -1,66 +0,0 @@
-"""
-This type stub file was generated by pyright.
-"""
-
-import mlx.nn as nn
-
-class LoRALinear(nn.Module):
-    @staticmethod
-    def from_base(
-        linear: nn.Linear, r: int = ..., dropout: float = ..., scale: float = ...
-    ):  # -> LoRALinear:
-        ...
-    def fuse(self, dequantize: bool = ...):  # -> QuantizedLinear | Linear:
-        ...
-    def __init__(
-        self,
-        input_dims: int,
-        output_dims: int,
-        r: int = ...,
-        dropout: float = ...,
-        scale: float = ...,
-        bias: bool = ...,
-    ) -> None: ...
-    def __call__(self, x):  # -> array:
-        ...
-
-class LoRASwitchLinear(nn.Module):
-    @staticmethod
-    def from_base(
-        linear: nn.Module, r: int = ..., dropout: float = ..., scale: float = ...
-    ):  # -> LoRASwitchLinear:
-        ...
-    def fuse(self, dequantize: bool = ...):  # -> QuantizedSwitchLinear | SwitchLinear:
-        ...
-    def __init__(
-        self,
-        input_dims: int,
-        output_dims: int,
-        num_experts: int,
-        r: int = ...,
-        dropout: float = ...,
-        scale: float = ...,
-        bias: bool = ...,
-    ) -> None: ...
-    def __call__(self, x, indices, sorted_indices=...): ...
-
-class LoRAEmbedding(nn.Module):
-    @staticmethod
-    def from_base(
-        embedding: nn.Embedding, r: int = ..., dropout: float = ..., scale: float = ...
-    ):  # -> LoRAEmbedding:
-        ...
-    def fuse(self, dequantize: bool = ...):  # -> QuantizedEmbedding | Embedding:
-        ...
-    def __init__(
-        self,
-        num_embeddings: int,
-        dims: int,
-        r: int = ...,
-        dropout: float = ...,
-        scale: float = ...,
-    ) -> None: ...
-    def __call__(self, x):  # -> array:
-        ...
-    def as_linear(self, x):  # -> array:
-        ...

.mlx_typings/mlx_lm/tuner/utils.pyi

@@ -1,57 +0,0 @@
-"""
-This type stub file was generated by pyright.
-"""
-
-import mlx.nn as nn
-from typing import Dict
-
-def build_schedule(schedule_config: Dict):  # -> Any:
-    """
-    Build a learning rate schedule from the given config.
-    """
-    ...
-
-def linear_to_lora_layers(
-    model: nn.Module, num_layers: int, config: Dict, use_dora: bool = ...
-):  # -> None:
-    """
-    Convert some of the models linear layers to lora layers.
-
-    Args:
-        model (nn.Module): The neural network model.
-        num_layers (int): The number of blocks to convert to lora layers
-        starting from the last layer.
-        config (dict): More configuration parameters for LoRA, including the
-          rank, scale, and optional layer keys.
-        use_dora (bool): If True, uses DoRA instead of LoRA.
-          Default: ``False``
-    """
-    ...
-
-def load_adapters(model: nn.Module, adapter_path: str) -> nn.Module:
-    """
-    Load any fine-tuned adapters / layers.
-
-    Args:
-        model (nn.Module): The neural network model.
-        adapter_path (str): Path to the adapter configuration file.
-
-    Returns:
-        nn.Module: The updated model with LoRA layers applied.
-    """
-    ...
-
-def remove_lora_layers(model: nn.Module) -> nn.Module:
-    """
-    Remove the LoRA layers from the model.
-
-    Args:
-        model (nn.Module): The model with LoRA layers.
-
-    Returns:
-        nn.Module: The model without LoRA layers.
-    """
-    ...
-
-def print_trainable_parameters(model):  # -> None:
-    ...

.mlx_typings/mlx_vlm/prompt_utils.pyi

@@ -1,12 +0,0 @@
-from typing import Any
-
-def get_message_json(
-    model_name: str,
-    prompt: str,
-    role: str = "user",
-    skip_image_token: bool = False,
-    skip_audio_token: bool = False,
-    num_images: int = 0,
-    num_audios: int = 0,
-    **kwargs: Any,
-) -> dict[str, Any]: ...

.mlx_typings/mlx_vlm/utils.pyi

@@ -1,15 +0,0 @@
-from pathlib import Path
-from typing import Any
-
-class ImageProcessor:
-    def preprocess(
-        self, images: list[dict[str, Any]], **kwargs: Any
-    ) -> dict[str, Any]: ...
-    def __call__(self, **kwargs: Any) -> dict[str, Any]: ...
-
-def load_image_processor(
-    model_path: str | Path, **kwargs: Any
-) -> ImageProcessor | None: ...
-def load_processor(
-    model_path: str | Path, add_detokenizer: bool = ..., **kwargs: Any
-) -> ImageProcessor: ...

.mlx_typings/safetensors/__init__.pyi

@@ -1,8 +0,0 @@
-from typing import Any, Self
-
-class safe_open:
-    def __init__(self, filename: str, framework: str = "pt") -> None: ...
-    def __enter__(self) -> Self: ...
-    def __exit__(self, *args: Any) -> None: ...
-    def keys(self) -> list[str]: ...
-    def get_tensor(self, name: str) -> Any: ...

.vscode/extensions.json

@@ -1,8 +1,7 @@
 {
     "recommendations": [
         "detachhead.basedpyright",
-        "ms-python.python",
-        "jnoortheen.nix-ide"
+        "ms-python.python"
     ],
     "unwantedRecommendations": [
         "ms-python.vscode-pylance",

.vscode/settings.json

@@ -1,32 +1,3 @@
 {
-    "files.associations": {
-        "*.nix": "nix",
-    },
-    "nix.enableLanguageServer": true,
-    "nix.serverPath": "nixd",
-    "nix.serverSettings": {
-        "nixd": {
-        "formatting": {
-            "command": ["nixpkgs-fmt"]
-        },
-        "nixpkgs": {
-            "expr": "(builtins.getFlake \"path:${workspaceFolder}\").currentSystem.config._module.args.pkgs"
-        },
-        "options": {
-            "flake-parts": {
-                "expr": "(builtins.getFlake \"path:${workspaceFolder}\").debug.options"
-            },
-            "flake-parts-perSystem": {
-                "expr": "(builtins.getFlake \"path:${workspaceFolder}\").currentSystem.options"
-            }
-        }
-      }
-    },
-    "[nix]": {
-        "editor.defaultFormatter": "jnoortheen.nix-ide"
-    },
-    
-    "python.defaultInterpreterPath": "${workspaceFolder}/.venv/bin/python",
-    "basedpyright.analysis.configFilePath": "${workspaceFolder}/pyproject.toml",
-    "basedpyright.importStrategy": "fromEnvironment",
+    "basedpyright.importStrategy": "fromEnvironment"
 }

AGENTS.md

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

CONTRIBUTING.md

@@ -11,18 +11,9 @@ To run EXO from source:
   ```bash
   brew install uv
   ```
-- [rust](https://github.com/rust-lang/rustup) (to build Rust bindings, nightly for now)
-  ```bash
-  curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh
-  rustup toolchain install nightly
-  ```
 - [macmon](https://github.com/vladkens/macmon) (for hardware monitoring on Apple Silicon)
-  Use the pinned fork revision used by this repo instead of Homebrew `macmon`.
   ```bash
-  cargo install --git https://github.com/vladkens/macmon \
-    --rev a1cd06b6cc0d5e61db24fd8832e74cd992097a7d \
-    macmon \
-    --force
+  brew install macmon
   ```
 
 ```bash
@@ -48,119 +39,6 @@ Write pure functions where possible. When adding new code, prefer Rust unless th
 
 Run `nix fmt` to auto-format your code before submitting.
 
-## Model Cards
-
-EXO uses TOML-based model cards to define model metadata and capabilities. Model cards are stored in:
-- `resources/inference_model_cards/` for text generation models
-- `resources/image_model_cards/` for image generation models
-- `~/.exo/custom_model_cards/` for user-added custom models
-
-### Adding a Model Card
-
-To add a new model, create a TOML file with the following structure:
-
-```toml
-model_id = "mlx-community/Llama-3.2-1B-Instruct-4bit"
-n_layers = 16
-hidden_size = 2048
-supports_tensor = true
-tasks = ["TextGeneration"]
-family = "llama"
-quantization = "4bit"
-base_model = "Llama 3.2 1B"
-capabilities = ["text"]
-
-[storage_size]
-in_bytes = 729808896
-```
-
-### Required Fields
-
-- `model_id`: Hugging Face model identifier
-- `n_layers`: Number of transformer layers
-- `hidden_size`: Hidden dimension size
-- `supports_tensor`: Whether the model supports tensor parallelism
-- `tasks`: List of supported tasks (`TextGeneration`, `TextToImage`, `ImageToImage`)
-- `family`: Model family (e.g., "llama", "deepseek", "qwen")
-- `quantization`: Quantization level (e.g., "4bit", "8bit", "bf16")
-- `base_model`: Human-readable base model name
-- `capabilities`: List of capabilities (e.g., `["text"]`, `["text", "thinking"]`)
-
-### Optional Fields
-
-- `components`: For multi-component models (like image models with separate text encoders and transformers)
-- `uses_cfg`: Whether the model uses classifier-free guidance (for image models)
-- `trust_remote_code`: Whether to allow remote code execution (defaults to `false` for security)
-
-### Capabilities
-
-The `capabilities` field defines what the model can do:
-- `text`: Standard text generation
-- `thinking`: Model supports chain-of-thought reasoning
-- `thinking_toggle`: Thinking can be enabled/disabled via `enable_thinking` parameter
-- `image_edit`: Model supports image-to-image editing (FLUX.1-Kontext)
-
-### Security Note
-
-By default, `trust_remote_code` is set to `false` for security. Only enable it if the model explicitly requires remote code execution from the Hugging Face hub.
-
-## API Adapters
-
-EXO supports multiple API formats through an adapter pattern. Adapters convert API-specific request formats to the internal `TextGenerationTaskParams` format and convert internal token chunks back to API-specific responses.
-
-### Adapter Architecture
-
-All adapters live in `src/exo/master/adapters/` and follow the same pattern:
-
-1. Convert API-specific requests to `TextGenerationTaskParams`
-2. Handle both streaming and non-streaming response generation
-3. Convert internal `TokenChunk` objects to API-specific formats
-4. Manage error handling and edge cases
-
-### Existing Adapters
-
-- `chat_completions.py`: OpenAI Chat Completions API
-- `claude.py`: Anthropic Claude Messages API
-- `responses.py`: OpenAI Responses API
-- `ollama.py`: Ollama API (for OpenWebUI compatibility)
-
-### Adding a New API Adapter
-
-To add support for a new API format:
-
-1. Create a new adapter file in `src/exo/master/adapters/`
-2. Implement a request conversion function:
-   ```python
-   def your_api_request_to_text_generation(
-       request: YourAPIRequest,
-   ) -> TextGenerationTaskParams:
-       # Convert API request to internal format
-       pass
-   ```
-3. Implement streaming response generation:
-   ```python
-   async def generate_your_api_stream(
-       command_id: CommandId,
-       chunk_stream: AsyncGenerator[TokenChunk | ErrorChunk | ToolCallChunk, None],
-   ) -> AsyncGenerator[str, None]:
-       # Convert internal chunks to API-specific streaming format
-       pass
-   ```
-4. Implement non-streaming response collection:
-   ```python
-   async def collect_your_api_response(
-       command_id: CommandId,
-       chunk_stream: AsyncGenerator[TokenChunk | ErrorChunk | ToolCallChunk, None],
-   ) -> AsyncGenerator[str]:
-       # Collect all chunks and return single response
-       pass
-   ```
-5. Register the adapter endpoints in `src/exo/master/api.py`
-
-The adapter pattern keeps API-specific logic isolated from core inference systems. Internal systems (worker, runner, event sourcing) only see `TextGenerationTaskParams` and `TokenChunk` objects - no API-specific types cross the adapter boundary.
-
-For detailed API documentation, see [docs/api.md](docs/api.md).
-
 ## Testing
 
 EXO relies heavily on manual testing at this point in the project, but this is evolving. Before submitting a change, test both before and after to demonstrate how your change improves behavior. Do the best you can with the hardware you have available - if you need help testing, ask and we'll do our best to assist. Add automated tests where possible - we're actively working to substantially improve our automated testing story.

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"
@@ -356,6 +353,31 @@ dependencies = [
  "generic-array",
 ]
 
+[[package]]
+name = "bon"
+version = "3.8.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ebeb9aaf9329dff6ceb65c689ca3db33dbf15f324909c60e4e5eef5701ce31b1"
+dependencies = [
+ "bon-macros",
+ "rustversion",
+]
+
+[[package]]
+name = "bon-macros"
+version = "3.8.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "77e9d642a7e3a318e37c2c9427b5a6a48aa1ad55dcd986f3034ab2239045a645"
+dependencies = [
+ "darling",
+ "ident_case",
+ "prettyplease",
+ "proc-macro2",
+ "quote",
+ "rustversion",
+ "syn 2.0.111",
+]
+
 [[package]]
 name = "bs58"
 version = "0.5.1"
@@ -519,6 +541,15 @@ 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"
@@ -669,6 +700,41 @@ dependencies = [
  "syn 2.0.111",
 ]
 
+[[package]]
+name = "darling"
+version = "0.21.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9cdf337090841a411e2a7f3deb9187445851f91b309c0c0a29e05f74a00a48c0"
+dependencies = [
+ "darling_core",
+ "darling_macro",
+]
+
+[[package]]
+name = "darling_core"
+version = "0.21.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1247195ecd7e3c85f83c8d2a366e4210d588e802133e1e355180a9870b517ea4"
+dependencies = [
+ "fnv",
+ "ident_case",
+ "proc-macro2",
+ "quote",
+ "strsim",
+ "syn 2.0.111",
+]
+
+[[package]]
+name = "darling_macro"
+version = "0.21.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d38308df82d1080de0afee5d069fa14b0326a88c14f15c5ccda35b4a6c414c81"
+dependencies = [
+ "darling_core",
+ "quote",
+ "syn 2.0.111",
+]
+
 [[package]]
 name = "data-encoding"
 version = "2.9.0"
@@ -740,6 +806,29 @@ 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 +999,22 @@ 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 +1030,6 @@ 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 +1138,7 @@ 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",
 ]
 
@@ -1540,6 +1625,12 @@ dependencies = [
  "zerovec",
 ]
 
+[[package]]
+name = "ident_case"
+version = "1.0.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b9e0384b61958566e926dc50660321d12159025e767c18e043daf26b70104c39"
+
 [[package]]
 name = "idna"
 version = "1.1.0"
@@ -1615,6 +1706,17 @@ 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"
@@ -1643,6 +1745,15 @@ dependencies = [
  "generic-array",
 ]
 
+[[package]]
+name = "internment"
+version = "0.8.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "636d4b0f6a39fd684effe2a73f5310df16a3fa7954c26d36833e98f44d1977a2"
+dependencies = [
+ "hashbrown 0.15.5",
+]
+
 [[package]]
 name = "inventory"
 version = "0.3.21"
@@ -1793,6 +1904,12 @@ 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 +2898,17 @@ 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 +2993,17 @@ 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"
@@ -3178,6 +3307,16 @@ dependencies = [
  "zerocopy",
 ]
 
+[[package]]
+name = "prettyplease"
+version = "0.2.37"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "479ca8adacdd7ce8f1fb39ce9ecccbfe93a3f1344b3d0d97f20bc0196208f62b"
+dependencies = [
+ "proc-macro2",
+ "syn 2.0.111",
+]
+
 [[package]]
 name = "primeorder"
 version = "0.13.6"
@@ -3225,14 +3364,28 @@ 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",
 ]
 
@@ -3587,6 +3740,12 @@ dependencies = [
  "yasna",
 ]
 
+[[package]]
+name = "recursion"
+version = "0.5.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9dba2197bf7b1d87b4dd460c195f4edeb45a94e82e8054f8d5f317c1f0e93ca1"
+
 [[package]]
 name = "redox_syscall"
 version = "0.5.18"
@@ -3673,6 +3832,16 @@ 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 +4706,24 @@ 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"
@@ -4626,6 +4807,15 @@ checksum = "06abde3611657adf66d383f00b093d7faecc7fa57071cce2578660c9f1010821"
 [[package]]
 name = "util"
 version = "0.0.1"
+dependencies = [
+ "bon",
+ "derive_more",
+ "extend",
+ "internment",
+ "once_cell",
+ "recursion",
+ "thiserror 2.0.17",
+]
 
 [[package]]
 name = "uuid"

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"

MISSED_THINGS.md

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

README.md

@@ -26,8 +26,6 @@ exo connects all your devices into an AI cluster. Not only does exo enable runni
 - **Topology-Aware Auto Parallel**: exo figures out the best way to split your model across all available devices based on a realtime view of your device topology. It takes into account device resources and network latency/bandwidth between each link.
 - **Tensor Parallelism**: exo supports sharding models, for up to 1.8x speedup on 2 devices and 3.2x speedup on 4 devices.
 - **MLX Support**: exo uses [MLX](https://github.com/ml-explore/mlx) as an inference backend and [MLX distributed](https://ml-explore.github.io/mlx/build/html/usage/distributed.html) for distributed communication.
-- **Multiple API Compatibility**: Compatible with OpenAI Chat Completions API, Claude Messages API, OpenAI Responses API, and Ollama API - use your existing tools and clients.
-- **Custom Model Support**: Load custom models from HuggingFace hub to expand the range of available models.
 
 ## Dashboard
 
@@ -74,31 +72,18 @@ 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 node
+  brew install uv macmon node
   ```
 - [rust](https://github.com/rust-lang/rustup) (to build Rust bindings, nightly for now)
 
@@ -106,17 +91,6 @@ Then restart the Nix daemon: `sudo launchctl kickstart -k system/org.nixos.nix-d
   curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh
   rustup toolchain install nightly
   ```
-- [macmon](https://github.com/vladkens/macmon) (for hardware monitoring on Apple Silicon)
-
-  Install the pinned fork revision used by this repo instead of Homebrew `macmon`.
-  Homebrew `macmon 0.6.1` still crashes on Apple M5.
-
-  ```bash
-  cargo install --git https://github.com/vladkens/macmon \
-    --rev a1cd06b6cc0d5e61db24fd8832e74cd992097a7d \
-    macmon \
-    --force
-  ```
 
 Clone the repo, build the dashboard, and run exo:
 
@@ -208,8 +182,6 @@ exo follows the [XDG Base Directory Specification](https://specifications.freede
 - **Configuration files**: `~/.config/exo/` (or `$XDG_CONFIG_HOME/exo/`)
 - **Data files**: `~/.local/share/exo/` (or `$XDG_DATA_HOME/exo/`)
 - **Cache files**: `~/.cache/exo/` (or `$XDG_CACHE_HOME/exo/`)
-- **Log files**: `~/.cache/exo/exo_log/` (with automatic log rotation)
-- **Custom model cards**: `~/.local/share/exo/custom_model_cards/`
 
 You can override these locations by setting the corresponding XDG environment variables.
 
@@ -289,51 +261,8 @@ After that, RDMA will be enabled in macOS and exo will take care of the rest.
 
 ---
 
-## Environment Variables
-
-exo supports several environment variables for configuration:
-
-| Variable | Description | Default |
-|----------|-------------|---------|
-| `EXO_DEFAULT_MODELS_DIR` | Default directory for model downloads and caches. Always first in the writable dirs list. | `~/.local/share/exo/models` (Linux) or `~/.exo/models` (macOS) |
-| `EXO_MODELS_DIRS` | Colon-separated additional writable directories for model downloads. Checked in order after the default; first with enough free space is used. | None |
-| `EXO_MODELS_READ_ONLY_DIRS` | Colon-separated read-only directories to search for pre-downloaded models (e.g., NFS mounts, shared storage). Models here cannot be deleted. | None |
-| `EXO_OFFLINE` | Run without internet connection (uses only local models) | `false` |
-| `EXO_ENABLE_IMAGE_MODELS` | Enable image model support | `false` |
-| `EXO_LIBP2P_NAMESPACE` | Custom namespace for cluster isolation | None |
-| `EXO_FAST_SYNCH` | Control MLX_METAL_FAST_SYNCH behavior (for JACCL backend) | Auto |
-| `EXO_TRACING_ENABLED` | Enable distributed tracing for performance analysis | `false` |
-
-**Example usage:**
-
-```bash
-# Use pre-downloaded models from NFS mount (read-only)
-EXO_MODELS_READ_ONLY_DIRS=/mnt/nfs/models:/opt/ai-models uv run exo
-
-# Download models to an external SSD (falls back to default dir if full)
-EXO_MODELS_DIRS=/Volumes/ExternalSSD/exo-models uv run exo
-
-# Run in offline mode
-EXO_OFFLINE=true uv run exo
-
-# Enable image models
-EXO_ENABLE_IMAGE_MODELS=true uv run exo
-
-# Use custom namespace for cluster isolation
-EXO_LIBP2P_NAMESPACE=my-dev-cluster uv run exo
-```
-
----
-
 ### Using the API
 
-exo provides multiple API-compatible interfaces for maximum compatibility with existing tools:
-
-- **OpenAI Chat Completions API** - Compatible with OpenAI clients
-- **Claude Messages API** - Compatible with Anthropic's Claude format
-- **OpenAI Responses API** - Compatible with OpenAI's Responses format
-- **Ollama API** - Compatible with Ollama and tools like OpenWebUI
-
 If you prefer to interact with exo via the API, here is an example creating an instance of a small model (`mlx-community/Llama-3.2-1B-Instruct-4bit`), sending a chat completions request and deleting the instance.
 
 ---
@@ -423,85 +352,14 @@ When you're done, delete the instance by its ID (find it via `/state` or `/insta
 curl -X DELETE http://localhost:52415/instance/YOUR_INSTANCE_ID
 ```
 
-### Claude Messages API Compatibility
-
-Use the Claude Messages API format with the `/v1/messages` endpoint:
-
-```bash
-curl -N -X POST http://localhost:52415/v1/messages \
-  -H 'Content-Type: application/json' \
-  -d '{
-    "model": "mlx-community/Llama-3.2-1B-Instruct-4bit",
-    "messages": [
-      {"role": "user", "content": "Hello"}
-    ],
-    "max_tokens": 1024,
-    "stream": true
-  }'
-```
-
-### OpenAI Responses API Compatibility
-
-Use the OpenAI Responses API format with the `/v1/responses` endpoint:
-
-```bash
-curl -N -X POST http://localhost:52415/v1/responses \
-  -H 'Content-Type: application/json' \
-  -d '{
-    "model": "mlx-community/Llama-3.2-1B-Instruct-4bit",
-    "messages": [
-      {"role": "user", "content": "Hello"}
-    ],
-    "stream": true
-  }'
-```
-
-### Ollama API Compatibility
-
-exo supports Ollama API endpoints for compatibility with tools like OpenWebUI:
-
-```bash
-# Ollama chat
-curl -X POST http://localhost:52415/ollama/api/chat \
-  -H 'Content-Type: application/json' \
-  -d '{
-    "model": "mlx-community/Llama-3.2-1B-Instruct-4bit",
-    "messages": [
-      {"role": "user", "content": "Hello"}
-    ],
-    "stream": false
-  }'
-
-# List models (Ollama format)
-curl http://localhost:52415/ollama/api/tags
-```
-
-### Custom Model Loading from HuggingFace
-
-You can add custom models from the HuggingFace hub:
-
-```bash
-curl -X POST http://localhost:52415/models/add \
-  -H 'Content-Type: application/json' \
-  -d '{
-    "model_id": "mlx-community/my-custom-model"
-  }'
-```
-
-**Security Note:**
-
-Custom models requiring `trust_remote_code` in their configuration must be explicitly enabled (default is false) for security. Only enable this if you trust the model's remote code execution. Models are fetched from HuggingFace and stored locally as custom model cards.
-
 **Other useful API endpoints*:**
 
 - List all models: `curl http://localhost:52415/models`
-- List downloaded models only: `curl http://localhost:52415/models?status=downloaded`
-- Search HuggingFace: `curl "http://localhost:52415/models/search?query=llama&limit=10"`
 - Inspect instance IDs and deployment state: `curl http://localhost:52415/state`
 
 For further details, see:
 
-- API documentation in [docs/api.md](docs/api.md).
+- API basic documentation in [docs/api.md](docs/api.md).
 - API types and endpoints in [src/exo/master/api.py](src/exo/master/api.py).
 
 ---
@@ -560,4 +418,4 @@ On macOS, exo uses the GPU. On Linux, exo currently runs on CPU. We are working
 
 ## Contributing
 
-See [CONTRIBUTING.md](CONTRIBUTING.md) for guidelines on how to contribute to exo.
+See [CONTRIBUTING.md](CONTRIBUTING.md) for guidelines on how to contribute to exo.

TODO.md

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

app/EXO/EXO/ContentView.swift

@@ -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 {
@@ -512,45 +563,21 @@ struct ContentView: View {
     }
 
     private var rdmaStatusView: some View {
-        let rdmaStatuses = stateService.latestSnapshot?.nodeRdmaCtl ?? [:]
-        let localNodeId = stateService.localNodeId
-        let nodeProfiles = stateService.latestSnapshot?.nodeProfiles ?? [:]
-        let localDevices = networkStatusService.status.localRdmaDevices
-        let localPorts = networkStatusService.status.localRdmaActivePorts
-
+        let rdma = networkStatusService.status.rdmaStatus
         return VStack(alignment: .leading, spacing: 1) {
-            if rdmaStatuses.isEmpty {
-                Text("Cluster RDMA: No data")
-                    .font(.caption2)
-                    .foregroundColor(.secondary)
-            } else {
-                Text("Cluster RDMA Status:")
-                    .font(.caption2)
-                    .foregroundColor(.secondary)
-                ForEach(Array(rdmaStatuses.keys.sorted()), id: \.self) { nodeId in
-                    if let status = rdmaStatuses[nodeId] {
-                        let nodeName =
-                            nodeProfiles[nodeId]?.friendlyName ?? String(nodeId.prefix(8))
-                        let isLocal = nodeId == localNodeId
-                        let prefix = isLocal ? "  \(nodeName) (local):" : "  \(nodeName):"
-                        let statusText = status.enabled ? "Enabled" : "Disabled"
-                        let color: Color = status.enabled ? .green : .orange
-                        Text("\(prefix) \(statusText)")
-                            .font(.caption2)
-                            .foregroundColor(color)
-                    }
-                }
-            }
-            if !localDevices.isEmpty {
-                Text("  Local Devices: \(localDevices.joined(separator: ", "))")
+            Text("RDMA: \(rdmaStatusText(rdma))")
+                .font(.caption2)
+                .foregroundColor(rdmaStatusColor(rdma))
+            if !rdma.devices.isEmpty {
+                Text("  Devices: \(rdma.devices.joined(separator: ", "))")
                     .font(.caption2)
                     .foregroundColor(.secondary)
             }
-            if !localPorts.isEmpty {
-                Text("  Local Active Ports:")
+            if !rdma.activePorts.isEmpty {
+                Text("  Active Ports:")
                     .font(.caption2)
                     .foregroundColor(.secondary)
-                ForEach(localPorts, id: \.device) { port in
+                ForEach(rdma.activePorts, id: \.device) { port in
                     Text("    \(port.device) port \(port.port): \(port.state)")
                         .font(.caption2)
                         .foregroundColor(.green)
@@ -559,125 +586,62 @@ 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))
-                    )
-                }
-                .buttonStyle(.plain)
+    private func rdmaStatusText(_ rdma: RDMAStatus) -> String {
+        switch rdma.rdmaCtlEnabled {
+        case .some(true):
+            return "Enabled"
+        case .some(false):
+            return "Disabled"
+        case nil:
+            return rdma.devices.isEmpty ? "Not Available" : "Available"
+        }
+    }
 
-            case .prompting:
-                VStack(alignment: .leading, spacing: 6) {
-                    VStack(alignment: .leading, spacing: 2) {
-                        Text("Tell us what went wrong (optional)")
-                            .font(.caption2)
-                            .foregroundColor(.secondary)
-                        Text(
-                            "A quick description of what you were doing and what happened helps us track down the bug for you."
-                        )
-                        .font(.caption2)
-                        .foregroundColor(.secondary)
-                        .opacity(0.8)
-                        .fixedSize(horizontal: false, vertical: true)
-                    }
-                    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)
-                    }
+    private func rdmaStatusColor(_ rdma: RDMAStatus) -> Color {
+        switch rdma.rdmaCtlEnabled {
+        case .some(true):
+            return .green
+        case .some(false):
+            return .orange
+        case nil:
+            return rdma.devices.isEmpty ? .secondary : .green
+        }
+    }
+
+    private var sendBugReportButton: some View {
+        VStack(alignment: .leading, spacing: 4) {
+            Button {
+                Task {
+                    await sendBugReport()
                 }
-                .padding(8)
+            } label: {
+                HStack {
+                    if bugReportInFlight {
+                        ProgressView()
+                            .scaleEffect(0.6)
+                    }
+                    Text("Send Bug Report")
+                        .font(.caption)
+                        .fontWeight(.semibold)
+                    Spacer()
+                }
+                .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> {
@@ -721,58 +685,16 @@ 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

@@ -14,6 +14,7 @@ import SwiftUI
 import UserNotifications
 import os.log
 
+@main
 struct EXOApp: App {
     @StateObject private var controller: ExoProcessController
     @StateObject private var stateService: ClusterStateService
@@ -21,9 +22,7 @@ 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 +44,12 @@ 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 +63,8 @@ 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

@@ -4,30 +4,7 @@ import Foundation
 
 private let customNamespaceKey = "EXOCustomNamespace"
 private let hfTokenKey = "EXOHFToken"
-private let hfEndpointKey = "EXOHFEndpoint"
 private let enableImageModelsKey = "EXOEnableImageModels"
-private let offlineModeKey = "EXOOfflineMode"
-private let fastSynchEnabledKey = "EXOFastSynchEnabled"
-private let onboardingCompletedKey = "EXOOnboardingCompleted"
-private let defaultModelsDirKey = "EXODefaultModelsDir"
-private let additionalModelsDirsKey = "EXOAdditionalModelsDirs"
-private let readOnlyModelsDirsKey = "EXOReadOnlyModelsDirs"
-private let customEnvironmentVariablesKey = "EXOCustomEnvironmentVariables"
-
-/// A user-defined environment variable that is injected into the exo child
-/// process at launch. Used as an escape hatch for env vars that don't have
-/// first-class typed UI in Settings.
-struct CustomEnvironmentVariable: Codable, Identifiable, Equatable {
-    var id: UUID
-    var key: String
-    var value: String
-
-    init(id: UUID = UUID(), key: String = "", value: String = "") {
-        self.id = id
-        self.key = key
-        self.value = value
-    }
-}
 
 @MainActor
 final class ExoProcessController: ObservableObject {
@@ -51,10 +28,6 @@ final class ExoProcessController: ObservableObject {
         }
     }
 
-    static let exoDirectoryURL: URL = {
-        URL(fileURLWithPath: NSHomeDirectory()).appendingPathComponent(".exo")
-    }()
-
     @Published private(set) var status: Status = .stopped
     @Published private(set) var lastError: String?
     @Published private(set) var launchCountdownSeconds: Int?
@@ -74,14 +47,6 @@ final class ExoProcessController: ObservableObject {
             UserDefaults.standard.set(hfToken, forKey: hfTokenKey)
         }
     }
-    @Published var hfEndpoint: String = {
-        return UserDefaults.standard.string(forKey: hfEndpointKey) ?? ""
-    }()
-    {
-        didSet {
-            UserDefaults.standard.set(hfEndpoint, forKey: hfEndpointKey)
-        }
-    }
     @Published var enableImageModels: Bool = {
         return UserDefaults.standard.bool(forKey: enableImageModelsKey)
     }()
@@ -90,71 +55,6 @@ 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)
-        }
-    }
-    @Published var fastSynchEnabled: Bool = {
-        if UserDefaults.standard.object(forKey: fastSynchEnabledKey) == nil {
-            return true
-        }
-        return UserDefaults.standard.bool(forKey: fastSynchEnabledKey)
-    }()
-    {
-        didSet {
-            UserDefaults.standard.set(fastSynchEnabled, forKey: fastSynchEnabledKey)
-        }
-    }
-    @Published var defaultModelsDir: String = {
-        return UserDefaults.standard.string(forKey: defaultModelsDirKey) ?? ""
-    }()
-    {
-        didSet {
-            UserDefaults.standard.set(defaultModelsDir, forKey: defaultModelsDirKey)
-        }
-    }
-    @Published var additionalModelsDirs: String = {
-        return UserDefaults.standard.string(forKey: additionalModelsDirsKey) ?? ""
-    }()
-    {
-        didSet {
-            UserDefaults.standard.set(additionalModelsDirs, forKey: additionalModelsDirsKey)
-        }
-    }
-    @Published var readOnlyModelsDirs: String = {
-        return UserDefaults.standard.string(forKey: readOnlyModelsDirsKey) ?? ""
-    }()
-    {
-        didSet {
-            UserDefaults.standard.set(readOnlyModelsDirs, forKey: readOnlyModelsDirsKey)
-        }
-    }
-    @Published var customEnvironmentVariables: [CustomEnvironmentVariable] = {
-        guard
-            let data = UserDefaults.standard.data(forKey: customEnvironmentVariablesKey),
-            let decoded = try? JSONDecoder().decode(
-                [CustomEnvironmentVariable].self, from: data
-            )
-        else {
-            return []
-        }
-        return decoded
-    }()
-    {
-        didSet {
-            guard let data = try? JSONEncoder().encode(customEnvironmentVariables) else {
-                return
-            }
-            UserDefaults.standard.set(data, forKey: customEnvironmentVariablesKey)
-        }
-    }
-
-    /// 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?
@@ -178,11 +78,7 @@ final class ExoProcessController: ObservableObject {
 
             let child = Process()
             child.executableURL = executableURL
-            let exoHomeURL = Self.exoDirectoryURL
-            try? FileManager.default.createDirectory(
-                at: exoHomeURL, withIntermediateDirectories: true
-            )
-            child.currentDirectoryURL = exoHomeURL
+            child.currentDirectoryURL = runtimeURL
             child.environment = makeEnvironment(for: runtimeURL)
 
             child.standardOutput = FileHandle.nullDevice
@@ -209,9 +105,6 @@ 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")
@@ -225,37 +118,11 @@ 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() {
@@ -263,17 +130,6 @@ 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)))
@@ -356,16 +212,9 @@ final class ExoProcessController: ObservableObject {
         if !hfToken.isEmpty {
             environment["HF_TOKEN"] = hfToken
         }
-        if !hfEndpoint.isEmpty {
-            environment["HF_ENDPOINT"] = hfEndpoint
-        }
         if enableImageModels {
             environment["EXO_ENABLE_IMAGE_MODELS"] = "true"
         }
-        if offlineMode {
-            environment["EXO_OFFLINE"] = "true"
-        }
-        environment["EXO_FAST_SYNCH"] = fastSynchEnabled ? "true" : "false"
 
         var paths: [String] = []
         if let existing = environment["PATH"], !existing.isEmpty {
@@ -390,29 +239,6 @@ final class ExoProcessController: ObservableObject {
         }
 
         environment["PATH"] = paths.joined(separator: ":")
-
-        let trimmedDefaultModelsDir = defaultModelsDir.trimmingCharacters(in: .whitespaces)
-        if !trimmedDefaultModelsDir.isEmpty {
-            environment["EXO_DEFAULT_MODELS_DIR"] = trimmedDefaultModelsDir
-        }
-        let trimmedAdditionalModelsDirs = additionalModelsDirs.trimmingCharacters(in: .whitespaces)
-        if !trimmedAdditionalModelsDirs.isEmpty {
-            environment["EXO_MODELS_DIRS"] = trimmedAdditionalModelsDirs
-        }
-        let trimmedReadOnlyModelsDirs = readOnlyModelsDirs.trimmingCharacters(in: .whitespaces)
-        if !trimmedReadOnlyModelsDirs.isEmpty {
-            environment["EXO_MODELS_READ_ONLY_DIRS"] = trimmedReadOnlyModelsDirs
-        }
-
-        // Apply user-defined arbitrary environment variables last so that
-        // power users can override any of the typed fields above when
-        // necessary. Empty keys are ignored.
-        for variable in customEnvironmentVariables {
-            let trimmedKey = variable.key.trimmingCharacters(in: .whitespaces)
-            guard !trimmedKey.isEmpty else { continue }
-            environment[trimmedKey] = variable.value
-        }
-
         return environment
     }
 

app/EXO/EXO/Info.plist

@@ -9,7 +9,7 @@
 	<key>EXOBuildCommit</key>
 	<string>$(EXO_BUILD_COMMIT)</string>
 	<key>EXOBugReportPresignedUrlEndpoint</key>
-	<string>https://reports.exolabs.net/presigned-urls</string>
+	<string>$(EXO_BUG_REPORT_PRESIGNED_URL_ENDPOINT)</string>
 	<key>NSLocalNetworkUsageDescription</key>
 	<string>EXO needs local network access to discover and connect to other devices in your cluster for distributed AI inference.</string>
 	<key>NSBonjourServices</key>

app/EXO/EXO/Models/ClusterState.swift

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

app/EXO/EXO/Services/BugReportService.swift

@@ -38,19 +38,22 @@ 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)
         let prefix = "reports/\(dayPrefix)/\(timestamp)/"
 
-        let logFiles = readAllLogs()
+        let logData = readLog()
         let ifconfigText = try await captureIfconfig()
         let hostName = Host.current().localizedName ?? "unknown"
         let debugInfo = readDebugInfo()
 
-        let stateData = try await fetch(url: baseURL.appendingPathComponent("state"))
+        async let stateResult = fetch(url: baseURL.appendingPathComponent("state"))
+        async let eventsResult = fetch(url: baseURL.appendingPathComponent("events"))
+
+        let stateData = try await stateResult
+        let eventsData = try await eventsResult
 
         // Extract cluster TB bridge status from exo state
         let clusterTbBridgeStatus = extractClusterTbBridgeStatus(from: stateData)
@@ -61,23 +64,15 @@ struct BugReportService {
             ifconfig: ifconfigText,
             debugInfo: debugInfo,
             isManual: isManual,
-            clusterTbBridgeStatus: clusterTbBridgeStatus,
-            userDescription: userDescription
+            clusterTbBridgeStatus: clusterTbBridgeStatus
         )
 
-        let eventLogFiles = readAllEventLogs()
-
-        var uploads: [(path: String, data: Data?)] = logFiles.map { (path, data) in
-            ("\(prefix)\(path)", data)
-        }
-        uploads.append(
-            contentsOf: eventLogFiles.map { (path, data) in
-                ("\(prefix)\(path)", data as Data?)
-            })
-        uploads.append(contentsOf: [
+        let uploads: [(path: String, data: Data?)] = [
+            ("\(prefix)exo.log", logData),
             ("\(prefix)state.json", stateData),
+            ("\(prefix)events.json", eventsData),
             ("\(prefix)report.json", reportJSON),
-        ])
+        ]
 
         let uploadItems: [(key: String, body: Data)] = uploads.compactMap { item in
             guard let body = item.data else { return nil }
@@ -154,40 +149,11 @@ struct BugReportService {
         return decoded.urls
     }
 
-    private func readAllLogs() -> [(path: String, data: Data)] {
-        let dir = URL(fileURLWithPath: NSHomeDirectory())
+    private func readLog() -> Data? {
+        let logURL = URL(fileURLWithPath: NSHomeDirectory())
             .appendingPathComponent(".exo")
-            .appendingPathComponent("exo_log")
-        var results: [(path: String, data: Data)] = []
-
-        let contents = (try? FileManager.default.contentsOfDirectory(atPath: dir.path)) ?? []
-        for name in contents {
-            if let data = try? Data(contentsOf: dir.appendingPathComponent(name)) {
-                results.append(("exo_log/\(name)", data))
-            }
-        }
-
-        return results
-    }
-
-    private func readAllEventLogs() -> [(path: String, data: Data)] {
-        let eventLogDir = URL(fileURLWithPath: NSHomeDirectory())
-            .appendingPathComponent(".exo")
-            .appendingPathComponent("event_log")
-        var results: [(path: String, data: Data)] = []
-
-        for subdir in ["master", "api"] {
-            let dir = eventLogDir.appendingPathComponent(subdir)
-            let contents =
-                (try? FileManager.default.contentsOfDirectory(atPath: dir.path)) ?? []
-            for name in contents where name.hasPrefix("events.") {
-                if let data = try? Data(contentsOf: dir.appendingPathComponent(name)) {
-                    results.append(("event_log/\(subdir)/\(name)", data))
-                }
-            }
-        }
-
-        return results
+            .appendingPathComponent("exo.log")
+        return try? Data(contentsOf: logURL)
     }
 
     private func captureIfconfig() async throws -> String {
@@ -308,8 +274,7 @@ 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 +291,6 @@ 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/Services/NetworkSetupHelper.swift

@@ -288,61 +288,6 @@ enum NetworkSetupHelper {
         """
     }
 
-    /// Direct install without GUI (requires root).
-    /// Returns true on success, false on failure.
-    static func installDirectly() -> Bool {
-        let script = makeInstallerScript()
-        return runShellDirectly(script)
-    }
-
-    /// Direct uninstall without GUI (requires root).
-    /// Returns true on success, false on failure.
-    static func uninstallDirectly() -> Bool {
-        let script = makeUninstallScript()
-        return runShellDirectly(script)
-    }
-
-    /// Run a shell script directly via Process (no AppleScript, requires root).
-    /// Returns true on success, false on failure.
-    private static func runShellDirectly(_ script: String) -> Bool {
-        let process = Process()
-        process.executableURL = URL(fileURLWithPath: "/bin/bash")
-        process.arguments = ["-c", script]
-
-        let outputPipe = Pipe()
-        let errorPipe = Pipe()
-        process.standardOutput = outputPipe
-        process.standardError = errorPipe
-
-        do {
-            try process.run()
-            process.waitUntilExit()
-
-            let outputData = outputPipe.fileHandleForReading.readDataToEndOfFile()
-            let errorData = errorPipe.fileHandleForReading.readDataToEndOfFile()
-
-            if let output = String(data: outputData, encoding: .utf8), !output.isEmpty {
-                print(output)
-            }
-            if let errorOutput = String(data: errorData, encoding: .utf8), !errorOutput.isEmpty {
-                fputs(errorOutput, stderr)
-            }
-
-            if process.terminationStatus == 0 {
-                logger.info("Shell script completed successfully")
-                return true
-            } else {
-                logger.error("Shell script failed with exit code \(process.terminationStatus)")
-                return false
-            }
-        } catch {
-            logger.error(
-                "Failed to run shell script: \(error.localizedDescription, privacy: .public)")
-            fputs("Error: \(error.localizedDescription)\n", stderr)
-            return false
-        }
-    }
-
     private static func runShellAsAdmin(_ script: String) throws {
         let escapedScript =
             script

app/EXO/EXO/Services/NetworkStatusService.swift

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

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

@@ -1,764 +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 pendingHFEndpoint: String = ""
-    @State private var pendingEnableImageModels = false
-    @State private var pendingOfflineMode = false
-    @State private var pendingFastSynchEnabled = false
-    @State private var pendingDefaultModelsDir: String = ""
-    @State private var pendingAdditionalModelsDirs: String = ""
-    @State private var pendingReadOnlyModelsDirs: String = ""
-    @State private var pendingCustomEnvironmentVariables: [CustomEnvironmentVariable] = []
-    @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")
-                }
-            environmentTab
-                .tabItem {
-                    Label("Environment", systemImage: "terminal")
-                }
-            aboutTab
-                .tabItem {
-                    Label("About", systemImage: "info.circle")
-                }
-        }
-        .frame(width: 640, height: 560)
-        .onAppear {
-            pendingNamespace = controller.customNamespace
-            pendingHFToken = controller.hfToken
-            pendingHFEndpoint = controller.hfEndpoint
-            pendingEnableImageModels = controller.enableImageModels
-            pendingOfflineMode = controller.offlineMode
-            pendingFastSynchEnabled = controller.fastSynchEnabled
-            pendingDefaultModelsDir = controller.defaultModelsDir
-            pendingAdditionalModelsDirs = controller.additionalModelsDirs
-            pendingReadOnlyModelsDirs = controller.readOnlyModelsDirs
-            pendingCustomEnvironmentVariables = controller.customEnvironmentVariables
-            needsRestart = false
-        }
-    }
-
-    // MARK: - General Tab
-
-    private var generalTab: some View {
-        Form {
-            Section {
-                LabeledContent("Cluster Namespace") {
-                    TextField("", text: $pendingNamespace, prompt: Text("default"))
-                        .textFieldStyle(.roundedBorder)
-                        .frame(width: 260)
-                }
-                Text("Nodes with the same namespace form a cluster. Leave empty for default.")
-                    .font(.caption)
-                    .foregroundColor(.secondary)
-            }
-
-            Section {
-                LabeledContent("HuggingFace Token") {
-                    SecureField("", text: $pendingHFToken, prompt: Text("optional"))
-                        .textFieldStyle(.roundedBorder)
-                        .frame(width: 260)
-                }
-                Text("Required for gated models. Get yours at huggingface.co/settings/tokens")
-                    .font(.caption)
-                    .foregroundColor(.secondary)
-            }
-
-            Section {
-                LabeledContent("HuggingFace Endpoint") {
-                    TextField("", text: $pendingHFEndpoint, prompt: Text("default"))
-                        .textFieldStyle(.roundedBorder)
-                        .frame(width: 260)
-                }
-                Text("Defaults to huggingface.co. Use a mirror (e.g. hf-mirror.com) for China.")
-                    .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("Performance") {
-                Toggle("Fast Synch Enabled", isOn: $pendingFastSynchEnabled)
-                Text(
-                    "Experimental: enables fast CPU to GPU synchronization. Can sometimes cause a \"GPU lock\" where inference hangs for ~10 seconds before starting. Necessary for low latency with RDMA and Tensor Parallelism."
-                )
-                .font(.caption)
-                .foregroundColor(.secondary)
-
-                HStack {
-                    Spacer()
-                    Button("Save & Restart") {
-                        applyAdvancedSettings()
-                    }
-                    .disabled(!hasAdvancedChanges)
-                }
-            }
-
-            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: - Environment Tab
-
-    private var environmentTab: some View {
-        Form {
-            Section("Models Directories") {
-                LabeledContent("Default Models Directory") {
-                    TextField(
-                        "",
-                        text: $pendingDefaultModelsDir,
-                        prompt: Text("~/.exo/models")
-                    )
-                    .textFieldStyle(.roundedBorder)
-                    .font(.system(.body, design: .monospaced))
-                    .frame(width: 260)
-                }
-                Text("Sets EXO_DEFAULT_MODELS_DIR. Where models are downloaded.")
-                    .font(.caption)
-                    .foregroundColor(.secondary)
-
-                LabeledContent("Additional Directories") {
-                    TextField(
-                        "",
-                        text: $pendingAdditionalModelsDirs,
-                        prompt: Text("optional, colon-separated")
-                    )
-                    .textFieldStyle(.roundedBorder)
-                    .font(.system(.body, design: .monospaced))
-                    .frame(width: 260)
-                }
-                Text("Sets EXO_MODELS_DIRS. Extra writable model directories.")
-                    .font(.caption)
-                    .foregroundColor(.secondary)
-
-                LabeledContent("Read-Only Directories") {
-                    TextField(
-                        "",
-                        text: $pendingReadOnlyModelsDirs,
-                        prompt: Text("optional, colon-separated")
-                    )
-                    .textFieldStyle(.roundedBorder)
-                    .font(.system(.body, design: .monospaced))
-                    .frame(width: 260)
-                }
-                Text("Sets EXO_MODELS_READ_ONLY_DIRS. Never written to.")
-                    .font(.caption)
-                    .foregroundColor(.secondary)
-            }
-
-            Section("Custom Environment Variables") {
-                Text(
-                    "Escape hatch for env vars that don't have typed fields above. "
-                        + "Values here override the typed fields on conflict."
-                )
-                .font(.caption)
-                .foregroundColor(.secondary)
-
-                if pendingCustomEnvironmentVariables.isEmpty {
-                    Text("No custom variables.")
-                        .font(.caption)
-                        .foregroundColor(.secondary)
-                } else {
-                    ForEach($pendingCustomEnvironmentVariables) { $variable in
-                        HStack(alignment: .center, spacing: 8) {
-                            VStack(spacing: 4) {
-                                TextField("key", text: $variable.key)
-                                    .labelsHidden()
-                                    .textFieldStyle(.roundedBorder)
-                                    .font(.system(.body, design: .monospaced))
-                                TextField("value", text: $variable.value)
-                                    .labelsHidden()
-                                    .textFieldStyle(.roundedBorder)
-                                    .font(.system(.body, design: .monospaced))
-                            }
-                            VStack(spacing: 4) {
-                                Button {
-                                    pendingCustomEnvironmentVariables.removeAll {
-                                        $0.id == variable.id
-                                    }
-                                } label: {
-                                    Image(systemName: "minus.circle")
-                                }
-                                .buttonStyle(.borderless)
-                                .help("Remove variable")
-                                if !isValidEnvironmentVariableName(variable.key) {
-                                    Image(systemName: "exclamationmark.triangle.fill")
-                                        .foregroundColor(.orange)
-                                        .help(
-                                            "Invalid environment variable name. "
-                                                + "Must match [A-Za-z_][A-Za-z0-9_]*."
-                                        )
-                                }
-                            }
-                        }
-                    }
-                }
-
-                HStack {
-                    Button {
-                        pendingCustomEnvironmentVariables.append(
-                            CustomEnvironmentVariable()
-                        )
-                    } label: {
-                        Label("Add Variable", systemImage: "plus")
-                    }
-                    Spacer()
-                }
-            }
-
-            Section {
-                HStack {
-                    Spacer()
-                    Button("Save & Restart") {
-                        applyEnvironmentSettings()
-                    }
-                    .disabled(!hasEnvironmentChanges)
-                }
-            }
-        }
-        .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 components:
-
-            • Network configuration daemon
-            • Launch at login registration
-            • EXO network location
-            • EXO data directory (~/.exo)
-
-            The app will be moved to Trash.
-            """
-        alert.alertStyle = .warning
-
-        let checkbox = NSButton(
-            checkboxWithTitle: "Keep downloaded models (~/.exo/models)",
-            target: nil, action: nil)
-        checkbox.state = .off
-        checkbox.sizeToFit()
-        alert.accessoryView = checkbox
-
-        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(keepModels: checkbox.state == .on)
-        }
-    }
-
-    private func performUninstall(keepModels: Bool) {
-        uninstallInProgress = true
-
-        controller.cancelPendingLaunch()
-        controller.stop()
-        stateService.stopPolling()
-
-        DispatchQueue.global(qos: .utility).async {
-            do {
-                try NetworkSetupHelper.uninstall()
-                try Self.removeExoDirectory(keepModels: keepModels)
-
-                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 static func removeExoDirectory(keepModels: Bool) throws {
-        let fm = FileManager.default
-        let exoDir = ExoProcessController.exoDirectoryURL
-        guard fm.fileExists(atPath: exoDir.path) else { return }
-
-        if !keepModels {
-            try fm.removeItem(at: exoDir)
-            return
-        }
-
-        let contents = try fm.contentsOfDirectory(
-            at: exoDir, includingPropertiesForKeys: nil, options: [])
-        for entry in contents where entry.lastPathComponent != "models" {
-            try? fm.removeItem(at: entry)
-        }
-    }
-
-    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
-            || pendingHFEndpoint != controller.hfEndpoint
-            || pendingOfflineMode != controller.offlineMode
-    }
-
-    private var hasModelChanges: Bool {
-        pendingEnableImageModels != controller.enableImageModels
-    }
-
-    private var hasAdvancedChanges: Bool {
-        pendingFastSynchEnabled != controller.fastSynchEnabled
-    }
-
-    private var hasEnvironmentChanges: Bool {
-        pendingDefaultModelsDir != controller.defaultModelsDir
-            || pendingAdditionalModelsDirs != controller.additionalModelsDirs
-            || pendingReadOnlyModelsDirs != controller.readOnlyModelsDirs
-            || pendingCustomEnvironmentVariables != controller.customEnvironmentVariables
-    }
-
-    private func applyGeneralSettings() {
-        controller.customNamespace = pendingNamespace
-        controller.hfToken = pendingHFToken
-        controller.hfEndpoint = pendingHFEndpoint
-        controller.offlineMode = pendingOfflineMode
-        restartIfRunning()
-    }
-
-    private func applyModelSettings() {
-        controller.enableImageModels = pendingEnableImageModels
-        restartIfRunning()
-    }
-
-    private func applyAdvancedSettings() {
-        controller.fastSynchEnabled = pendingFastSynchEnabled
-        restartIfRunning()
-    }
-
-    private func applyEnvironmentSettings() {
-        controller.defaultModelsDir = pendingDefaultModelsDir.trimmingCharacters(
-            in: .whitespaces)
-        controller.additionalModelsDirs = pendingAdditionalModelsDirs.trimmingCharacters(
-            in: .whitespaces)
-        controller.readOnlyModelsDirs = pendingReadOnlyModelsDirs.trimmingCharacters(
-            in: .whitespaces)
-
-        pendingDefaultModelsDir = controller.defaultModelsDir
-        pendingAdditionalModelsDirs = controller.additionalModelsDirs
-        pendingReadOnlyModelsDirs = controller.readOnlyModelsDirs
-
-        // Trim whitespace from keys and drop empty ones so that the stored
-        // form matches what is actually injected into the child process and
-        // hasEnvironmentChanges doesn't show a stale diff after save.
-        let trimmed: [CustomEnvironmentVariable] =
-            pendingCustomEnvironmentVariables.compactMap { variable in
-                let key = variable.key.trimmingCharacters(in: .whitespaces)
-                guard !key.isEmpty else { return nil }
-                return CustomEnvironmentVariable(
-                    id: variable.id, key: key, value: variable.value
-                )
-            }
-
-        // De-duplicate keys, keeping the last occurrence. This matches the
-        // effective semantics of the dictionary assignment in
-        // ExoProcessController.makeEnvironment and avoids silently losing
-        // visible rows after save.
-        var seenKeys = Set<String>()
-        var deduplicatedReversed: [CustomEnvironmentVariable] = []
-        for variable in trimmed.reversed() {
-            if seenKeys.insert(variable.key).inserted {
-                deduplicatedReversed.append(variable)
-            }
-        }
-        let sanitized = Array(deduplicatedReversed.reversed())
-
-        pendingCustomEnvironmentVariables = sanitized
-        controller.customEnvironmentVariables = sanitized
-
-        restartIfRunning()
-    }
-
-    /// Validates a POSIX-style environment variable name:
-    /// `[A-Za-z_][A-Za-z0-9_]*`. Uses an ASCII-only charset so that
-    /// Unicode letters (e.g. `ñ`, Cyrillic) are rejected in line with what
-    /// the help tooltip advertises. Empty strings are treated as valid
-    /// here so that a freshly added blank row does not immediately look
-    /// broken; the save step filters empty keys out instead.
-    private func isValidEnvironmentVariableName(_ key: String) -> Bool {
-        if key.isEmpty { return true }
-        let headAllowed = CharacterSet(
-            charactersIn: "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz_"
-        )
-        let tailAllowed = headAllowed.union(CharacterSet(charactersIn: "0123456789"))
-        guard let first = key.unicodeScalars.first, headAllowed.contains(first) else {
-            return false
-        }
-        for scalar in key.unicodeScalars.dropFirst() {
-            if !tailAllowed.contains(scalar) { return false }
-        }
-        return true
-    }
-
-    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: 640, height: 560),
-            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
-    }
-}

app/EXO/EXO/main.swift

@@ -1,85 +0,0 @@
-//
-//  main.swift
-//  EXO
-//
-//  Created by Jake Hillion on 2026-02-03.
-//
-
-import Foundation
-
-/// Command line options for the EXO app
-enum CLICommand {
-    case install
-    case uninstall
-    case help
-    case none
-}
-
-/// Parse command line arguments to determine the CLI command
-func parseArguments() -> CLICommand {
-    let args = CommandLine.arguments
-    if args.contains("--help") || args.contains("-h") {
-        return .help
-    }
-    if args.contains("--install") {
-        return .install
-    }
-    if args.contains("--uninstall") {
-        return .uninstall
-    }
-    return .none
-}
-
-/// Print usage information
-func printUsage() {
-    let programName = (CommandLine.arguments.first as NSString?)?.lastPathComponent ?? "EXO"
-    print(
-        """
-        Usage: \(programName) [OPTIONS]
-
-        Options:
-          --install     Install EXO network configuration (requires root)
-          --uninstall   Uninstall EXO network configuration (requires root)
-          --help, -h    Show this help message
-
-        When run without options, starts the normal GUI application.
-
-        Examples:
-          sudo \(programName) --install    Install network components as root
-          sudo \(programName) --uninstall  Remove network components as root
-        """)
-}
-
-/// Check if running as root
-func isRunningAsRoot() -> Bool {
-    return getuid() == 0
-}
-
-// Main entry point
-let command = parseArguments()
-
-switch command {
-case .help:
-    printUsage()
-    exit(0)
-
-case .install:
-    if !isRunningAsRoot() {
-        fputs("Error: --install requires root privileges. Run with sudo.\n", stderr)
-        exit(1)
-    }
-    let success = NetworkSetupHelper.installDirectly()
-    exit(success ? 0 : 1)
-
-case .uninstall:
-    if !isRunningAsRoot() {
-        fputs("Error: --uninstall requires root privileges. Run with sudo.\n", stderr)
-        exit(1)
-    }
-    let success = NetworkSetupHelper.uninstallDirectly()
-    exit(success ? 0 : 1)
-
-case .none:
-    // Start normal GUI application
-    EXOApp.main()
-}

app/EXO/uninstall-exo.sh

@@ -3,55 +3,25 @@
 # EXO Uninstaller Script
 #
 # This script removes all EXO system components that persist after deleting the app.
-# Run with: sudo ./uninstall-exo.sh [--keep-models]
-#
-# Options:
-#   --keep-models   Preserve ~/.exo/models when removing the EXO data directory.
+# Run with: sudo ./uninstall-exo.sh
 #
 # Components removed:
 # - LaunchDaemon: /Library/LaunchDaemons/io.exo.networksetup.plist
 # - Network script: /Library/Application Support/EXO/
 # - Log files: /var/log/io.exo.networksetup.*
 # - Network location: "exo"
-# - EXO data directory: ~/.exo (or all of ~/.exo except models/ when --keep-models is set)
 # - Launch at login registration
 #
 
 set -euo pipefail
 
-KEEP_MODELS=0
-for arg in "$@"; do
-  case "$arg" in
-  --keep-models)
-    KEEP_MODELS=1
-    ;;
-  -h | --help)
-    echo "Usage: sudo ./uninstall-exo.sh [--keep-models]"
-    echo "  --keep-models   Preserve ~/.exo/models when removing the EXO data directory."
-    exit 0
-    ;;
-  *)
-    echo "Unknown argument: $arg" >&2
-    echo "Usage: sudo ./uninstall-exo.sh [--keep-models]" >&2
-    exit 2
-    ;;
-  esac
-done
-
 LABEL="io.exo.networksetup"
-# Current script path. Older installs used a different filename; keep the
-# legacy path here so a fresh uninstall still cleans up upgraded machines.
-CURRENT_SCRIPT_DEST="/Library/Application Support/EXO/disable_bridge.sh"
-LEGACY_SCRIPT_DEST="/Library/Application Support/EXO/disable_bridge_enable_dhcp.sh"
+SCRIPT_DEST="/Library/Application Support/EXO/disable_bridge_enable_dhcp.sh"
 PLIST_DEST="/Library/LaunchDaemons/io.exo.networksetup.plist"
 LOG_OUT="/var/log/${LABEL}.log"
 LOG_ERR="/var/log/${LABEL}.err.log"
 APP_BUNDLE_ID="io.exo.EXO"
 
-# Resolve the invoking user's home, even when run via sudo.
-USER_HOME="$(eval echo "~${SUDO_USER:-$USER}")"
-EXO_DIR="$USER_HOME/.exo"
-
 # Colors for output
 RED='\033[0;31m'
 GREEN='\033[0;32m'
@@ -99,17 +69,11 @@ else
   echo_warn "LaunchDaemon plist not found (already removed?)"
 fi
 
-# Remove the script (current and legacy filenames) — backwards-compatible:
-# tolerate either, both, or neither being present.
-removed_any_script=0
-for script in "$CURRENT_SCRIPT_DEST" "$LEGACY_SCRIPT_DEST"; do
-  if [[ -f $script ]]; then
-    rm -f "$script"
-    echo_info "Removed network setup script: $script"
-    removed_any_script=1
-  fi
-done
-if [[ $removed_any_script -eq 0 ]]; then
+# Remove the script and parent directory
+if [[ -f $SCRIPT_DEST ]]; then
+  rm -f "$SCRIPT_DEST"
+  echo_info "Removed network setup script"
+else
   echo_warn "Network setup script not found (already removed?)"
 fi
 
@@ -151,22 +115,6 @@ if networksetup -listnetworkservices 2>/dev/null | grep -q "Thunderbolt Bridge";
   echo_info "Re-enabled Thunderbolt Bridge"
 fi
 
-# Remove EXO data directory (~/.exo)
-EXO_DIR_REMOVED=""
-if [[ -d $EXO_DIR ]]; then
-  if [[ $KEEP_MODELS == "1" && -d "$EXO_DIR/models" ]]; then
-    find "$EXO_DIR" -mindepth 1 -maxdepth 1 ! -name models -exec rm -rf {} +
-    EXO_DIR_REMOVED="kept_models"
-    echo_info "Removed ~/.exo (preserved models/)"
-  else
-    rm -rf "$EXO_DIR"
-    EXO_DIR_REMOVED="full"
-    echo_info "Removed ~/.exo"
-  fi
-else
-  echo_warn "~/.exo not found (already removed?)"
-fi
-
 # Note about launch at login registration
 # SMAppService-based login items cannot be removed from a shell script.
 # They can only be unregistered from within the app itself or manually via System Settings.
@@ -196,10 +144,6 @@ echo "  • Network setup LaunchDaemon"
 echo "  • Network configuration script"
 echo "  • Log files"
 echo "  • 'exo' network location"
-case "$EXO_DIR_REMOVED" in
-full) echo "  • EXO data directory (~/.exo)" ;;
-kept_models) echo "  • EXO data directory (~/.exo, models preserved)" ;;
-esac
 echo ""
 echo "Your network has been restored to use the 'Automatic' location."
 echo "Thunderbolt Bridge has been re-enabled (if present)."

bench/METHODOLOGY.md

@@ -1,160 +0,0 @@
-# Exo-Bench — Methodology
-
-exo bench measures inference throughput and resource consumption of an exo cluster under controlled conditions. It sends prompts to the `/bench/chat/completions` endpoint, collects server-reported timing statistics, and records system-level metrics (power, GPU utilisation, temperature) throughout each run.
-
-The goal is to have accurate, transparent and reproducible numbers to compare speed and scaling across different models and different setups, and to be able to track these results as optimizations and features are added to EXO.
-
-Below is a technical summary of how Exo-Bench works. While the methodology and benchmark may change over time, this document will be kept up to date whenever this happens. If you find an issue with the methodology, or would like a  feature to be added, please open a GitHub issue!
-
----
-
-## Prompt Construction
-
-Benchmarks need prompts of an exact token length. Unfortunately, we do not have direct access to the model but just the chat completion endpoint. To get around this fact, we create a request that will tokenise to a certain prompt length.
-
-This is achieved by:
-
-1. Tokenising a sample message through the model's `apply_chat_template()` to measure overhead (system tokens, special tokens, chat formatting).
-2. Binary-searching over a repeated atom string (default `"a "`) to find the content length that produces exactly the target number of tokens after template expansion.
-3. Returning both the content string and the verified token count.
-
-The actual token count is recorded in every result row as `pp_tokens`, so downstream analysis can confirm the prompt hit its target.
-
-Chat template formatting means that it may be impossible to attain very small pp benchmarks. e.g. pp=32 may not work. This tradeoff was made because the result of such a small prompt does not seem very interesting or useful for any real-world use cases.
-
----
-
-## Bench Endpoint
-
-When a request reaches the server via the `/bench/chat/completions` endpoint, three things change compared to a normal chat completion:
-
-- **KV prefix cache is disabled by default**. Every request starts from a cold cache, ensuring prefill timing is not affected by prior requests. See [Prefix Cache Mode](#prefix-cache-mode) for the `--use-prefix-cache` option.
-- **EOS tokens are banned**. A logits processor suppresses all end-of-sequence tokens, forcing the model to generate exactly `max_tokens` tokens. This guarantees consistent generation length for fair TPS comparison — the model cannot short-circuit a run by stopping early.
-- **No model output parsing**. The bench collection path concatenates raw token text without any model-specific post-processing (thinking tag extraction, structured output handling, etc.). This is to avoid model outputs such as tool parsing or any structural mistakes from breaking the benchmark - we are testing for speed; see Exo-Eval for performance metrics.
-
----
-
-## Timing
-
-### Prefill TPS
-
-Measured server-side per task.
-
-```
-prefill_tps = num_prompt_tokens / prefill_wall_seconds
-```
-
-### Generation TPS
-
-Measured server-side per task. Each task records wall-clock timestamps as tokens arrive:
-
-- First generated token: timestamp recorded
-- Every subsequent token: timestamp updated
-
-When generation completes:
-
-```
-gen_span = last_token_time - first_token_time
-generation_tps = (completion_tokens - 1) / gen_span
-```
-
-The first token is excluded from the numerator because the rate measures inter-token throughput — the time between the first and last token divided by the number of intervals.
-
-This does mean that tg=1 will not work.
-
----
-
-## Concurrency
-
-### Single Request
-
-The client records wall-clock `elapsed_s` around the HTTP round-trip (network latency + server prefill + generation + response serialisation). This is a convenience metric for end-to-end latency. The authoritative TPS numbers come from the server-side per-task timing in the `generation_stats` response.
-
-### Concurrent Requests
-
-When `--concurrency N` is set with N > 1, all N requests must hit the server at the same instant. The mechanism:
-
-1. The prompt is built once and shared across all threads.
-2. Each thread gets its own HTTP connection.
-3. A thread barrier blocks all threads until every thread is ready.
-4. The first thread past the barrier records the batch start time and signals the others.
-5. All threads use the same start time as their reference, then fire their HTTP request.
-6. Each thread's `elapsed_s` is measured from the shared start time to its own response completion.
-
-**Batch wall time** is the maximum `elapsed_s` across all N requests — the time until the last request finishes.
-
-### Aggregate TPS
-
-```
-per_req_tps = max(generation_tps across N concurrent requests)
-agg_gen_tps = per_req_tps * concurrency
-```
-
-`max` is used instead of `mean` because all requests run in parallel against the same model. The fastest request's generation rate represents the system's per-stream throughput capacity; multiplying by concurrency gives aggregate throughput.
-
----
-
-## Prefix Cache Mode
-
-When `--use-prefix-cache` is passed, the KV prefix cache remains active during benchmarking. This speeds up repeated runs by skipping redundant prefill work, which is useful when prompt processing is not the focus of the benchmark (e.g. when measuring generation throughput or power consumption across many configurations).
-
-Each response includes a `prefix_cache_hit` field (`"none"`, `"partial"`, or `"exact"`):
-
-- **none**: Cold prefill — no cached KV state was available. The reported `prompt_tps` is the real prefill throughput.
-- **partial**: A prefix of the prompt was found in cache. Only the remaining tokens were prefilled. The reported `prompt_tps` reflects the real throughput on the uncached portion. This occurs when multiple ascending `--pp` values share a common prefix (e.g. `--pp 1000,5000` — the 5000-token prompt reuses the 1000-token cache entry and prefills the remaining 4000 tokens).
-- **exact**: The entire prompt was found in cache (e.g. same `--pp` value on a `--repeat`). No prefill work was done. The reported `prompt_tps` is the TPS from when the cache entry was originally created, not a new measurement.
-
-**Prompt TPS is approximate in this mode.** Exact-hit runs report the stored TPS from the original cold/partial prefill rather than a freshly measured value. For accurate cold prefill numbers, run without `--use-prefix-cache`.
-
-Ascending `--pp` order (e.g. `--pp 1000,5000,10000`) gives the most useful data: each size gets a meaningful partial hit except the first which is cold. Descending order produces exact hits with approximate TPS from a longer prompt's original run.
-
----
-
-## Warmup
-
-Before measurement begins, `--warmup N` (default: 0) discarded requests are sent using the first pp/tg pair. Warmup results are not included in the output.
-
----
-
-## System Metrics
-
-A background thread polls each node at 1 Hz, collecting:
-
-- GPU utilisation (%)
-- Temperature (C)
-- System power draw (W)
-- CPU cluster usage (performance and efficiency cores)
-
-**Energy** is computed via trapezoidal integration of the power samples over each inference window (the wall-clock span of each benchmark request or concurrent batch). Average power is `total_joules / total_inference_seconds`.
-
----
-
-## Output Format
-
-Results are written as JSON with three top-level keys:
-
-- **`runs`**: Array of per-request result objects, each containing:
-  - `elapsed_s`, `output_text_preview` (first 200 chars)
-  - `stats`: `{ prompt_tps, generation_tps, prompt_tokens, generation_tokens, peak_memory_usage }`
-  - Placement metadata: `model_id`, `placement_sharding`, `placement_instance_meta`, `placement_nodes`
-  - Run metadata: `pp_tokens`, `tg`, `repeat_index`, `concurrency`, `concurrent_index`
-  - `download_duration_s` (if model was freshly downloaded)
-- **`cluster`**: Cluster state snapshot at time of benchmarking.
-- **`system_metrics`**: Per-node time-series samples (GPU, power, temperature).
-
----
-
-## Reproducing Results
-
-```bash
-cd bench && uv run python exo_bench.py \
-  --model "mlx-community/Qwen3.5-27B-4bit" \
-  --instance-meta jaccl \
-  --sharding tensor \
-  --min-nodes 2 --max-nodes 2 \
-  --pp 512 4096 --tg 128 \
-  --repeat 3 \
-  --warmup 1
-```
-
-Run --help for all the available flags.

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/eval_configs/models.toml

@@ -1,347 +0,0 @@
-# Model evaluation configurations for exo_eval.
-#
-# Each [[model]] entry uses `patterns` — a list of substrings matched
-# against the model_id. First matching entry wins.
-#
-# Required fields:
-#   name, patterns, reasoning
-#
-# Optional per-model overrides (CLI flags take priority over these):
-#   temperature, top_p, max_tokens, reasoning_effort, enable_thinking
-#
-# Fallback defaults (when no per-model config):
-#   reasoning:     temperature=1.0, max_tokens=131072, reasoning_effort="high"
-#   non-reasoning: temperature=0.0, max_tokens=16384
-#
-# All per-model values below are sourced from official model cards,
-# generation_config.json files, and vendor documentation.
-
-# ─── Qwen3.5 (Feb 2026) ─────────────────────────────────────────────
-# Source: HuggingFace model cards (Qwen/Qwen3.5-*)
-# Model card recommends: temp=0.6, top_p=0.95, top_k=20
-# We omit top_k to match vllm eval (which doesn't set it).
-# max_tokens=121072 to match vllm eval (131072 context - 10000 safety margin).
-
-[[model]]
-name = "Qwen3.5 2B"
-patterns = ["Qwen3.5-2B"]
-reasoning = true
-temperature = 0.6
-top_p = 0.95
-enable_thinking = true
-max_tokens = 121072
-
-[[model]]
-name = "Qwen3.5 9B"
-patterns = ["Qwen3.5-9B"]
-reasoning = true
-temperature = 0.6
-top_p = 0.95
-enable_thinking = true
-max_tokens = 121072
-
-[[model]]
-name = "Qwen3.5 27B"
-patterns = ["Qwen3.5-27B"]
-reasoning = true
-temperature = 0.6
-top_p = 0.95
-enable_thinking = true
-max_tokens = 121072
-
-[[model]]
-name = "Qwen3.5 35B A3B"
-patterns = ["Qwen3.5-35B-A3B"]
-reasoning = true
-temperature = 0.6
-top_p = 0.95
-enable_thinking = true
-max_tokens = 121072
-
-[[model]]
-name = "Qwen3.5 122B A10B"
-patterns = ["Qwen3.5-122B-A10B"]
-reasoning = true
-temperature = 0.6
-top_p = 0.95
-enable_thinking = true
-max_tokens = 121072
-
-[[model]]
-name = "Qwen3.5 397B A17B"
-patterns = ["Qwen3.5-397B-A17B"]
-reasoning = true
-temperature = 0.6
-top_p = 0.95
-enable_thinking = true
-max_tokens = 121072
-
-# ─── Qwen3 (Apr 2025) ───────────────────────────────────────────────
-# Source: HuggingFace model cards (Qwen/Qwen3-*)
-# Model card recommends: temp=0.6, top_p=0.95, top_k=20
-# We omit top_k to match vllm eval (which doesn't set it).
-# Non-thinking: temp=0.7, top_p=0.8
-# max_tokens: 32768 general, 38912 for complex math/code
-
-[[model]]
-name = "Qwen3 0.6B"
-patterns = ["Qwen3-0.6B"]
-reasoning = true
-temperature = 0.6
-top_p = 0.95
-enable_thinking = true
-max_tokens = 38912
-
-[[model]]
-name = "Qwen3 30B A3B"
-patterns = ["Qwen3-30B-A3B"]
-reasoning = true
-temperature = 0.6
-top_p = 0.95
-enable_thinking = true
-max_tokens = 38912
-
-[[model]]
-name = "Qwen3 235B A22B"
-patterns = ["Qwen3-235B-A22B"]
-reasoning = true
-temperature = 0.6
-top_p = 0.95
-enable_thinking = true
-max_tokens = 38912
-
-[[model]]
-name = "Qwen3 Next 80B Thinking"
-patterns = ["Qwen3-Next-80B-A3B-Thinking"]
-reasoning = true
-temperature = 0.6
-top_p = 0.95
-enable_thinking = true
-max_tokens = 38912
-
-[[model]]
-name = "Qwen3 Next 80B Instruct"
-patterns = ["Qwen3-Next-80B-A3B-Instruct"]
-reasoning = false
-temperature = 0.7
-top_p = 0.8
-max_tokens = 16384
-
-[[model]]
-name = "Qwen3 Coder 480B"
-patterns = ["Qwen3-Coder-480B"]
-reasoning = false
-temperature = 0.7
-top_p = 0.8
-max_tokens = 16384
-
-[[model]]
-name = "Qwen3 Coder Next"
-patterns = ["Qwen3-Coder-Next"]
-reasoning = false
-temperature = 1.0
-top_p = 0.95
-max_tokens = 121072
-
-# ─── GPT-OSS (OpenAI) ───────────────────────────────────────────────
-# Source: OpenAI GitHub README + HuggingFace discussion #21
-# temp=1.0, top_p=1.0, NO top_k, NO repetition_penalty
-# reasoning_effort supported: low/medium/high
-
-[[model]]
-name = "GPT-OSS 20B"
-patterns = ["gpt-oss-20b"]
-reasoning = true
-temperature = 1.0
-top_p = 1.0
-
-[[model]]
-name = "GPT-OSS 120B"
-patterns = ["gpt-oss-120b"]
-reasoning = true
-temperature = 1.0
-top_p = 1.0
-
-# ─── DeepSeek ────────────────────────────────────────────────────────
-# Source: https://api-docs.deepseek.com/quick_start/parameter_settings
-# Coding/Math: temp=0.0, General: temp=1.3, Creative: temp=1.5
-# NOTE: DeepSeek API applies nonlinear temp mapping. These are API values.
-# When running model directly: API temp 1.0 = model temp 0.3
-# We use temp=0.0 for eval (coding/math focus).
-
-[[model]]
-name = "DeepSeek V3.1"
-patterns = ["DeepSeek-V3.1"]
-reasoning = true
-temperature = 0.0
-
-[[model]]
-name = "DeepSeek V3.2"
-patterns = ["DeepSeek-V3.2"]
-reasoning = true
-temperature = 1.0
-top_p = 0.95
-enable_thinking = true
-
-# ─── NVIDIA Nemotron ───────────────────────────────────────────────────
-# Source: HuggingFace model cards
-# All variants: temp=1.0, top_p=0.95, enable_thinking=true
-
-[[model]]
-name = "Nemotron Cascade 2 30B A3B"
-patterns = ["Nemotron-Cascade-2-30B-A3B"]
-reasoning = true
-temperature = 1.0
-top_p = 0.95
-enable_thinking = true
-
-[[model]]
-name = "Nemotron 3 Super 120B A12B"
-patterns = ["Nemotron-3-Super-120B-A12B", "NVIDIA-Nemotron-3-Super-120B-A12B"]
-reasoning = true
-temperature = 1.0
-top_p = 0.95
-enable_thinking = true
-
-# ─── GLM (ZhipuAI / THUDM) ──────────────────────────────────────────
-# Source: HuggingFace model cards + generation_config.json + docs.z.ai
-# GLM 4.5+: temp=1.0, top_p=0.95
-# max_tokens=121072 to match vllm eval (131072 context - 10000 safety margin)
-
-[[model]]
-name = "GLM-5"
-patterns = ["GLM-5"]
-reasoning = true
-temperature = 1.0
-top_p = 0.95
-enable_thinking = true
-max_tokens = 121072
-
-[[model]]
-name = "GLM 4.5 Air"
-patterns = ["GLM-4.5-Air"]
-reasoning = true
-temperature = 1.0
-top_p = 0.95
-
-[[model]]
-name = "GLM 4.7"
-patterns = ["GLM-4.7-"]
-reasoning = true
-temperature = 1.0
-top_p = 0.95
-enable_thinking = true
-max_tokens = 121072
-# Note: matches both GLM-4.7 and GLM-4.7-Flash
-
-# ─── Kimi (Moonshot AI) ─────────────────────────────────────────────
-# Source: HuggingFace model cards (moonshotai/Kimi-K2-*)
-# K2-Instruct: temp=0.6
-# K2-Thinking: temp=1.0, max_length=262144
-# K2.5: thinking temp=1.0, top_p=0.95; instant temp=0.6, top_p=0.95
-
-[[model]]
-name = "Kimi K2 Thinking"
-patterns = ["Kimi-K2-Thinking"]
-reasoning = true
-temperature = 1.0
-max_tokens = 131072
-
-[[model]]
-name = "Kimi K2.5"
-patterns = ["Kimi-K2.5"]
-reasoning = true
-temperature = 1.0
-top_p = 0.95
-enable_thinking = true
-max_tokens = 121072
-
-[[model]]
-name = "Kimi K2 Instruct"
-patterns = ["Kimi-K2-Instruct"]
-reasoning = false
-temperature = 0.6
-
-# ─── MiniMax ─────────────────────────────────────────────────────────
-# Source: HuggingFace model cards + generation_config.json
-# All models: temp=1.0, top_p=0.95
-# max_tokens=90000 to match vllm eval (100000 context - 10000 safety margin)
-
-[[model]]
-name = "MiniMax M2.7"
-patterns = ["MiniMax-M2.7"]
-reasoning = true
-temperature = 1.0
-top_p = 0.95
-enable_thinking = true
-max_tokens = 90000
-
-[[model]]
-name = "MiniMax M2.5"
-patterns = ["MiniMax-M2.5"]
-reasoning = true
-temperature = 1.0
-top_p = 0.95
-enable_thinking = true
-max_tokens = 90000
-
-[[model]]
-name = "MiniMax M2.1"
-patterns = ["MiniMax-M2.1"]
-reasoning = true
-temperature = 1.0
-top_p = 0.95
-
-# ─── Step (StepFun) ─────────────────────────────────────────────────
-# Source: HuggingFace model card (stepfun-ai/Step-3.5-Flash)
-# Reasoning: temp=1.0, top_p=0.95
-# General chat: temp=0.6, top_p=0.95
-# We use reasoning settings for eval.
-
-[[model]]
-name = "Step 3.5 Flash"
-patterns = ["Step-3.5-Flash"]
-reasoning = true
-temperature = 1.0
-top_p = 0.95
-enable_thinking = true
-max_tokens = 121072
-
-# ─── Llama (Meta) ───────────────────────────────────────────────────
-# Source: generation_config.json + meta-llama/llama-models generation.py
-# All variants: temp=0.6, top_p=0.9
-
-[[model]]
-name = "Llama 3.2 1B"
-patterns = ["Llama-3.2-1B"]
-reasoning = false
-temperature = 0.6
-top_p = 0.9
-
-[[model]]
-name = "Llama 3.2 3B"
-patterns = ["Llama-3.2-3B"]
-reasoning = false
-temperature = 0.6
-top_p = 0.9
-
-[[model]]
-name = "Llama 3.1 8B"
-patterns = ["Llama-3.1-8B", "Meta-Llama-3.1-8B"]
-reasoning = false
-temperature = 0.6
-top_p = 0.9
-
-[[model]]
-name = "Llama 3.1 70B"
-patterns = ["Llama-3.1-70B", "Meta-Llama-3.1-70B"]
-reasoning = false
-temperature = 0.6
-top_p = 0.9
-
-[[model]]
-name = "Llama 3.3 70B"
-patterns = ["Llama-3.3-70B", "llama-3.3-70b"]
-reasoning = false
-temperature = 0.6
-top_p = 0.9

bench/harness.py

@@ -1,627 +0,0 @@
-# type: ignore
-from __future__ import annotations
-
-import argparse
-import http.client
-import json
-import os
-import time
-from collections.abc import Iterator
-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 stream_bench_chat_completions(self, payload: dict[str, Any]) -> Iterator[str]:
-        """POST /bench/chat/completions with stream=True, yielding raw SSE lines."""
-        payload = {**payload, "stream": True}
-        data = json.dumps(payload).encode("utf-8")
-        conn = http.client.HTTPConnection(self.host, self.port, timeout=self.timeout_s)
-        try:
-            conn.request(
-                "POST",
-                "/bench/chat/completions",
-                body=data,
-                headers={
-                    "Content-Type": "application/json",
-                    "Accept": "text/event-stream",
-                },
-            )
-            resp = conn.getresponse()
-            if resp.status >= 400:
-                raw = resp.read().decode("utf-8", errors="replace")
-                raise ExoHttpError(resp.status, resp.reason, raw[:300])
-            for line in resp:
-                yield line.decode("utf-8", errors="replace")
-        finally:
-            conn.close()
-
-    def get_state_path(self, path: str) -> Any:
-        try:
-            return self.request_json("GET", f"/state/{path}")
-        except ExoHttpError as e:
-            if e.status == 404:
-                return None
-            raise
-
-    def get_instance(self, instance_id: str) -> dict[str, Any] | None:
-        return self.get_state_path(f"instances/{instance_id}")
-
-    def get_runner(self, runner_id: str) -> dict[str, Any] | None:
-        return self.get_state_path(f"runners/{runner_id}")
-
-    def get_node_downloads(self, node_id: str) -> list[dict[str, Any]] | None:
-        return self.get_state_path(f"downloads/{node_id}")
-
-    def get_node_disk(self, node_id: str) -> dict[str, Any] | None:
-        return self.get_state_path(f"nodeDisk/{node_id}")
-
-    def get_node_system(self, node_id: str) -> dict[str, Any] | None:
-        return self.get_state_path(f"nodeSystem/{node_id}")
-
-    def get_node_identities(self) -> dict[str, Any] | None:
-        return self.get_state_path("nodeIdentities")
-
-    def get_topology(self) -> dict[str, Any] | None:
-        return self.get_state_path("topology")
-
-
-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 node_ids_from_instance(instance: dict[str, Any]) -> list[str]:
-    inner = unwrap_instance(instance)
-    return list(inner["shardAssignments"]["nodeToRunner"].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
-    last_loaded: dict[str, int] = {}
-    while time.time() - start_time < timeout:
-        instance = client.get_instance(instance_id)
-
-        if instance is None:
-            if instance_existed:
-                raise RuntimeError(
-                    f"Instance {instance_id} was deleted (runner may have failed)"
-                )
-            time.sleep(0.1)
-            continue
-
-        instance_existed = True
-        rids = runner_ids_from_instance(instance)
-
-        all_ready = True
-        for rid in rids:
-            runner = client.get_runner(rid) or {}
-            if runner_failed(runner):
-                error_msg = get_runner_failed_message(runner) or "Unknown error"
-                raise RuntimeError(f"Runner {rid} failed: {error_msg}")
-            if "RunnerLoading" in runner:
-                loading = runner["RunnerLoading"]
-                loaded = loading.get("layersLoaded", 0)
-                total = loading.get("totalLayers", 0)
-                if total > 0 and last_loaded.get(rid) != loaded:
-                    last_loaded[rid] = loaded
-                    logger.debug(f"Runner {rid}: loading layers {loaded}/{total}")
-            if not runner_ready(runner):
-                all_ready = False
-
-        if all_ready:
-            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 capture_cluster_snapshot(client: ExoClient) -> dict[str, Any]:
-    snapshot: dict[str, Any] = {}
-    identities = client.get_node_identities()
-    if identities:
-        snapshot["nodeIdentities"] = identities
-    topology = client.get_topology()
-    if topology:
-        snapshot["topology"] = topology
-    node_memory = client.get_state_path("nodeMemory")
-    if node_memory:
-        snapshot["nodeMemory"] = node_memory
-    node_system = client.get_state_path("nodeSystem")
-    if node_system:
-        snapshot["nodeSystem"] = node_system
-    return snapshot
-
-
-def resolve_model_short_id(
-    client: ExoClient, model_arg: str, *, force_download: bool = False
-) -> 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
-
-    if force_download and "/" in model_arg:
-        logger.info(f"Model not in /models, adding from HuggingFace: {model_arg}")
-        result = client.request_json(
-            "POST", "/models/add", body={"model_id": model_arg}
-        )
-        if result:
-            short_id = str(result.get("name") or model_arg.rsplit("/", 1)[-1])
-            full_id = str(result.get("hugging_face_id") or model_arg)
-            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,
-    node_id: str | None = None,
-) -> list[dict[str, Any]]:
-    params: dict[str, str] = {"model_id": full_model_id}
-    if node_id is not None:
-        params["node_ids"] = node_id
-    previews_resp = client.request_json("GET", "/instance/previews", params=params)
-    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,
-    node_id: str | None = None,
-) -> list[dict[str, Any]]:
-    selected = fetch_and_filter_placements(client, full_model_id, args, node_id=node_id)
-
-    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, node_id=node_id
-            )
-
-    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"]
-
-    needs_download = False
-
-    for node_id in node_ids:
-        node_downloads = client.get_node_downloads(node_id) or []
-
-        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
-
-        disk_info = client.get_node_disk(node_id) or {}
-        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)
-            disk_info = client.get_node_disk(node_id) or {}
-
-        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."
-            )
-
-        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 (no timeout — poll until complete or failed)
-    while True:
-        all_done = True
-        for node_id in node_ids:
-            node_downloads = client.get_node_downloads(node_id) or []
-            done = any(
-                "DownloadCompleted" in p
-                and unwrap_instance(p["DownloadCompleted"]["shardMetadata"])[
-                    "modelCard"
-                ]["modelId"]
-                == full_model_id
-                for p in node_downloads
-            )
-            failed = [
-                p["DownloadFailed"]["errorMessage"]
-                for p in node_downloads
-                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
-                ongoing = [
-                    p
-                    for p in node_downloads
-                    if "DownloadOngoing" in p
-                    and unwrap_instance(p["DownloadOngoing"]["shardMetadata"])[
-                        "modelCard"
-                    ]["modelId"]
-                    == full_model_id
-                ]
-                if ongoing:
-                    prog = ongoing[0]["DownloadOngoing"]["downloadProgress"]
-                    speed_mb = prog.get("speed", 0) / (1024 * 1024)
-                    eta_s = prog.get("etaMs", 0) / 1000
-                    dl_bytes = prog.get("downloaded", {}).get("inBytes", 0)
-                    total_bytes = prog.get("total", {}).get("inBytes", 0)
-                    pct = (dl_bytes / total_bytes * 100) if total_bytes else 0
-                    logger.info(
-                        f"Downloading on {node_id}: {pct:.1f}% @ {speed_mb:.1f} MB/s, "
-                        f"ETA {eta_s:.0f}s "
-                        f"({prog.get('completedFiles', 0)}/{prog.get('totalFiles', 0)} files)"
-                    )
-        if all_done:
-            if download_t0 is not None:
-                return time.perf_counter() - download_t0
-            return None
-        time.sleep(10)
-
-
-def find_existing_instance(client: ExoClient, model_id: str) -> str | None:
-    """Find an existing running instance for the given model."""
-    try:
-        state = client.request_json("GET", "/state")
-    except Exception:
-        return None
-    for inst_id, inst in state.get("instances", {}).items():
-        # Instance structure is nested: {"MlxJacclInstance": {"shardAssignments": {"modelId": ...}}}
-        for _inst_type, inner in inst.items():
-            if not isinstance(inner, dict):
-                continue
-            sa = inner.get("shardAssignments", {})
-            if sa.get("modelId") == model_id:
-                return inst_id
-    return None
-
-
-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(
-        "--force-download",
-        action="store_true",
-        help="If model not in /models, add it from HuggingFace via exo and download.",
-    )
-    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", "vllm", "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=60.0,
-        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.",
-    )
-    ap.add_argument(
-        "--reuse-instance",
-        action="store_true",
-        help="Reuse an existing running instance for this model instead of creating a new one.",
-    )

bench/parallel_requests.py

@@ -1,255 +0,0 @@
-# type: ignore
-import argparse
-import asyncio
-import sys
-import termios
-import time
-import tty
-
-import aiohttp
-
-NUM_REQUESTS = 10
-BASE_URL = ""
-
-QUESTIONS = [
-    "What is the capital of Australia?",
-    "How many bones are in the human body?",
-    "What year did World War II end?",
-    "What is the speed of light in meters per second?",
-    "Who wrote Romeo and Juliet?",
-    "What is the chemical formula for water?",
-    "How many planets are in our solar system?",
-    "What is the largest ocean on Earth?",
-    "Who painted the Mona Lisa?",
-    "What is the boiling point of water in Celsius?",
-]
-
-
-def write(s: str) -> None:
-    sys.stdout.write(s)
-
-
-# ---------------------------------------------------------------------------
-# Model picker (same style as exo_eval)
-# ---------------------------------------------------------------------------
-
-
-def fetch_models() -> list[str]:
-    import json
-    import urllib.request
-
-    with urllib.request.urlopen(f"{BASE_URL}/state") as resp:
-        data = json.loads(resp.read())
-    model_ids: set[str] = set()
-    for instance in data.get("instances", {}).values():
-        for variant in instance.values():
-            sa = variant.get("shardAssignments", {})
-            model_id = sa.get("modelId")
-            if model_id:
-                model_ids.add(model_id)
-    return sorted(model_ids)
-
-
-def pick_model() -> str | None:
-    models = fetch_models()
-    if not models:
-        print("No models found.")
-        return None
-
-    cursor = 0
-    total_lines = len(models) + 4
-
-    def render(first: bool = False) -> None:
-        if not first:
-            write(f"\033[{total_lines}A")
-        write("\033[J")
-        write("\033[1mSelect model\033[0m (up/down, enter confirm, q quit)\r\n\r\n")
-        for i, model in enumerate(models):
-            line = f"  {'>' if i == cursor else ' '} {model}"
-            write(f"\033[7m{line}\033[0m\r\n" if i == cursor else f"{line}\r\n")
-        write("\r\n")
-        sys.stdout.flush()
-
-    fd = sys.stdin.fileno()
-    old = termios.tcgetattr(fd)
-    try:
-        tty.setraw(fd)
-        write("\033[?25l")
-        render(first=True)
-        while True:
-            ch = sys.stdin.read(1)
-            if ch in ("q", "\x03"):
-                write("\033[?25h\033[0m\r\n")
-                return None
-            elif ch in ("\r", "\n"):
-                break
-            elif ch == "\x1b":
-                seq = sys.stdin.read(2)
-                if seq == "[A":
-                    cursor = (cursor - 1) % len(models)
-                elif seq == "[B":
-                    cursor = (cursor + 1) % len(models)
-            render()
-    finally:
-        termios.tcsetattr(fd, termios.TCSADRAIN, old)
-        write(f"\033[{total_lines}A\033[J")  # clear picker UI
-        write("\033[?25h\033[0m")
-        sys.stdout.flush()
-
-    return models[cursor]
-
-
-# ---------------------------------------------------------------------------
-# Parallel requests
-# ---------------------------------------------------------------------------
-
-statuses: list[str] = []
-times: list[str] = []
-previews: list[str] = []
-tokens: list[str] = []
-full_responses: list[dict | None] = []
-total_lines = 0
-start_time: float = 0
-selected_model: str = ""
-
-
-def render_progress(first: bool = False) -> None:
-    if not first:
-        write(f"\033[{total_lines}A")
-    write("\033[J")
-    elapsed = time.monotonic() - start_time if start_time else 0
-    done = sum(1 for s in statuses if s == "done")
-    write(
-        f"\033[1m{selected_model}\033[0m  [{done}/{NUM_REQUESTS}]  {elapsed:.1f}s\r\n\r\n"
-    )
-
-    for i in range(NUM_REQUESTS):
-        q = QUESTIONS[i % len(QUESTIONS)]
-        status = statuses[i]
-        if status == "pending":
-            color = "\033[33m"  # yellow
-        elif status == "running":
-            color = "\033[36m"  # cyan
-        elif status == "done":
-            color = "\033[32m"  # green
-        else:
-            color = "\033[31m"  # red
-        write(
-            f"  {i:>2}  {color}{status:<8}\033[0m  {times[i]:>6}  {tokens[i]:>5}tok  {q[:40]:<40}  {previews[i][:50]}\r\n"
-        )
-
-    write("\r\n")
-    sys.stdout.flush()
-
-
-async def send_request(
-    session: aiohttp.ClientSession, i: int, lock: asyncio.Lock
-) -> None:
-    payload = {
-        "model": selected_model,
-        "messages": [{"role": "user", "content": QUESTIONS[i % len(QUESTIONS)]}],
-        "max_tokens": 1024,
-    }
-    statuses[i] = "running"
-    async with lock:
-        render_progress()
-    t0 = time.monotonic()
-    try:
-        async with session.post(
-            f"{BASE_URL}/v1/chat/completions", json=payload
-        ) as resp:
-            data = await resp.json()
-            elapsed = time.monotonic() - t0
-            full_responses[i] = data
-            times[i] = f"{elapsed:.1f}s"
-            if resp.status == 200:
-                choice = data["choices"][0]
-                msg = choice["message"]
-                content = msg.get("content", "")
-                previews[i] = content[:50].replace("\n", " ") or "(empty)"
-                if "usage" in data:
-                    tokens[i] = str(data["usage"].get("total_tokens", ""))
-                statuses[i] = "done"
-            else:
-                statuses[i] = f"err:{resp.status}"
-                previews[i] = str(data.get("error", {}).get("message", ""))[:50]
-    except Exception as e:
-        elapsed = time.monotonic() - t0
-        times[i] = f"{elapsed:.1f}s"
-        statuses[i] = "error"
-        previews[i] = str(e)[:50]
-    async with lock:
-        render_progress()
-
-
-async def run_requests(print_stdout: bool = False) -> None:
-    global start_time, total_lines, statuses, times, previews, tokens, full_responses
-
-    statuses = ["pending"] * NUM_REQUESTS
-    times = ["-"] * NUM_REQUESTS
-    previews = ["-"] * NUM_REQUESTS
-    tokens = ["-"] * NUM_REQUESTS
-    full_responses = [None] * NUM_REQUESTS
-    total_lines = NUM_REQUESTS + 4
-
-    write("\033[?25l")  # hide cursor
-    start_time = time.monotonic()
-    render_progress(first=True)
-    lock = asyncio.Lock()
-    try:
-        async with aiohttp.ClientSession() as session:
-            tasks = [send_request(session, i, lock) for i in range(NUM_REQUESTS)]
-            await asyncio.gather(*tasks)
-        total = time.monotonic() - start_time
-        write(
-            f"\033[1m=== All {NUM_REQUESTS} requests done in {total:.1f}s ===\033[0m\r\n\r\n"
-        )
-
-        if print_stdout:
-            for i in range(NUM_REQUESTS):
-                data = full_responses[i]
-                if not data or "choices" not in data:
-                    continue
-                choice = data["choices"][0]
-                msg = choice["message"]
-                q = QUESTIONS[i % len(QUESTIONS)]
-                write(f"\033[1m--- #{i}: {q} ---\033[0m\r\n")
-                if msg.get("reasoning_content"):
-                    write(f"\033[2m[Thinking]: {msg['reasoning_content']}\033[0m\r\n")
-                write(f"{msg.get('content', '')}\r\n")
-                if "usage" in data:
-                    u = data["usage"]
-                    write(
-                        f"\033[2m[Usage: prompt={u.get('prompt_tokens')}, "
-                        f"completion={u.get('completion_tokens')}, "
-                        f"total={u.get('total_tokens')}]\033[0m\r\n"
-                    )
-                write("\r\n")
-    finally:
-        write("\033[?25h")  # show cursor
-        sys.stdout.flush()
-
-
-def main() -> None:
-    global selected_model, BASE_URL
-    parser = argparse.ArgumentParser(
-        description="Send parallel requests to an exo cluster"
-    )
-    parser.add_argument(
-        "--host", required=True, help="Hostname of the exo node (e.g. s1)"
-    )
-    parser.add_argument("--port", type=int, default=52415, help="Port (default: 52415)")
-    parser.add_argument(
-        "--stdout", action="store_true", help="Print full responses after completion"
-    )
-    args = parser.parse_args()
-    BASE_URL = f"http://{args.host}:{args.port}"
-    model = pick_model()
-    if not model:
-        return
-    selected_model = model
-    asyncio.run(run_requests(print_stdout=args.stdout))
-
-
-if __name__ == "__main__":
-    main()

bench/prefill-decode.toml

@@ -1,36 +0,0 @@
-# Prefill/Decode disaggregation benchmark config.
-#
-# Top-level keys are bench-wide. [prefill] and [decode] sections set per-side
-# placement filters and (optionally) per-side model.
-#
-# Example:
-#   uv run python bench/prefill_decode_bench.py --config bench/prefill-decode.toml
-
-host = "james"
-port = 52415
-timeout = 7200.0
-settle_timeout = 60.0
-
-# Workload
-pp = [4096, 8192]
-tg = [128]
-repeat = 1
-warmup = 0
-
-json_out = "bench/prefill_decode_results.json"
-
-[prefill]
-model = "sakamakismile/Qwen3.6-27B-NVFP4"
-node = "gx10-de89"
-instance_meta = "vllm"
-sharding = "pipeline"
-min_nodes = 1
-max_nodes = 1
-
-[decode]
-model = "mlx-community/Qwen3.6-27B-4bit"
-node = "Ryuichi’s MacBook Pro"
-instance_meta = "ring"
-sharding = "pipeline"
-min_nodes = 1
-max_nodes = 1

bench/prefill_decode_bench.py

@@ -1,869 +0,0 @@
-# type: ignore
-#!/usr/bin/env python3
-"""Disaggregated prefill-decode benchmark for exo (MLX → MLX).
-
-Spins up two MLX instances on the cluster, marks one as Prefill source and
-the other as Decode target via /v1/instance-links, then sends chat
-completions to the API. The master routes the request to the decode
-instance and stamps `prefill_endpoint` pointing at the prefill instance —
-the worker decides per-request whether to ship prefill remotely
-(uncached_count > REMOTE_PREFILL_MIN_TOKENS).
-
-Usage:
-    uv run python bench/prefill_decode_bench.py --model <id> --pp 2048,8192 --tg 128
-    uv run python bench/prefill_decode_bench.py --model <id> --pp 4096 --tg 128 --repeat 3
-    uv run python bench/prefill_decode_bench.py --model <id> --pp 2048 --tg 128 --dry-run
-"""
-
-from __future__ import annotations
-
-import argparse
-import contextlib
-import copy
-import itertools
-import json
-import sys
-import time
-import tomllib
-from pathlib import Path
-from statistics import mean
-from typing import Any
-
-from exo_bench import (
-    PromptSizer,
-    SystemMetricsSampler,
-    format_peak_memory,
-    load_tokenizer_for_bench,
-    parse_int_list,
-)
-from harness import (
-    ExoClient,
-    ExoHttpError,
-    add_common_instance_args,
-    instance_id_from_instance,
-    node_ids_from_instance,
-    nodes_used_in_instance,
-    resolve_model_short_id,
-    run_planning_phase,
-    settle_and_fetch_placements,
-    unwrap_instance,
-    wait_for_instance_gone,
-    wait_for_instance_ready,
-)
-from loguru import logger
-
-
-def _node_id_to_friendly(client: ExoClient) -> dict[str, str]:
-    identities = client.get_node_identities() or {}
-    out: dict[str, str] = {}
-    for node_id, identity in identities.items():
-        if isinstance(identity, dict):
-            name = identity.get("friendlyName") or identity.get("friendly_name")
-            if isinstance(name, str):
-                out[str(node_id)] = name
-    return out
-
-
-def _placement_node_friendly_names(
-    placement: dict[str, Any], id_to_friendly: dict[str, str]
-) -> list[str]:
-    instance = placement["instance"]
-    return [id_to_friendly.get(nid, nid) for nid in node_ids_from_instance(instance)]
-
-
-def _filter_by_node(
-    placements: list[dict[str, Any]],
-    friendly_name: str,
-    id_to_friendly: dict[str, str],
-) -> list[dict[str, Any]]:
-    target = friendly_name.lower()
-    matched: list[dict[str, Any]] = []
-    for p in placements:
-        names = [n.lower() for n in _placement_node_friendly_names(p, id_to_friendly)]
-        if any(target == n or target in n for n in names):
-            matched.append(p)
-    return matched
-
-
-def _node_id_by_friendly(id_to_friendly: dict[str, str], target: str) -> str | None:
-    target_lc = target.lower()
-    for nid, name in id_to_friendly.items():
-        if target_lc == name.lower() or target_lc in name.lower():
-            return nid
-    return None
-
-
-def _load_toml(path: str) -> dict[str, Any]:
-    with Path(path).open("rb") as f:
-        return tomllib.load(f)
-
-
-_TOP_LEVEL_TOML_KEYS = {
-    "host",
-    "port",
-    "timeout",
-    "settle_timeout",
-    "model",
-    "pp",
-    "tg",
-    "repeat",
-    "warmup",
-    "json_out",
-    "instance_meta",
-    "sharding",
-    "min_nodes",
-    "max_nodes",
-    "force_download",
-    "danger_delete_downloads",
-    "all_combinations",
-}
-
-
-def _inject_toml_into_argv() -> None:
-    """If --config X is in sys.argv, pre-load it and inject required CLI args
-    (--model, --pp, --tg) so argparse's required=True checks pass."""
-    argv = sys.argv
-    if "--config" not in argv:
-        return
-    idx = argv.index("--config")
-    if idx + 1 >= len(argv):
-        return
-    cfg_path = argv[idx + 1]
-    cfg = _load_toml(cfg_path)
-    decode = cfg.get("decode", {})
-
-    def _has(flag: str) -> bool:
-        return any(a == flag or a.startswith(flag + "=") for a in argv)
-
-    # --model: prefer top-level, then [decode].model
-    if not _has("--model"):
-        model = cfg.get("model") or decode.get("model")
-        if model:
-            argv += ["--model", str(model)]
-    if not _has("--pp"):
-        pp = cfg.get("pp")
-        if pp:
-            argv += (
-                ["--pp", *(str(x) for x in pp)]
-                if isinstance(pp, list)
-                else [
-                    "--pp",
-                    str(pp),
-                ]
-            )
-    if not _has("--tg"):
-        tg = cfg.get("tg")
-        if tg:
-            argv += (
-                ["--tg", *(str(x) for x in tg)]
-                if isinstance(tg, list)
-                else [
-                    "--tg",
-                    str(tg),
-                ]
-            )
-
-
-def _merge_toml_into_args(args: argparse.Namespace, cfg: dict[str, Any]) -> None:
-    """Apply top-level toml keys onto args namespace where args has a default."""
-    for key, value in cfg.items():
-        if key in {"prefill", "decode"}:
-            continue
-        if key not in _TOP_LEVEL_TOML_KEYS:
-            continue
-        attr = key
-        current = getattr(args, attr, None)
-        if current in (None, [], False):
-            setattr(args, attr, value)
-
-
-def _side_args(
-    base: argparse.Namespace, overrides: dict[str, Any]
-) -> argparse.Namespace:
-    out = copy.copy(base)
-    for k in (
-        "instance_meta",
-        "sharding",
-        "min_nodes",
-        "max_nodes",
-        "skip_pipeline_jaccl",
-        "skip_tensor_ring",
-    ):
-        if k in overrides:
-            setattr(out, k, overrides[k])
-    return out
-
-
-def _pick_two_distinct_placements(
-    placements: list[dict[str, Any]],
-) -> tuple[dict[str, Any], dict[str, Any]] | None:
-    if len(placements) < 2:
-        return None
-    seen_nodes: set[tuple[str, ...]] = set()
-    chosen: list[dict[str, Any]] = []
-    for p in placements:
-        nodes = tuple(sorted(str(n) for n in p.get("nodes", [])))
-        if nodes in seen_nodes:
-            continue
-        seen_nodes.add(nodes)
-        chosen.append(p)
-        if len(chosen) == 2:
-            return chosen[0], chosen[1]
-    return None
-
-
-def _create_instance_link(
-    client: ExoClient,
-    prefill_instance_id: str,
-    decode_instance_id: str,
-) -> str:
-    out = client.request_json(
-        "POST",
-        "/v1/instance-links",
-        body={
-            "prefill_instances": [prefill_instance_id],
-            "decode_instances": [decode_instance_id],
-        },
-    )
-    return str(out.get("commandId", ""))
-
-
-def _list_instance_links(client: ExoClient) -> list[dict[str, Any]]:
-    out = client.request_json("GET", "/v1/instance-links")
-    return out if isinstance(out, list) else []
-
-
-def _delete_instance_link(client: ExoClient, link_id: str) -> None:
-    client.request_json("DELETE", f"/v1/instance-links/{link_id}")
-
-
-def run_one(
-    client: ExoClient,
-    model_id: str,
-    pp_hint: int,
-    tg: int,
-    prompt_sizer: PromptSizer,
-) -> tuple[dict[str, Any], int]:
-    content, pp_tokens = prompt_sizer.build(pp_hint)
-    payload: dict[str, Any] = {
-        "model": model_id,
-        "messages": [{"role": "user", "content": content}],
-        "stream": False,
-        "max_tokens": tg,
-    }
-
-    t0 = time.perf_counter()
-    out = client.post_bench_chat_completions(payload)
-    elapsed = time.perf_counter() - t0
-
-    stats = out.get("generation_stats")
-    choices = out.get("choices") or [{}]
-    message = choices[0].get("message", {}) if choices else {}
-    text = message.get("content") or ""
-    preview = text[:200] if text else ""
-
-    return {
-        "elapsed_s": elapsed,
-        "output_text_preview": preview,
-        "stats": stats,
-    }, pp_tokens
-
-
-def _run_phase(
-    *,
-    client: ExoClient,
-    label: str,
-    pp_tg_pairs: list[tuple[int, int]],
-    model_id: str,
-    prompt_sizer: PromptSizer,
-    warmup: int,
-    repeat: int,
-    common_meta: dict[str, Any],
-    sampler: SystemMetricsSampler | None = None,
-) -> list[dict[str, Any]]:
-    logger.info(f"=== phase: {label} (model={model_id}) ===")
-    rows: list[dict[str, Any]] = []
-    for i in range(warmup):
-        run_one(client, model_id, pp_tg_pairs[0][0], pp_tg_pairs[0][1], prompt_sizer)
-        logger.debug(f"  warmup {i + 1}/{warmup} done")
-
-    for pp, tg in pp_tg_pairs:
-        logger.info(f"--- {label}: pp={pp} tg={tg} ---")
-        runs: list[dict[str, Any]] = []
-        inference_windows: list[tuple[float, float]] = []
-        for r in range(repeat):
-            time.sleep(2)
-            try:
-                inf_t0 = time.monotonic()
-                row, actual_pp_tokens = run_one(client, model_id, pp, tg, prompt_sizer)
-                inference_windows.append((inf_t0, time.monotonic()))
-            except Exception as e:
-                logger.error(e)
-                continue
-            row.update(common_meta)
-            row.update(
-                {
-                    "phase": label,
-                    "phase_model_id": model_id,
-                    "pp_tokens": actual_pp_tokens,
-                    "tg": tg,
-                    "repeat_index": r,
-                }
-            )
-            runs.append(row)
-            rows.append(row)
-
-        if runs:
-            prompt_tps = mean(x["stats"]["prompt_tps"] for x in runs)
-            gen_tps = mean(x["stats"]["generation_tps"] for x in runs)
-            ptok = mean(x["stats"]["prompt_tokens"] for x in runs)
-            gtok = mean(x["stats"]["generation_tokens"] for x in runs)
-            peak = mean(x["stats"]["peak_memory_usage"]["inBytes"] for x in runs)
-            avg_elapsed = mean(x["elapsed_s"] for x in runs)
-            energy_str = ""
-            if sampler is not None and inference_windows:
-                joules = sum(
-                    sampler.energy_between(t0, t1) for t0, t1 in inference_windows
-                )
-                inf_seconds = sum(t1 - t0 for t0, t1 in inference_windows)
-                avg_watts = joules / inf_seconds if inf_seconds > 0 else 0.0
-                energy_per_run = joules / len(runs) if runs else 0.0
-                energy_str = (
-                    f"    energy={joules:.1f}J ({avg_watts:.1f}W avg over "
-                    f"{inf_seconds:.1f}s inference, {energy_per_run:.1f}J/run)"
-                )
-                for run_row, (t0, t1) in zip(runs, inference_windows, strict=False):
-                    run_row["energy_joules"] = sampler.energy_between(t0, t1)
-                    run_row["inference_window_s"] = t1 - t0
-            logger.info(
-                f"[{label}] prompt_tps={prompt_tps:.2f} gen_tps={gen_tps:.2f}    "
-                f"prompt_tokens={ptok} gen_tokens={gtok}    "
-                f"peak_memory={format_peak_memory(peak)}    "
-                f"avg_elapsed={avg_elapsed:.2f}s{energy_str}"
-            )
-        time.sleep(2)
-    return rows
-
-
-def _summarise(rows: list[dict[str, Any]]) -> dict[tuple[int, int], dict[str, float]]:
-    grouped: dict[tuple[int, int], list[dict[str, Any]]] = {}
-    for r in rows:
-        key = (int(r["pp_tokens"]), int(r["tg"]))
-        grouped.setdefault(key, []).append(r)
-    out: dict[tuple[int, int], dict[str, float]] = {}
-    for key, runs in grouped.items():
-        energy_runs = [x.get("energy_joules") for x in runs if "energy_joules" in x]
-        window_runs = [
-            x.get("inference_window_s") for x in runs if "inference_window_s" in x
-        ]
-        out[key] = {
-            "prompt_tps": mean(x["stats"]["prompt_tps"] for x in runs),
-            "gen_tps": mean(x["stats"]["generation_tps"] for x in runs),
-            "elapsed_s": mean(x["elapsed_s"] for x in runs),
-            "prompt_tokens": mean(x["stats"]["prompt_tokens"] for x in runs),
-            "gen_tokens": mean(x["stats"]["generation_tokens"] for x in runs),
-            "energy_j": mean(energy_runs) if energy_runs else 0.0,
-            "inference_window_s": mean(window_runs) if window_runs else 0.0,
-        }
-    return out
-
-
-def _normalised_seconds(summary: dict[str, float], pp: int, tg: int) -> float | None:
-    """Wall-clock time implied by reported tps for the *configured* pp/tg.
-
-    elapsed_s is not comparable across phases when models EOS at different
-    lengths. This formula reconstructs "what would this phase take to do
-    pp prompt tokens + tg generation tokens" using its own reported rates.
-    """
-    p_tps = summary.get("prompt_tps", 0.0)
-    g_tps = summary.get("gen_tps", 0.0)
-    if p_tps <= 0 or g_tps <= 0:
-        return None
-    return pp / p_tps + tg / g_tps
-
-
-def _print_diff(
-    disagg_rows: list[dict[str, Any]],
-    decode_alone_rows: list[dict[str, Any]],
-    prefill_alone_rows: list[dict[str, Any]],
-) -> None:
-    disagg = _summarise(disagg_rows)
-    decode_alone = _summarise(decode_alone_rows)
-    prefill_alone = _summarise(prefill_alone_rows)
-    keys = set(disagg.keys()) | set(decode_alone.keys()) | set(prefill_alone.keys())
-
-    width = 110
-    for key in sorted(keys):
-        pp, tg = key
-        logger.info("─" * width)
-        logger.info(f"  pp={pp}  tg={tg}")
-        logger.info("─" * width)
-        logger.info(
-            f"  {'phase':<16} {'elapsed':>9}  {'norm':>9}  "
-            f"{'prompt_tps':>11}  {'gen_tps':>8}  "
-            f"{'p_tok':>6}  {'g_tok':>6}  "
-            f"{'energy':>9}  {'avg_W':>7}"
-        )
-        for label, summary in (
-            ("disaggregated", disagg.get(key)),
-            ("decode_alone", decode_alone.get(key)),
-            ("prefill_alone", prefill_alone.get(key)),
-        ):
-            if summary is None:
-                logger.info(
-                    f"  {label:<16} {'—':>9}  {'—':>9}  "
-                    f"{'—':>11}  {'—':>8}  {'—':>6}  {'—':>6}  "
-                    f"{'—':>9}  {'—':>7}"
-                )
-                continue
-            norm = _normalised_seconds(summary, pp, tg)
-            norm_str = f"{norm:>8.2f}s" if norm is not None else f"{'—':>9}"
-            energy = summary.get("energy_j", 0.0)
-            window = summary.get("inference_window_s", 0.0)
-            energy_str = f"{energy:>8.1f}J" if energy > 0 else f"{'—':>9}"
-            avg_w = energy / window if window > 0 else 0.0
-            avg_w_str = f"{avg_w:>6.1f}W" if avg_w > 0 else f"{'—':>7}"
-            logger.info(
-                f"  {label:<16} "
-                f"{summary['elapsed_s']:>8.2f}s  "
-                f"{norm_str}  "
-                f"{summary['prompt_tps']:>11.1f}  "
-                f"{summary['gen_tps']:>8.2f}  "
-                f"{summary['prompt_tokens']:>6.0f}  "
-                f"{summary['gen_tokens']:>6.0f}  "
-                f"{energy_str}  "
-                f"{avg_w_str}"
-            )
-
-        d = disagg.get(key)
-        da = decode_alone.get(key)
-        pa = prefill_alone.get(key)
-        d_norm = _normalised_seconds(d, pp, tg) if d else None
-        if d_norm and da:
-            da_norm = _normalised_seconds(da, pp, tg)
-            if da_norm:
-                logger.info(
-                    f"  norm speedup vs decode_alone:  {da_norm / d_norm:.2f}x  "
-                    f"(prefill {d['prompt_tps'] / da['prompt_tps']:.2f}x, "
-                    f"decode {d['gen_tps'] / da['gen_tps']:.2f}x)"
-                )
-        if d_norm and pa:
-            pa_norm = _normalised_seconds(pa, pp, tg)
-            if pa_norm:
-                logger.info(
-                    f"  norm speedup vs prefill_alone: {pa_norm / d_norm:.2f}x  "
-                    f"(prefill {d['prompt_tps'] / pa['prompt_tps']:.2f}x, "
-                    f"decode {d['gen_tps'] / pa['gen_tps']:.2f}x)"
-                )
-    logger.info("─" * width)
-
-
-def main() -> int:
-    _inject_toml_into_argv()
-    ap = argparse.ArgumentParser(
-        prog="prefill-decode-bench",
-        description="Benchmark MLX-MLX disaggregated prefill/decode via instance links.",
-    )
-    add_common_instance_args(ap)
-    ap.add_argument(
-        "--pp",
-        nargs="+",
-        required=True,
-        help="Prompt-size hints (ints, must be >1000). Accepts commas.",
-    )
-    ap.add_argument(
-        "--tg",
-        nargs="+",
-        required=True,
-        help="Generation lengths (ints). Accepts commas.",
-    )
-    ap.add_argument(
-        "--repeat", type=int, default=1, help="Repetitions per (pp,tg) pair."
-    )
-    ap.add_argument(
-        "--warmup",
-        type=int,
-        default=0,
-        help="Warmup runs (uses first pp/tg).",
-    )
-    ap.add_argument(
-        "--json-out",
-        default="bench/prefill_decode_results.json",
-        help="Write raw per-run results JSON to this path.",
-    )
-    ap.add_argument("--stdout", action="store_true", help="Write results to stdout")
-    ap.add_argument(
-        "--dry-run", action="store_true", help="List selected placements and exit."
-    )
-    ap.add_argument(
-        "--all-combinations",
-        action="store_true",
-        help="Force all pp×tg combinations even when lists have equal length.",
-    )
-    ap.add_argument(
-        "--prefill-model",
-        default=None,
-        help="Model id for the prefill instance. Defaults to --model.",
-    )
-    ap.add_argument(
-        "--prefill-node",
-        default=None,
-        help="friendly_name of the node hosting the prefill instance.",
-    )
-    ap.add_argument(
-        "--decode-node",
-        default=None,
-        help="friendly_name of the node hosting the decode instance.",
-    )
-    ap.add_argument(
-        "--config",
-        default=None,
-        help="TOML config file. CLI flags override toml values.",
-    )
-    ap.add_argument(
-        "--compare-baseline",
-        action="store_true",
-        help="Also run each (pp,tg) pair without the prefill/decode link "
-        "(decode instance does its own prefill) and report the diff.",
-    )
-    args = ap.parse_args()
-    cfg = _load_toml(args.config) if args.config else {}
-    _merge_toml_into_args(args, cfg)
-    prefill_overrides = cfg.get("prefill", {}) if cfg else {}
-    decode_overrides = cfg.get("decode", {}) if cfg else {}
-    if args.prefill_model is None and "model" in prefill_overrides:
-        args.prefill_model = prefill_overrides["model"]
-    if args.prefill_node is None and "node" in prefill_overrides:
-        args.prefill_node = prefill_overrides["node"]
-    if args.decode_node is None and "node" in decode_overrides:
-        args.decode_node = decode_overrides["node"]
-    if "model" in decode_overrides and not args.model:
-        args.model = decode_overrides["model"]
-
-    pp_list = parse_int_list(args.pp)
-    tg_list = parse_int_list(args.tg)
-    if not pp_list or not tg_list:
-        logger.error("pp and tg lists must be non-empty")
-        return 2
-    for pp in pp_list:
-        if pp <= 1000:
-            logger.error(
-                f"pp={pp} must be >1000 (remote prefill triggers when uncached >1000)"
-            )
-            return 2
-    if args.repeat <= 0:
-        logger.error("--repeat must be >= 1")
-        return 2
-
-    use_combinations = args.all_combinations or len(pp_list) != len(tg_list)
-    if use_combinations:
-        logger.info(
-            f"pp/tg mode: combinations (product) — {len(pp_list) * len(tg_list)} pairs"
-        )
-    else:
-        logger.info(f"pp/tg mode: tandem (zip) — {len(pp_list)} pairs")
-
-    client = ExoClient(args.host, args.port, timeout_s=args.timeout)
-
-    decode_short_id, decode_full_id = resolve_model_short_id(
-        client, args.model, force_download=args.force_download
-    )
-    if args.prefill_model:
-        prefill_short_id, prefill_full_id = resolve_model_short_id(
-            client, args.prefill_model, force_download=args.force_download
-        )
-    else:
-        prefill_short_id, prefill_full_id = decode_short_id, decode_full_id
-
-    tokenizer = load_tokenizer_for_bench(decode_full_id)
-    if tokenizer is None:
-        raise RuntimeError("[prefill-decode-bench] decode tokenizer load failed")
-    try:
-        decode_prompt_sizer = PromptSizer(tokenizer)
-    except Exception:
-        logger.error("[prefill-decode-bench] decode prompt sizing failed")
-        raise
-
-    if prefill_full_id == decode_full_id:
-        prefill_prompt_sizer = decode_prompt_sizer
-    else:
-        prefill_tokenizer = load_tokenizer_for_bench(prefill_full_id)
-        if prefill_tokenizer is None:
-            raise RuntimeError("[prefill-decode-bench] prefill tokenizer load failed")
-        prefill_prompt_sizer = PromptSizer(prefill_tokenizer)
-
-    id_to_friendly = _node_id_to_friendly(client)
-
-    prefill_args = _side_args(args, prefill_overrides)
-    decode_args = _side_args(args, decode_overrides)
-
-    if prefill_full_id == decode_full_id and prefill_overrides == decode_overrides:
-        placements = settle_and_fetch_placements(
-            client, decode_full_id, args, settle_timeout=args.settle_timeout
-        )
-        prefill_candidates = (
-            _filter_by_node(placements, args.prefill_node, id_to_friendly)
-            if args.prefill_node
-            else placements
-        )
-        decode_candidates = (
-            _filter_by_node(placements, args.decode_node, id_to_friendly)
-            if args.decode_node
-            else placements
-        )
-        if args.prefill_node and not prefill_candidates:
-            logger.error(f"No placement on prefill node {args.prefill_node!r}.")
-            return 1
-        if args.decode_node and not decode_candidates:
-            logger.error(f"No placement on decode node {args.decode_node!r}.")
-            return 1
-        if args.prefill_node and args.decode_node:
-            prefill_p = prefill_candidates[0]
-            decode_p = decode_candidates[0]
-        else:
-            pair = _pick_two_distinct_placements(placements)
-            if pair is None:
-                logger.error(
-                    "Need at least two distinct-node MLX placements for the same model."
-                )
-                return 1
-            prefill_p, decode_p = pair
-            if args.prefill_node:
-                prefill_p = prefill_candidates[0]
-            if args.decode_node:
-                decode_p = decode_candidates[0]
-    else:
-        prefill_node_id = (
-            _node_id_by_friendly(id_to_friendly, args.prefill_node)
-            if args.prefill_node
-            else None
-        )
-        decode_node_id = (
-            _node_id_by_friendly(id_to_friendly, args.decode_node)
-            if args.decode_node
-            else None
-        )
-        if args.prefill_node and prefill_node_id is None:
-            logger.error(f"Unknown node {args.prefill_node!r}.")
-            return 1
-        if args.decode_node and decode_node_id is None:
-            logger.error(f"Unknown node {args.decode_node!r}.")
-            return 1
-        prefill_placements = settle_and_fetch_placements(
-            client,
-            prefill_full_id,
-            prefill_args,
-            settle_timeout=args.settle_timeout,
-            node_id=prefill_node_id,
-        )
-        decode_placements = settle_and_fetch_placements(
-            client,
-            decode_full_id,
-            decode_args,
-            settle_timeout=args.settle_timeout,
-            node_id=decode_node_id,
-        )
-        if not prefill_placements:
-            logger.error(
-                f"No placement found for prefill model {prefill_full_id}"
-                f"{f' on node {args.prefill_node!r}' if args.prefill_node else ''}."
-            )
-            return 1
-        if not decode_placements:
-            logger.error(
-                f"No placement found for decode model {decode_full_id}"
-                f"{f' on node {args.decode_node!r}' if args.decode_node else ''}."
-            )
-            return 1
-        prefill_p = prefill_placements[0]
-        decode_p = decode_placements[0]
-
-    prefill_node_names = _placement_node_friendly_names(prefill_p, id_to_friendly)
-    decode_node_names = _placement_node_friendly_names(decode_p, id_to_friendly)
-    _ = unwrap_instance
-
-    prefill_instance = prefill_p["instance"]
-    decode_instance = decode_p["instance"]
-    prefill_id = instance_id_from_instance(prefill_instance)
-    decode_id = instance_id_from_instance(decode_instance)
-    prefill_meta = str(prefill_p.get("instance_meta", ""))
-    decode_meta = str(decode_p.get("instance_meta", ""))
-    prefill_nodes = nodes_used_in_instance(prefill_instance)
-    decode_nodes = nodes_used_in_instance(decode_instance)
-
-    logger.info("=" * 80)
-    logger.info(
-        f"PREFILL: {prefill_meta} / nodes={prefill_nodes} ({','.join(prefill_node_names)}) "
-        f"/ {prefill_short_id} ({prefill_full_id}) / instance_id={prefill_id}"
-    )
-    logger.info(
-        f"DECODE:  {decode_meta} / nodes={decode_nodes} ({','.join(decode_node_names)}) "
-        f"/ {decode_short_id} ({decode_full_id}) / instance_id={decode_id}"
-    )
-
-    if args.dry_run:
-        return 0
-
-    settle_deadline = (
-        time.monotonic() + args.settle_timeout if args.settle_timeout > 0 else None
-    )
-
-    logger.info("Planning phase: prefill...")
-    run_planning_phase(
-        client,
-        prefill_full_id,
-        prefill_p,
-        args.danger_delete_downloads,
-        args.timeout,
-        settle_deadline,
-    )
-    logger.info("Planning phase: decode...")
-    run_planning_phase(
-        client,
-        decode_full_id,
-        decode_p,
-        args.danger_delete_downloads,
-        args.timeout,
-        settle_deadline,
-    )
-
-    if use_combinations:
-        pp_tg_pairs = list(itertools.product(pp_list, tg_list))
-    else:
-        pp_tg_pairs = list(zip(pp_list, tg_list, strict=True))
-
-    common_meta = {
-        "decode_model_short_id": decode_short_id,
-        "decode_model_id": decode_full_id,
-        "prefill_model_short_id": prefill_short_id,
-        "prefill_model_id": prefill_full_id,
-        "prefill_instance_id": prefill_id,
-        "prefill_instance_meta": prefill_meta,
-        "prefill_nodes": prefill_nodes,
-        "decode_instance_id": decode_id,
-        "decode_instance_meta": decode_meta,
-        "decode_nodes": decode_nodes,
-    }
-
-    all_rows: list[dict[str, Any]] = []
-    disagg_rows: list[dict[str, Any]] = []
-    decode_alone_rows: list[dict[str, Any]] = []
-    prefill_alone_rows: list[dict[str, Any]] = []
-    link_id = ""
-    prefill_alive = False
-    decode_alive = False
-    sampler_nodes = sorted(
-        {
-            *node_ids_from_instance(prefill_instance),
-            *node_ids_from_instance(decode_instance),
-        }
-    )
-    sampler = SystemMetricsSampler(
-        ExoClient(args.host, args.port, timeout_s=30), sampler_nodes
-    )
-    sampler.start()
-    try:
-        logger.info("Creating prefill instance...")
-        client.request_json("POST", "/instance", body={"instance": prefill_instance})
-        wait_for_instance_ready(client, prefill_id)
-        prefill_alive = True
-        logger.info("Prefill instance ready")
-
-        if args.compare_baseline:
-            time.sleep(2)
-            prefill_alone_rows = _run_phase(
-                client=client,
-                label="prefill_alone",
-                pp_tg_pairs=pp_tg_pairs,
-                model_id=prefill_full_id,
-                prompt_sizer=prefill_prompt_sizer,
-                warmup=args.warmup,
-                repeat=args.repeat,
-                common_meta=common_meta,
-                sampler=sampler,
-            )
-            all_rows.extend(prefill_alone_rows)
-
-        logger.info("Creating decode instance...")
-        client.request_json("POST", "/instance", body={"instance": decode_instance})
-        wait_for_instance_ready(client, decode_id)
-        decode_alive = True
-        logger.info("Decode instance ready")
-
-        logger.info("Linking instances (prefill → decode)...")
-        _create_instance_link(client, prefill_id, decode_id)
-        time.sleep(1)
-        links = _list_instance_links(client)
-        if not links:
-            logger.error("Link did not appear in state.")
-            return 1
-        link_id = str(links[-1].get("linkId") or links[-1].get("link_id") or "")
-        logger.info(f"Link created: {link_id}")
-        time.sleep(2)
-
-        disagg_rows = _run_phase(
-            client=client,
-            label="disaggregated",
-            pp_tg_pairs=pp_tg_pairs,
-            model_id=decode_full_id,
-            prompt_sizer=decode_prompt_sizer,
-            warmup=args.warmup,
-            repeat=args.repeat,
-            common_meta=common_meta,
-            sampler=sampler,
-        )
-        all_rows.extend(disagg_rows)
-
-        if args.compare_baseline:
-            logger.info("Removing link and prefill instance to isolate decode_alone.")
-            with contextlib.suppress(ExoHttpError):
-                if link_id:
-                    _delete_instance_link(client, link_id)
-                    link_id = ""
-            with contextlib.suppress(ExoHttpError):
-                client.request_json("DELETE", f"/instance/{prefill_id}")
-            wait_for_instance_gone(client, prefill_id)
-            prefill_alive = False
-            time.sleep(2)
-
-            decode_alone_rows = _run_phase(
-                client=client,
-                label="decode_alone",
-                pp_tg_pairs=pp_tg_pairs,
-                model_id=decode_full_id,
-                prompt_sizer=decode_prompt_sizer,
-                warmup=args.warmup,
-                repeat=args.repeat,
-                common_meta=common_meta,
-                sampler=sampler,
-            )
-            all_rows.extend(decode_alone_rows)
-
-            _print_diff(disagg_rows, decode_alone_rows, prefill_alone_rows)
-    finally:
-        sampler.stop()
-        with contextlib.suppress(ExoHttpError):
-            if link_id:
-                _delete_instance_link(client, link_id)
-        if decode_alive:
-            with contextlib.suppress(ExoHttpError):
-                client.request_json("DELETE", f"/instance/{decode_id}")
-            wait_for_instance_gone(client, decode_id)
-        if prefill_alive:
-            with contextlib.suppress(ExoHttpError):
-                client.request_json("DELETE", f"/instance/{prefill_id}")
-            wait_for_instance_gone(client, prefill_id)
-        logger.debug("Deleted both instances")
-
-    if args.stdout:
-        json.dump(all_rows, sys.stdout, indent=2, ensure_ascii=False)
-    elif args.json_out:
-        with open(args.json_out, "w", encoding="utf-8") as f:
-            json.dump(all_rows, f, indent=2, ensure_ascii=False)
-        logger.debug(f"\nWrote results JSON: {args.json_out}")
-
-    return 0
-
-
-if __name__ == "__main__":
-    sys.exit(main())

bench/pyproject.toml

@@ -1,23 +0,0 @@
-[project]
-name = "exo-bench"
-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",
-  "datasets>=2.0.0",
-  "math-verify>=0.7.0",
-  "lm-eval[api,math]>=0.4.0",
-  "human-eval>=1.0.3",
-  "numpy>=1.24.0",
-]
-
-[build-system]
-requires = ["hatchling"]
-build-backend = "hatchling.build"

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))"]

bench/vendor/lcb_testing_util.py

@@ -1,593 +0,0 @@
-# type: ignore
-# Vendored from LiveCodeBench (https://github.com/LiveCodeBench/LiveCodeBench)
-# File: lcb_runner/evaluation/testing_util.py
-# License: MIT
-# Vendored 2026-03-07 — do not modify without updating from upstream.
-
-import ast
-import faulthandler
-import json
-import platform
-
-# to run the solution files we're using a timing based approach
-import signal
-import sys
-import time
-
-# used for debugging to time steps
-from datetime import datetime
-from decimal import Decimal
-from enum import Enum
-from io import StringIO
-
-# from pyext import RuntimeModule
-from types import ModuleType
-
-# used for testing the code that reads from input
-from unittest.mock import mock_open, patch
-
-import_string = "from string import *\nfrom re import *\nfrom datetime import *\nfrom collections import *\nfrom heapq import *\nfrom bisect import *\nfrom copy import *\nfrom math import *\nfrom random import *\nfrom statistics import *\nfrom itertools import *\nfrom functools import *\nfrom operator import *\nfrom io import *\nfrom sys import *\nfrom json import *\nfrom builtins import *\nfrom typing import *\nimport string\nimport re\nimport datetime\nimport collections\nimport heapq\nimport bisect\nimport copy\nimport math\nimport random\nimport statistics\nimport itertools\nimport functools\nimport operator\nimport io\nimport sys\nimport json\nsys.setrecursionlimit(50000)\n"
-
-
-def truncatefn(s, length=300):
-    if isinstance(s, str):
-        pass
-    else:
-        s = str(s)
-    if len(s) <= length:
-        return s
-
-    return s[: length // 2] + "...(truncated) ..." + s[-length // 2 :]
-
-
-class CODE_TYPE(Enum):
-    call_based = 0
-    standard_input = 1
-
-
-# stuff for setting up signal timer
-class TimeoutException(Exception):
-    pass
-
-
-def timeout_handler(signum, frame):
-    print("timeout occured: alarm went off")
-    raise TimeoutException
-
-
-# used to capture stdout as a list
-# from https://stackoverflow.com/a/16571630/6416660
-# alternative use redirect_stdout() from contextlib
-class Capturing(list):
-    def __enter__(self):
-        self._stdout = sys.stdout
-        sys.stdout = self._stringio = StringIO()
-        # Make closing the StringIO a no-op
-        self._stringio.close = lambda x: 1
-        return self
-
-    def __exit__(self, *args):
-        self.append(self._stringio.getvalue())
-        del self._stringio  # free up some memory
-        sys.stdout = self._stdout
-
-
-# Custom mock for sys.stdin that supports buffer attribute
-class MockStdinWithBuffer:
-    def __init__(self, inputs: str):
-        self.inputs = inputs
-        self._stringio = StringIO(inputs)
-        self.buffer = MockBuffer(inputs)
-
-    def read(self, *args):
-        return self.inputs
-
-    def readline(self, *args):
-        return self._stringio.readline(*args)
-
-    def readlines(self, *args):
-        return self.inputs.split("\n")
-
-    def __getattr__(self, name):
-        # Delegate other attributes to StringIO
-        return getattr(self._stringio, name)
-
-
-class MockBuffer:
-    def __init__(self, inputs: str):
-        self.inputs = inputs.encode("utf-8")  # Convert to bytes
-
-    def read(self, *args):
-        # Return as byte strings that can be split
-        return self.inputs
-
-    def readline(self, *args):
-        return self.inputs.split(b"\n")[0] + b"\n"
-
-
-def clean_if_name(code: str) -> str:
-    try:
-        astree = ast.parse(code)
-        last_block = astree.body[-1]
-        if isinstance(last_block, ast.If):
-            condition = last_block.test
-            if ast.unparse(condition).strip() == "__name__ == '__main__'":
-                code = (
-                    ast.unparse(astree.body[:-1]) + "\n" + ast.unparse(last_block.body)  # type: ignore
-                )
-    except:
-        pass
-
-    return code
-
-
-def make_function(code: str) -> str:
-    try:
-        import_stmts = []
-        all_other_stmts = []
-        astree = ast.parse(code)
-        for stmt in astree.body:
-            if isinstance(stmt, (ast.Import, ast.ImportFrom)):
-                import_stmts.append(stmt)
-            else:
-                all_other_stmts.append(stmt)
-
-        function_ast = ast.FunctionDef(
-            name="wrapped_function",
-            args=ast.arguments(
-                posonlyargs=[], args=[], kwonlyargs=[], kw_defaults=[], defaults=[]
-            ),
-            body=all_other_stmts,
-            decorator_list=[],
-            lineno=-1,
-        )
-        main_code = (
-            import_string
-            + "\n"
-            + ast.unparse(import_stmts)
-            + "\n"
-            + ast.unparse(function_ast)
-        )
-        return main_code
-    except Exception:
-        return code
-
-
-def call_method(method, inputs):
-    if isinstance(inputs, list):
-        inputs = "\n".join(inputs)
-
-    inputs_line_iterator = iter(inputs.split("\n"))
-
-    # Create custom stdin mock with buffer support
-    mock_stdin = MockStdinWithBuffer(inputs)
-
-    # sys.setrecursionlimit(10000)
-
-    # @patch('builtins.input', side_effect=inputs.split("\n"))
-    @patch("builtins.open", mock_open(read_data=inputs))
-    @patch("sys.stdin", mock_stdin)  # Use our custom mock instead of StringIO
-    @patch("sys.stdin.readline", lambda *args: next(inputs_line_iterator))
-    @patch("sys.stdin.readlines", lambda *args: inputs.split("\n"))
-    @patch("sys.stdin.read", lambda *args: inputs)
-    # @patch('sys.stdout.write', print)
-    def _inner_call_method(_method):
-        try:
-            return _method()
-        except SystemExit:
-            pass
-        finally:
-            pass
-
-    return _inner_call_method(method)
-
-
-def get_function(compiled_sol, fn_name: str):  # type: ignore
-    try:
-        assert hasattr(compiled_sol, fn_name)
-        return getattr(compiled_sol, fn_name)
-    except Exception:
-        return
-
-
-def compile_code(code: str, timeout: int):
-    signal.alarm(timeout)
-    try:
-        tmp_sol = ModuleType("tmp_sol", "")
-        exec(code, tmp_sol.__dict__)
-        if "class Solution" in code:
-            # leetcode wraps solutions in `Solution`
-            # this is a hack to check if it is leetcode solution or not
-            # currently livecodebench only supports LeetCode but
-            # else condition allows future extensibility to other platforms
-            compiled_sol = tmp_sol.Solution()
-        else:
-            # do nothing in the other case since function is accesible
-            compiled_sol = tmp_sol
-
-        assert compiled_sol is not None
-    finally:
-        signal.alarm(0)
-
-    return compiled_sol
-
-
-def convert_line_to_decimals(line: str) -> tuple[bool, list[Decimal]]:
-    try:
-        decimal_line = [Decimal(elem) for elem in line.split()]
-    except:
-        return False, []
-    return True, decimal_line
-
-
-def get_stripped_lines(val: str):
-    ## you don't want empty lines to add empty list after splitlines!
-    val = val.strip()
-
-    return [val_line.strip() for val_line in val.split("\n")]
-
-
-def grade_call_based(
-    code: str, all_inputs: list, all_outputs: list, fn_name: str, timeout: int
-):
-    # call-based clean up logic
-    # need to wrap in try-catch logic after to catch the correct errors, but for now this is fine.
-    code = import_string + "\n\n" + code
-    compiled_sol = compile_code(code, timeout)
-
-    if compiled_sol is None:
-        return
-
-    method = get_function(compiled_sol, fn_name)
-
-    if method is None:
-        return
-
-    all_inputs = [
-        [json.loads(line) for line in inputs.split("\n")] for inputs in all_inputs
-    ]
-
-    all_outputs = [json.loads(output) for output in all_outputs]
-
-    total_execution = 0
-    all_results = []
-    for idx, (gt_inp, gt_out) in enumerate(zip(all_inputs, all_outputs)):
-        signal.alarm(timeout)
-        faulthandler.enable()
-        try:
-            # can lock here so time is useful
-            start = time.time()
-            prediction = method(*gt_inp)
-            total_execution += time.time() - start
-            signal.alarm(0)
-
-            # don't penalize model if it produces tuples instead of lists
-            # ground truth sequences are not tuples
-            if isinstance(prediction, tuple):
-                prediction = list(prediction)
-
-            tmp_result = prediction == gt_out
-
-            # handle floating point comparisons
-
-            all_results.append(tmp_result)
-
-            if not tmp_result:
-                return all_results, {
-                    "output": truncatefn(prediction),
-                    "inputs": truncatefn(gt_inp),
-                    "expected": truncatefn(gt_out),
-                    "error_code": -2,
-                    "error_message": "Wrong Answer",
-                }
-        except Exception as e:
-            signal.alarm(0)
-            if "timeoutexception" in repr(e).lower():
-                all_results.append(-3)
-                return all_results, {
-                    "error": repr(e),
-                    "error_code": -3,
-                    "error_message": "Time Limit Exceeded",
-                    "inputs": truncatefn(gt_inp),
-                    "expected": truncatefn(gt_out),
-                }
-            else:
-                all_results.append(-4)
-                return all_results, {
-                    "error": repr(e),
-                    "error_code": -4,
-                    "error_message": "Runtime Error",
-                    "inputs": truncatefn(gt_inp),
-                    "expected": truncatefn(gt_out),
-                }
-
-        finally:
-            signal.alarm(0)
-            faulthandler.disable()
-
-    return all_results, {"execution time": total_execution}
-
-
-def grade_stdio(
-    code: str,
-    all_inputs: list,
-    all_outputs: list,
-    timeout: int,
-):
-    ## runtime doesn't interact well with __name__ == '__main__'
-    code = clean_if_name(code)
-
-    ## we wrap the given code inside another function
-    code = make_function(code)
-
-    compiled_sol = compile_code(code, timeout)
-    if compiled_sol is None:
-        return
-
-    method = get_function(compiled_sol, "wrapped_function")
-
-    if method is None:
-        return
-
-    all_results = []
-    total_execution_time = 0
-    for idx, (gt_inp, gt_out) in enumerate(zip(all_inputs, all_outputs)):
-        signal.alarm(timeout)
-        faulthandler.enable()
-
-        signal.alarm(timeout)
-        with Capturing() as captured_output:
-            try:
-                start = time.time()
-                call_method(method, gt_inp)
-                total_execution_time += time.time() - start
-                # reset the alarm
-                signal.alarm(0)
-            except Exception as e:
-                signal.alarm(0)
-                if "timeoutexception" in repr(e).lower():
-                    all_results.append(-3)
-                    return all_results, {
-                        "error": repr(e),
-                        "error_code": -3,
-                        "error_message": "Time Limit Exceeded",
-                        "inputs": truncatefn(gt_inp),
-                        "expected": truncatefn(gt_out),
-                    }
-                else:
-                    all_results.append(-4)
-                    return all_results, {
-                        "error": repr(e),
-                        "error_code": -4,
-                        "error_message": "Runtime Error",
-                        "inputs": truncatefn(gt_inp),
-                        "expected": truncatefn(gt_out),
-                    }
-
-            finally:
-                signal.alarm(0)
-                faulthandler.disable()
-
-        prediction = captured_output[0]
-
-        stripped_prediction_lines = get_stripped_lines(prediction)
-        stripped_gt_out_lines = get_stripped_lines(gt_out)
-
-        ## WA happens in multiple circumstances
-        ## so cache the return to make it clean!
-        WA_send_args = {
-            "output": truncatefn(prediction),
-            "inputs": truncatefn(gt_inp),
-            "expected": truncatefn(gt_out),
-            "error_code": -2,
-        }
-
-        if len(stripped_prediction_lines) != len(stripped_gt_out_lines):
-            all_results.append(-2)
-            WA_send_args["error_message"] = "Wrong answer: mismatched output length"
-            return all_results, WA_send_args
-
-        for output_line_idx, (
-            stripped_prediction_line,
-            stripped_gt_out_line,
-        ) in enumerate(zip(stripped_prediction_lines, stripped_gt_out_lines)):
-            WA_send_args["error_message"] = (
-                f"Wrong answer at {output_line_idx=}: {truncatefn(stripped_prediction_line)} != {truncatefn(stripped_gt_out_line)}"
-            )
-
-            ## CASE 1: exact match
-            if stripped_prediction_line == stripped_gt_out_line:
-                continue
-
-            ## CASE 2: element-wise comparision
-            ## if there are floating elements
-            ## use `decimal` library for good floating point comparision
-            ## otherwise gotcha: np.isclose(50000000000000000, 50000000000000001) = True
-            ## note that we should always be able to convert to decimals
-
-            success, decimal_prediction_line = convert_line_to_decimals(
-                stripped_prediction_line
-            )
-            if not success:
-                all_results.append(-2)
-                return all_results, WA_send_args
-            success, decimal_gtout_line = convert_line_to_decimals(stripped_gt_out_line)
-            if not success:
-                all_results.append(-2)
-                return all_results, WA_send_args
-
-            if decimal_prediction_line == decimal_gtout_line:
-                continue
-
-            all_results.append(-2)
-            return all_results, WA_send_args
-        all_results.append(True)
-
-    return all_results, {"execution time": total_execution_time}
-
-
-def run_test(sample, test=None, debug=False, timeout=6):
-    """
-    if test(generated_code) is not None it'll try to run the code.
-    otherwise it'll just return an input and output pair.
-    """
-    signal.signal(signal.SIGALRM, timeout_handler)
-
-    # Disable functionalities that can make destructive changes to the test.
-    # max memory is set to 4GB
-    reliability_guard()
-
-    if debug:
-        print(f"start = {datetime.now().time()}")
-
-    try:
-        in_outs = json.loads(sample["input_output"])
-    except ValueError as e:
-        raise e
-        in_outs = None
-
-    if in_outs:
-        if in_outs.get("fn_name") is None:
-            which_type = CODE_TYPE.standard_input  # Standard input
-            method_name = None
-
-        else:
-            which_type = CODE_TYPE.call_based  # Call-based
-            method_name = in_outs["fn_name"]
-
-    if debug:
-        print(f"loaded input_output = {datetime.now().time()}")
-
-    if test is None:
-        assert False, "should not happen: test code is none"
-        return in_outs, {"error": "no test code provided"}
-    elif test is not None:
-        results = []
-        sol = import_string
-        if debug:
-            print(f"loading test code = {datetime.now().time()}")
-
-        if which_type == CODE_TYPE.call_based:
-            signal.alarm(timeout)
-            try:
-                results, metadata = grade_call_based(
-                    code=test,
-                    all_inputs=in_outs["inputs"],
-                    all_outputs=in_outs["outputs"],
-                    fn_name=method_name,
-                    timeout=timeout,
-                )
-                return results, metadata
-            except Exception as e:
-                return [-4], {
-                    "error_code": -4,
-                    "error_message": f"Error during testing: {e}",
-                }
-            finally:
-                signal.alarm(0)
-        elif which_type == CODE_TYPE.standard_input:
-            # sol
-            # if code has if __name__ == "__main__": then remove it
-
-            signal.alarm(timeout)
-            try:
-                results, metadata = grade_stdio(
-                    code=test,
-                    all_inputs=in_outs["inputs"],
-                    all_outputs=in_outs["outputs"],
-                    timeout=timeout,
-                )
-                return results, metadata
-            except Exception as e:
-                return [-4], {
-                    "error_code": -4,
-                    "error_message": f"Error during testing: {e}",
-                }
-            finally:
-                signal.alarm(0)
-
-
-def reliability_guard(maximum_memory_bytes=None):
-    """
-    This disables various destructive functions and prevents the generated code
-    from interfering with the test (e.g. fork bomb, killing other processes,
-    removing filesystem files, etc.)
-    WARNING
-    This function is NOT a security sandbox. Untrusted code, including, model-
-    generated code, should not be blindly executed outside of one. See the
-    Codex paper for more information about OpenAI's code sandbox, and proceed
-    with caution.
-    """
-
-    if maximum_memory_bytes is not None:
-        import resource
-
-        resource.setrlimit(
-            resource.RLIMIT_AS, (maximum_memory_bytes, maximum_memory_bytes)
-        )
-        resource.setrlimit(
-            resource.RLIMIT_DATA, (maximum_memory_bytes, maximum_memory_bytes)
-        )
-        if not platform.uname().system == "Darwin":
-            resource.setrlimit(
-                resource.RLIMIT_STACK, (maximum_memory_bytes, maximum_memory_bytes)
-            )
-
-    faulthandler.disable()
-
-    import builtins
-
-    # builtins.exit = None
-    builtins.quit = None
-
-    import os
-
-    os.environ["OMP_NUM_THREADS"] = "1"
-
-    os.kill = None
-    os.system = None
-    os.putenv = None
-    os.remove = None
-    os.removedirs = None
-    os.rmdir = None
-    os.fchdir = None
-    os.setuid = None
-    os.fork = None
-    os.forkpty = None
-    os.killpg = None
-    os.rename = None
-    os.renames = None
-    os.truncate = None
-    os.replace = None
-    os.unlink = None
-    os.fchmod = None
-    os.fchown = None
-    os.chmod = None
-    os.chown = None
-    os.chroot = None
-    os.fchdir = None
-    os.lchflags = None
-    os.lchmod = None
-    os.lchown = None
-    os.getcwd = None
-    os.chdir = None
-
-    import shutil
-
-    shutil.rmtree = None
-    shutil.move = None
-    shutil.chown = None
-
-    import subprocess
-
-    subprocess.Popen = None
-
-    __builtins__["help"] = None
-
-    import sys
-
-    sys.modules["ipdb"] = None
-    sys.modules["joblib"] = None
-    sys.modules["resource"] = None
-    sys.modules["psutil"] = None
-    sys.modules["tkinter"] = None

dashboard/package-lock.json

@@ -11,16 +11,16 @@
 				"highlight.js": "^11.11.1",
 				"katex": "^0.16.27",
 				"marked": "^17.0.1",
-				"mode-watcher": "^1.1.0",
-				"pdfjs-dist": "^5.6.205"
+				"mode-watcher": "^1.1.0"
 			},
 			"devDependencies": {
+				"@playwright/test": "^1.41.0",
 				"@sveltejs/adapter-static": "^3.0.10",
 				"@sveltejs/kit": "^2.48.4",
 				"@sveltejs/vite-plugin-svelte": "^5.0.0",
 				"@tailwindcss/vite": "^4.0.0",
 				"@types/d3": "^7.4.3",
-				"@types/node": "^22",
+				"@types/node": "^22.19.8",
 				"d3": "^7.9.0",
 				"prettier": "^3.4.2",
 				"prettier-plugin-svelte": "^3.3.3",
@@ -519,254 +519,20 @@
 				"@jridgewell/sourcemap-codec": "^1.4.14"
 			}
 		},
-		"node_modules/@napi-rs/canvas": {
-			"version": "0.1.97",
-			"resolved": "https://registry.npmjs.org/@napi-rs/canvas/-/canvas-0.1.97.tgz",
-			"integrity": "sha512-8cFniXvrIEnVwuNSRCW9wirRZbHvrD3JVujdS2P5n5xiJZNZMOZcfOvJ1pb66c7jXMKHHglJEDVJGbm8XWFcXQ==",
-			"license": "MIT",
-			"optional": true,
-			"workspaces": [
-				"e2e/*"
-			],
+		"node_modules/@playwright/test": {
+			"version": "1.58.1",
+			"resolved": "https://registry.npmjs.org/@playwright/test/-/test-1.58.1.tgz",
+			"integrity": "sha512-6LdVIUERWxQMmUSSQi0I53GgCBYgM2RpGngCPY7hSeju+VrKjq3lvs7HpJoPbDiY5QM5EYRtRX5fvrinnMAz3w==",
+			"dev": true,
+			"license": "Apache-2.0",
+			"dependencies": {
+				"playwright": "1.58.1"
+			},
+			"bin": {
+				"playwright": "cli.js"
+			},
 			"engines": {
-				"node": ">= 10"
-			},
-			"funding": {
-				"type": "github",
-				"url": "https://github.com/sponsors/Brooooooklyn"
-			},
-			"optionalDependencies": {
-				"@napi-rs/canvas-android-arm64": "0.1.97",
-				"@napi-rs/canvas-darwin-arm64": "0.1.97",
-				"@napi-rs/canvas-darwin-x64": "0.1.97",
-				"@napi-rs/canvas-linux-arm-gnueabihf": "0.1.97",
-				"@napi-rs/canvas-linux-arm64-gnu": "0.1.97",
-				"@napi-rs/canvas-linux-arm64-musl": "0.1.97",
-				"@napi-rs/canvas-linux-riscv64-gnu": "0.1.97",
-				"@napi-rs/canvas-linux-x64-gnu": "0.1.97",
-				"@napi-rs/canvas-linux-x64-musl": "0.1.97",
-				"@napi-rs/canvas-win32-arm64-msvc": "0.1.97",
-				"@napi-rs/canvas-win32-x64-msvc": "0.1.97"
-			}
-		},
-		"node_modules/@napi-rs/canvas-android-arm64": {
-			"version": "0.1.97",
-			"resolved": "https://registry.npmjs.org/@napi-rs/canvas-android-arm64/-/canvas-android-arm64-0.1.97.tgz",
-			"integrity": "sha512-V1c/WVw+NzH8vk7ZK/O8/nyBSCQimU8sfMsB/9qeSvdkGKNU7+mxy/bIF0gTgeBFmHpj30S4E9WHMSrxXGQuVQ==",
-			"cpu": [
-				"arm64"
-			],
-			"license": "MIT",
-			"optional": true,
-			"os": [
-				"android"
-			],
-			"engines": {
-				"node": ">= 10"
-			},
-			"funding": {
-				"type": "github",
-				"url": "https://github.com/sponsors/Brooooooklyn"
-			}
-		},
-		"node_modules/@napi-rs/canvas-darwin-arm64": {
-			"version": "0.1.97",
-			"resolved": "https://registry.npmjs.org/@napi-rs/canvas-darwin-arm64/-/canvas-darwin-arm64-0.1.97.tgz",
-			"integrity": "sha512-ok+SCEF4YejcxuJ9Rm+WWunHHpf2HmiPxfz6z1a/NFQECGXtsY7A4B8XocK1LmT1D7P174MzwPF9Wy3AUAwEPw==",
-			"cpu": [
-				"arm64"
-			],
-			"license": "MIT",
-			"optional": true,
-			"os": [
-				"darwin"
-			],
-			"engines": {
-				"node": ">= 10"
-			},
-			"funding": {
-				"type": "github",
-				"url": "https://github.com/sponsors/Brooooooklyn"
-			}
-		},
-		"node_modules/@napi-rs/canvas-darwin-x64": {
-			"version": "0.1.97",
-			"resolved": "https://registry.npmjs.org/@napi-rs/canvas-darwin-x64/-/canvas-darwin-x64-0.1.97.tgz",
-			"integrity": "sha512-PUP6e6/UGlclUvAQNnuXCcnkpdUou6VYZfQOQxExLp86epOylmiwLkqXIvpFmjoTEDmPmXrI+coL/9EFU1gKPA==",
-			"cpu": [
-				"x64"
-			],
-			"license": "MIT",
-			"optional": true,
-			"os": [
-				"darwin"
-			],
-			"engines": {
-				"node": ">= 10"
-			},
-			"funding": {
-				"type": "github",
-				"url": "https://github.com/sponsors/Brooooooklyn"
-			}
-		},
-		"node_modules/@napi-rs/canvas-linux-arm-gnueabihf": {
-			"version": "0.1.97",
-			"resolved": "https://registry.npmjs.org/@napi-rs/canvas-linux-arm-gnueabihf/-/canvas-linux-arm-gnueabihf-0.1.97.tgz",
-			"integrity": "sha512-XyXH2L/cic8eTNtbrXCcvqHtMX/nEOxN18+7rMrAM2XtLYC/EB5s0wnO1FsLMWmK+04ZSLN9FBGipo7kpIkcOw==",
-			"cpu": [
-				"arm"
-			],
-			"license": "MIT",
-			"optional": true,
-			"os": [
-				"linux"
-			],
-			"engines": {
-				"node": ">= 10"
-			},
-			"funding": {
-				"type": "github",
-				"url": "https://github.com/sponsors/Brooooooklyn"
-			}
-		},
-		"node_modules/@napi-rs/canvas-linux-arm64-gnu": {
-			"version": "0.1.97",
-			"resolved": "https://registry.npmjs.org/@napi-rs/canvas-linux-arm64-gnu/-/canvas-linux-arm64-gnu-0.1.97.tgz",
-			"integrity": "sha512-Kuq/M3djq0K8ktgz6nPlK7Ne5d4uWeDxPpyKWOjWDK2RIOhHVtLtyLiJw2fuldw7Vn4mhw05EZXCEr4Q76rs9w==",
-			"cpu": [
-				"arm64"
-			],
-			"license": "MIT",
-			"optional": true,
-			"os": [
-				"linux"
-			],
-			"engines": {
-				"node": ">= 10"
-			},
-			"funding": {
-				"type": "github",
-				"url": "https://github.com/sponsors/Brooooooklyn"
-			}
-		},
-		"node_modules/@napi-rs/canvas-linux-arm64-musl": {
-			"version": "0.1.97",
-			"resolved": "https://registry.npmjs.org/@napi-rs/canvas-linux-arm64-musl/-/canvas-linux-arm64-musl-0.1.97.tgz",
-			"integrity": "sha512-kKmSkQVnWeqg7qdsiXvYxKhAFuHz3tkBjW/zyQv5YKUPhotpaVhpBGv5LqCngzyuRV85SXoe+OFj+Tv0a0QXkQ==",
-			"cpu": [
-				"arm64"
-			],
-			"license": "MIT",
-			"optional": true,
-			"os": [
-				"linux"
-			],
-			"engines": {
-				"node": ">= 10"
-			},
-			"funding": {
-				"type": "github",
-				"url": "https://github.com/sponsors/Brooooooklyn"
-			}
-		},
-		"node_modules/@napi-rs/canvas-linux-riscv64-gnu": {
-			"version": "0.1.97",
-			"resolved": "https://registry.npmjs.org/@napi-rs/canvas-linux-riscv64-gnu/-/canvas-linux-riscv64-gnu-0.1.97.tgz",
-			"integrity": "sha512-Jc7I3A51jnEOIAXeLsN/M/+Z28LUeakcsXs07FLq9prXc0eYOtVwsDEv913Gr+06IRo34gJJVgT0TXvmz+N2VA==",
-			"cpu": [
-				"riscv64"
-			],
-			"license": "MIT",
-			"optional": true,
-			"os": [
-				"linux"
-			],
-			"engines": {
-				"node": ">= 10"
-			},
-			"funding": {
-				"type": "github",
-				"url": "https://github.com/sponsors/Brooooooklyn"
-			}
-		},
-		"node_modules/@napi-rs/canvas-linux-x64-gnu": {
-			"version": "0.1.97",
-			"resolved": "https://registry.npmjs.org/@napi-rs/canvas-linux-x64-gnu/-/canvas-linux-x64-gnu-0.1.97.tgz",
-			"integrity": "sha512-iDUBe7AilfuBSRbSa8/IGX38Mf+iCSBqoVKLSQ5XaY2JLOaqz1TVyPFEyIck7wT6mRQhQt5sN6ogfjIDfi74tg==",
-			"cpu": [
-				"x64"
-			],
-			"license": "MIT",
-			"optional": true,
-			"os": [
-				"linux"
-			],
-			"engines": {
-				"node": ">= 10"
-			},
-			"funding": {
-				"type": "github",
-				"url": "https://github.com/sponsors/Brooooooklyn"
-			}
-		},
-		"node_modules/@napi-rs/canvas-linux-x64-musl": {
-			"version": "0.1.97",
-			"resolved": "https://registry.npmjs.org/@napi-rs/canvas-linux-x64-musl/-/canvas-linux-x64-musl-0.1.97.tgz",
-			"integrity": "sha512-AKLFd/v0Z5fvgqBDqhvqtAdx+fHMJ5t9JcUNKq4FIZ5WH+iegGm8HPdj00NFlCSnm83Fp3Ln8I2f7uq1aIiWaA==",
-			"cpu": [
-				"x64"
-			],
-			"license": "MIT",
-			"optional": true,
-			"os": [
-				"linux"
-			],
-			"engines": {
-				"node": ">= 10"
-			},
-			"funding": {
-				"type": "github",
-				"url": "https://github.com/sponsors/Brooooooklyn"
-			}
-		},
-		"node_modules/@napi-rs/canvas-win32-arm64-msvc": {
-			"version": "0.1.97",
-			"resolved": "https://registry.npmjs.org/@napi-rs/canvas-win32-arm64-msvc/-/canvas-win32-arm64-msvc-0.1.97.tgz",
-			"integrity": "sha512-u883Yr6A6fO7Vpsy9YE4FVCIxzzo5sO+7pIUjjoDLjS3vQaNMkVzx5bdIpEL+ob+gU88WDK4VcxYMZ6nmnoX9A==",
-			"cpu": [
-				"arm64"
-			],
-			"license": "MIT",
-			"optional": true,
-			"os": [
-				"win32"
-			],
-			"engines": {
-				"node": ">= 10"
-			},
-			"funding": {
-				"type": "github",
-				"url": "https://github.com/sponsors/Brooooooklyn"
-			}
-		},
-		"node_modules/@napi-rs/canvas-win32-x64-msvc": {
-			"version": "0.1.97",
-			"resolved": "https://registry.npmjs.org/@napi-rs/canvas-win32-x64-msvc/-/canvas-win32-x64-msvc-0.1.97.tgz",
-			"integrity": "sha512-sWtD2EE3fV0IzN+iiQUqr/Q1SwqWhs2O1FKItFlxtdDkikpEj5g7DKQpY3x55H/MAOnL8iomnlk3mcEeGiUMoQ==",
-			"cpu": [
-				"x64"
-			],
-			"license": "MIT",
-			"optional": true,
-			"os": [
-				"win32"
-			],
-			"engines": {
-				"node": ">= 10"
-			},
-			"funding": {
-				"type": "github",
-				"url": "https://github.com/sponsors/Brooooooklyn"
+				"node": ">=18"
 			}
 		},
 		"node_modules/@polka/url": {
@@ -1766,9 +1532,9 @@
 			"license": "MIT"
 		},
 		"node_modules/@types/node": {
-			"version": "22.19.1",
-			"resolved": "https://registry.npmjs.org/@types/node/-/node-22.19.1.tgz",
-			"integrity": "sha512-LCCV0HdSZZZb34qifBsyWlUmok6W7ouER+oQIGBScS8EsZsQbrtFTUrDX4hOl+CS6p7cnNC4td+qrSVGSCTUfQ==",
+			"version": "22.19.8",
+			"resolved": "https://registry.npmjs.org/@types/node/-/node-22.19.8.tgz",
+			"integrity": "sha512-ebO/Yl+EAvVe8DnMfi+iaAyIqYdK0q/q0y0rw82INWEKJOBe6b/P3YWE8NW7oOlF/nXFNrHwhARrN/hdgDkraA==",
 			"dev": true,
 			"license": "MIT",
 			"dependencies": {
@@ -2886,26 +2652,6 @@
 				"node": "^10 || ^12 || ^13.7 || ^14 || >=15.0.1"
 			}
 		},
-		"node_modules/node-readable-to-web-readable-stream": {
-			"version": "0.4.2",
-			"resolved": "https://registry.npmjs.org/node-readable-to-web-readable-stream/-/node-readable-to-web-readable-stream-0.4.2.tgz",
-			"integrity": "sha512-/cMZNI34v//jUTrI+UIo4ieHAB5EZRY/+7OmXZgBxaWBMcW2tGdceIw06RFxWxrKZ5Jp3sI2i5TsRo+CBhtVLQ==",
-			"license": "MIT",
-			"optional": true
-		},
-		"node_modules/pdfjs-dist": {
-			"version": "5.6.205",
-			"resolved": "https://registry.npmjs.org/pdfjs-dist/-/pdfjs-dist-5.6.205.tgz",
-			"integrity": "sha512-tlUj+2IDa7G1SbvBNN74UHRLJybZDWYom+k6p5KIZl7huBvsA4APi6mKL+zCxd3tLjN5hOOEE9Tv7VdzO88pfg==",
-			"license": "Apache-2.0",
-			"engines": {
-				"node": ">=20.19.0 || >=22.13.0 || >=24"
-			},
-			"optionalDependencies": {
-				"@napi-rs/canvas": "^0.1.96",
-				"node-readable-to-web-readable-stream": "^0.4.2"
-			}
-		},
 		"node_modules/picocolors": {
 			"version": "1.1.1",
 			"resolved": "https://registry.npmjs.org/picocolors/-/picocolors-1.1.1.tgz",
@@ -2926,6 +2672,53 @@
 				"url": "https://github.com/sponsors/jonschlinkert"
 			}
 		},
+		"node_modules/playwright": {
+			"version": "1.58.1",
+			"resolved": "https://registry.npmjs.org/playwright/-/playwright-1.58.1.tgz",
+			"integrity": "sha512-+2uTZHxSCcxjvGc5C891LrS1/NlxglGxzrC4seZiVjcYVQfUa87wBL6rTDqzGjuoWNjnBzRqKmF6zRYGMvQUaQ==",
+			"dev": true,
+			"license": "Apache-2.0",
+			"dependencies": {
+				"playwright-core": "1.58.1"
+			},
+			"bin": {
+				"playwright": "cli.js"
+			},
+			"engines": {
+				"node": ">=18"
+			},
+			"optionalDependencies": {
+				"fsevents": "2.3.2"
+			}
+		},
+		"node_modules/playwright-core": {
+			"version": "1.58.1",
+			"resolved": "https://registry.npmjs.org/playwright-core/-/playwright-core-1.58.1.tgz",
+			"integrity": "sha512-bcWzOaTxcW+VOOGBCQgnaKToLJ65d6AqfLVKEWvexyS3AS6rbXl+xdpYRMGSRBClPvyj44njOWoxjNdL/H9UNg==",
+			"dev": true,
+			"license": "Apache-2.0",
+			"bin": {
+				"playwright-core": "cli.js"
+			},
+			"engines": {
+				"node": ">=18"
+			}
+		},
+		"node_modules/playwright/node_modules/fsevents": {
+			"version": "2.3.2",
+			"resolved": "https://registry.npmjs.org/fsevents/-/fsevents-2.3.2.tgz",
+			"integrity": "sha512-xiqMQR4xAeHTuB9uWm+fFRcIOgKBMiOBP+eXiyT7jsgVCq1bkVygt00oASowB7EdtpOHaaPgKt812P9ab+DDKA==",
+			"dev": true,
+			"hasInstallScript": true,
+			"license": "MIT",
+			"optional": true,
+			"os": [
+				"darwin"
+			],
+			"engines": {
+				"node": "^8.16.0 || ^10.6.0 || >=11.0.0"
+			}
+		},
 		"node_modules/postcss": {
 			"version": "8.5.6",
 			"resolved": "https://registry.npmjs.org/postcss/-/postcss-8.5.6.tgz",

dashboard/package.json

@@ -8,18 +8,23 @@
 		"build": "vite build",
 		"preview": "vite preview",
 		"prepare": "svelte-kit sync || echo ''",
-		"check": "svelte-kit sync && svelte-check --tsconfig ./tsconfig.json"
+		"check": "svelte-kit sync && svelte-check --tsconfig ./tsconfig.json",
+		"test": "playwright test",
+		"test:e2e": "playwright test tests/e2e",
+		"test:visual": "playwright test tests/visual",
+		"test:update-snapshots": "playwright test tests/visual --update-snapshots"
 	},
 	"devDependencies": {
-		"prettier": "^3.4.2",
-		"prettier-plugin-svelte": "^3.3.3",
+		"@playwright/test": "^1.41.0",
 		"@sveltejs/adapter-static": "^3.0.10",
 		"@sveltejs/kit": "^2.48.4",
 		"@sveltejs/vite-plugin-svelte": "^5.0.0",
 		"@tailwindcss/vite": "^4.0.0",
 		"@types/d3": "^7.4.3",
-		"@types/node": "^22",
+		"@types/node": "^22.19.8",
 		"d3": "^7.9.0",
+		"prettier": "^3.4.2",
+		"prettier-plugin-svelte": "^3.3.3",
 		"svelte": "^5.0.0",
 		"svelte-check": "^4.0.0",
 		"tailwindcss": "^4.0.0",
@@ -31,7 +36,6 @@
 		"highlight.js": "^11.11.1",
 		"katex": "^0.16.27",
 		"marked": "^17.0.1",
-		"mode-watcher": "^1.1.0",
-		"pdfjs-dist": "^5.6.205"
+		"mode-watcher": "^1.1.0"
 	}
 }

dashboard/playwright.config.ts

@@ -0,0 +1,43 @@
+/// <reference types="node" />
+import { defineConfig, devices } from "@playwright/test";
+
+export default defineConfig({
+  testDir: "./tests",
+  fullyParallel: true,
+  forbidOnly: !!process.env.CI,
+  retries: process.env.CI ? 2 : 0,
+  workers: process.env.CI ? 1 : undefined,
+  reporter: [["html", { open: "never" }], ["list"]],
+  use: {
+    baseURL: "http://localhost:52415",
+    trace: "on-first-retry",
+    video: "on",
+    screenshot: "only-on-failure",
+  },
+  projects: [
+    {
+      name: "chromium",
+      use: { ...devices["Desktop Chrome"] },
+    },
+  ],
+  webServer: {
+    command: "cd .. && uv run exo",
+    url: "http://localhost:52415/node_id",
+    reuseExistingServer: !process.env.CI,
+    timeout: 300000, // 5 minutes - CI needs time to install dependencies
+    env: {
+      ...process.env,
+      // Ensure macmon and system tools are accessible
+      PATH: `/usr/sbin:/usr/bin:/opt/homebrew/bin:${process.env.PATH}`,
+      // Override memory detection for CI (macmon may not work on CI runners)
+      // 24GB is typical for GitHub Actions macos-26 runners
+      ...(process.env.CI ? { OVERRIDE_MEMORY_MB: "24000" } : {}),
+    },
+  },
+  expect: {
+    toHaveScreenshot: {
+      maxDiffPixelRatio: 0.05,
+      threshold: 0.2,
+    },
+  },
+});

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

@@ -1,15 +1,17 @@
 <script lang="ts">
   import {
     isLoading,
+    sendMessage,
+    generateImage,
+    editImage,
     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";
@@ -23,20 +25,6 @@
     autofocus?: boolean;
     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 {
@@ -46,11 +34,6 @@
     autofocus = true,
     showModelSelector = false,
     modelTasks = {},
-    modelCapabilities = {},
-    onSend,
-    onAutoSend,
-    onOpenModelPicker,
-    modelDisplayOverride,
   }: Props = $props();
 
   let message = $state("");
@@ -58,15 +41,29 @@
   let fileInputRef: HTMLInputElement | undefined = $state();
   let uploadedFiles = $state<ChatUploadedFile[]>([]);
   let isDragOver = $state(false);
-  const thinkingEnabled = $derived(thinkingEnabledStore());
   let loading = $derived(isLoading());
   const currentModel = $derived(selectedChatModel());
+  const instanceData = $derived(instances());
   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"]);
 
@@ -98,12 +95,6 @@
     );
   });
 
-  const modelSupportsThinking = $derived(() => {
-    if (!currentModel) return false;
-    const caps = modelCapabilities[currentModel] || [];
-    return caps.includes("thinking_toggle") && caps.includes("text");
-  });
-
   const isEditOnlyWithoutImage = $derived(
     currentModel !== null &&
       modelSupportsOnlyImageEditing(currentModel) &&
@@ -119,14 +110,73 @@
         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;
@@ -204,7 +254,6 @@
 
   function handleSubmit() {
     if ((!message.trim() && uploadedFiles.length === 0) || loading) return;
-    if (isEditOnlyWithoutImage) return;
 
     const content = message.trim();
     const files = [...uploadedFiles];
@@ -213,10 +262,30 @@
     uploadedFiles = [];
     resetTextareaHeight();
 
-    // Parent controls all send logic (including image routing,
-    // launching non-running models before sending, etc.)
-    onAutoSend(content, files);
-    onSend?.();
+    // Use image editing if in edit mode
+    if (isEditMode && currentEditingImage && content) {
+      editImage(content, currentEditingImage.imageDataUrl);
+    }
+    // If user attached an image with an ImageToImage model, use edit endpoint
+    else if (
+      currentModel &&
+      modelSupportsImageEditing(currentModel) &&
+      files.length > 0 &&
+      content
+    ) {
+      // Use the first attached image for editing
+      const imageFile = files[0];
+      if (imageFile.preview) {
+        editImage(content, imageFile.preview);
+      }
+    } else if (isImageModel() && content) {
+      // Use image generation for text-to-image models
+      generateImage(content);
+    } else {
+      sendMessage(content, files);
+    }
+
+    // Refocus the textarea after sending
     setTimeout(() => textareaRef?.focus(), 10);
   }
 
@@ -326,7 +395,7 @@
     {/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"
       >
@@ -335,22 +404,34 @@
             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
+              data-testid="chat-model-selector"
+              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"
@@ -367,36 +448,79 @@
               </svg>
             </div>
           </div>
-        </div>
-        <!-- Thinking toggle -->
-        {#if modelSupportsThinking()}
-          <button
-            type="button"
-            onclick={() => setConversationThinking(!thinkingEnabled)}
-            class="flex items-center gap-1.5 px-2 py-1 rounded text-xs font-mono tracking-wide transition-all duration-200 flex-shrink-0 cursor-pointer border {thinkingEnabled
-              ? 'bg-exo-yellow/15 border-exo-yellow/40 text-exo-yellow'
-              : 'bg-exo-medium-gray/30 border-exo-medium-gray/50 text-exo-light-gray/60 hover:text-exo-light-gray'}"
-            title={thinkingEnabled
-              ? "Thinking enabled — click to disable"
-              : "Thinking disabled — click to enable"}
-          >
-            <svg
-              class="w-3.5 h-3.5"
-              viewBox="0 0 24 24"
-              fill="none"
-              stroke="currentColor"
-              stroke-width="1.5"
-            >
-              <path
-                d="M12 2a7 7 0 0 0-7 7c0 2.38 1.19 4.47 3 5.74V17a1 1 0 0 0 1 1h6a1 1 0 0 0 1-1v-2.26c1.81-1.27 3-3.36 3-5.74a7 7 0 0 0-7-7zM9 20h6M10 22h4"
-                stroke-linecap="round"
-                stroke-linejoin="round"
-              />
-            </svg>
-            <span>{thinkingEnabled ? "THINK" : "NO THINK"}</span>
-          </button>
-        {/if}
 
+          {#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>
         <!-- Performance stats -->
         {#if currentTtft !== null || currentTps !== null}
           <div class="flex items-center gap-4 text-xs font-mono flex-shrink-0">
@@ -464,6 +588,7 @@
       >
 
       <textarea
+        data-testid="chat-input"
         bind:this={textareaRef}
         bind:value={message}
         onkeydown={handleKeydown}
@@ -476,97 +601,93 @@
             : isImageModel()
               ? "Describe the image you want to generate..."
               : placeholder}
+        disabled={loading}
         rows={1}
-        class="flex-1 resize-none bg-transparent text-foreground placeholder:text-exo-light-gray/60 placeholder:text-sm placeholder:tracking-[0.15em] placeholder:leading-7 focus:outline-none focus:ring-0 focus:border-none text-sm leading-7 font-mono"
+        class="flex-1 resize-none bg-transparent text-foreground placeholder:text-exo-light-gray/60 placeholder:text-sm placeholder:tracking-[0.15em] placeholder:leading-7 focus:outline-none focus:ring-0 focus:border-none disabled:opacity-50 text-sm leading-7 font-mono"
         style="min-height: 28px; max-height: 150px;"
       ></textarea>
 
-      {#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
+        data-testid="send-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

@@ -3,18 +3,14 @@
     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 {
     class?: string;
@@ -26,7 +22,6 @@
   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;
@@ -104,26 +99,6 @@
   let copiedMessageId = $state<string | null>(null);
   let expandedThinkingMessageIds = $state<Set<string>>(new Set());
 
-  // Lightbox state
-  let expandedImageSrc = $state<string | null>(null);
-
-  // Uncertainty heatmap toggle
-  let heatmapMessageIds = $state<Set<string>>(new Set());
-
-  function toggleHeatmap(messageId: string) {
-    const next = new Set(heatmapMessageIds);
-    if (next.has(messageId)) {
-      next.delete(messageId);
-    } else {
-      next.add(messageId);
-    }
-    heatmapMessageIds = next;
-  }
-
-  function isHeatmapVisible(messageId: string): boolean {
-    return heatmapMessageIds.has(messageId);
-  }
-
   function formatTimestamp(timestamp: number): string {
     return new Date(timestamp).toLocaleTimeString("en-US", {
       hour12: false,
@@ -139,8 +114,6 @@
         return "🖼";
       case "text":
         return "📄";
-      case "pdf":
-        return "📑";
       default:
         return "📎";
     }
@@ -229,7 +202,6 @@
   }
 
   function handleDeleteClick(messageId: string) {
-    if (loading) return;
     deleteConfirmId = messageId;
   }
 
@@ -260,11 +232,14 @@
 </script>
 
 <div class="flex flex-col gap-4 sm:gap-6 {className}">
-  {#each messageList as message, i (message.id)}
+  {#each messageList as message (message.id)}
     <div
       class="group flex {message.role === 'user'
         ? 'justify-end'
         : 'justify-start'}"
+      data-testid={message.role === "user"
+        ? "user-message"
+        : "assistant-message"}
     >
       <div
         class={message.role === "user"
@@ -322,11 +297,9 @@
           <!-- Delete confirmation -->
           <div class="bg-red-500/10 border border-red-500/30 rounded-lg p-3">
             <p class="text-xs text-red-400 mb-3">
-              {#if i === messageList.length - 1}
-                Delete this message?
-              {:else}
-                Delete this message and all messages after it?
-              {/if}
+              Delete this message{message.role === "user"
+                ? " and all responses after it"
+                : ""}?
             </p>
             <div class="flex gap-2 justify-end">
               <button
@@ -400,15 +373,10 @@
                         class="flex items-center gap-2 bg-exo-dark-gray/60 border border-exo-yellow/20 rounded px-2 py-1 text-xs font-mono"
                       >
                         {#if attachment.type === "image" && attachment.preview}
-                          <!-- svelte-ignore a11y_no_noninteractive_element_interactions, a11y_click_events_have_key_events -->
                           <img
                             src={attachment.preview}
                             alt={attachment.name}
-                            class="w-12 h-12 object-cover rounded border border-exo-yellow/20 cursor-pointer hover:border-exo-yellow/50 transition-colors"
-                            onclick={() => {
-                              if (attachment.preview)
-                                expandedImageSrc = attachment.preview;
-                            }}
+                            class="w-12 h-12 object-cover rounded border border-exo-yellow/20"
                           />
                         {:else}
                           <span>{getAttachmentIcon(attachment)}</span>
@@ -432,9 +400,6 @@
             {: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"
@@ -485,44 +450,15 @@
                   <div class="mb-3">
                     {#each message.attachments.filter((a) => a.type === "generated-image") as attachment}
                       <div class="relative group/img inline-block">
-                        <!-- svelte-ignore a11y_no_noninteractive_element_interactions, a11y_click_events_have_key_events -->
                         <img
                           src={attachment.preview}
                           alt=""
-                          class="max-w-full max-h-[512px] rounded-lg border border-exo-yellow/20 shadow-lg shadow-black/20 cursor-pointer"
-                          onclick={() => {
-                            if (attachment.preview)
-                              expandedImageSrc = attachment.preview;
-                          }}
+                          class="max-w-full max-h-[512px] rounded-lg border border-exo-yellow/20 shadow-lg shadow-black/20"
                         />
                         <!-- Button overlay -->
                         <div
                           class="absolute top-2 right-2 flex gap-1 opacity-0 group-hover/img:opacity-100 transition-opacity"
                         >
-                          <!-- Expand button -->
-                          <button
-                            type="button"
-                            class="p-2 rounded-lg bg-exo-dark-gray/80 border border-exo-yellow/30 text-exo-yellow hover:bg-exo-dark-gray hover:border-exo-yellow/50 cursor-pointer"
-                            onclick={() => {
-                              if (attachment.preview)
-                                expandedImageSrc = attachment.preview;
-                            }}
-                            title="Expand image"
-                          >
-                            <svg
-                              class="w-4 h-4"
-                              fill="none"
-                              viewBox="0 0 24 24"
-                              stroke="currentColor"
-                              stroke-width="2"
-                            >
-                              <path
-                                stroke-linecap="round"
-                                stroke-linejoin="round"
-                                d="M4 8V4m0 0h4M4 4l5 5m11-1V4m0 0h-4m4 0l-5 5M4 16v4m0 0h4m-4 0l5-5m11 5l-5-5m5 5v-4m0 4h-4"
-                              />
-                            </svg>
-                          </button>
                           <!-- Edit button -->
                           <button
                             type="button"
@@ -615,23 +551,13 @@
                       >
                     </div>
                   {:else if message.content || (loading && !message.attachments?.some((a) => a.type === "generated-image"))}
-                    {#if isHeatmapVisible(message.id) && message.tokens && message.tokens.length > 0}
-                      <TokenHeatmap
-                        tokens={message.tokens}
-                        isGenerating={loading &&
-                          isLastAssistantMessage(message.id)}
-                        onRegenerateFrom={(tokenIndex) =>
-                          regenerateFromToken(message.id, tokenIndex)}
-                      />
-                    {:else}
-                      <MarkdownContent
-                        content={message.content || (loading ? response : "")}
-                      />
-                      {#if loading && !message.content}
-                        <span
-                          class="inline-block w-2 h-4 bg-exo-yellow/70 ml-1 cursor-blink"
-                        ></span>
-                      {/if}
+                    <MarkdownContent
+                      content={message.content || (loading ? response : "")}
+                    />
+                    {#if loading && !message.content}
+                      <span
+                        class="inline-block w-2 h-4 bg-exo-yellow/70 ml-1 cursor-blink"
+                      ></span>
                     {/if}
                   {/if}
                 </div>
@@ -706,35 +632,6 @@
               </button>
             {/if}
 
-            <!-- Uncertainty heatmap toggle (assistant messages with tokens) -->
-            {#if message.role === "assistant" && message.tokens && message.tokens.length > 0}
-              <button
-                onclick={() => toggleHeatmap(message.id)}
-                class="p-1.5 transition-colors rounded cursor-pointer {isHeatmapVisible(
-                  message.id,
-                )
-                  ? 'text-exo-yellow'
-                  : 'text-exo-light-gray hover:text-exo-yellow'}"
-                title={isHeatmapVisible(message.id)
-                  ? "Hide uncertainty heatmap"
-                  : "Show uncertainty heatmap"}
-              >
-                <svg
-                  class="w-3.5 h-3.5"
-                  fill="none"
-                  viewBox="0 0 24 24"
-                  stroke="currentColor"
-                >
-                  <path
-                    stroke-linecap="round"
-                    stroke-linejoin="round"
-                    stroke-width="2"
-                    d="M9 19v-6a2 2 0 00-2-2H5a2 2 0 00-2 2v6a2 2 0 002 2h2a2 2 0 002-2zm0 0V9a2 2 0 012-2h2a2 2 0 012 2v10m-6 0a2 2 0 002 2h2a2 2 0 002-2m0 0V5a2 2 0 012-2h2a2 2 0 012 2v14a2 2 0 01-2 2h-2a2 2 0 01-2-2z"
-                  />
-                </svg>
-              </button>
-            {/if}
-
             <!-- Regenerate button (last assistant message only) -->
             {#if message.role === "assistant" && isLastAssistantMessage(message.id) && !loading}
               <button
@@ -761,13 +658,8 @@
             <!-- Delete button -->
             <button
               onclick={() => handleDeleteClick(message.id)}
-              disabled={loading}
-              class="p-1.5 transition-colors rounded {loading
-                ? 'text-exo-light-gray/30 cursor-not-allowed'
-                : 'text-exo-light-gray hover:text-red-400 hover:bg-red-500/10 cursor-pointer'}"
-              title={loading
-                ? "Cannot delete while generating"
-                : "Delete message"}
+              class="p-1.5 text-exo-light-gray hover:text-red-400 transition-colors rounded hover:bg-red-500/10 cursor-pointer"
+              title="Delete message"
             >
               <svg
                 class="w-3.5 h-3.5"
@@ -809,8 +701,8 @@
       >
         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}
@@ -825,7 +717,6 @@
       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"
@@ -843,8 +734,3 @@
     </button>
   {/if}
 </div>
-
-<ImageLightbox
-  src={expandedImageSrc}
-  onclose={() => (expandedImageSrc = null)}
-/>

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,
@@ -16,21 +17,9 @@
 
   interface Props {
     class?: string;
-    onNewChat?: () => void;
-    onSelectConversation?: () => void;
-    isMobileDrawer?: boolean;
-    isOpen?: boolean;
-    onClose?: () => void;
   }
 
-  let {
-    class: className = "",
-    onNewChat,
-    onSelectConversation,
-    isMobileDrawer = false,
-    isOpen = false,
-    onClose,
-  }: Props = $props();
+  let { class: className = "" }: Props = $props();
 
   const conversationList = $derived(conversations());
   const activeId = $derived(activeConversationId());
@@ -53,16 +42,11 @@
   );
 
   function handleNewChat() {
-    onNewChat?.();
+    createConversation();
   }
 
   function handleSelectConversation(id: string) {
-    onSelectConversation?.();
     loadConversation(id);
-    // Close mobile drawer when selecting a conversation
-    if (isMobileDrawer && isOpen) {
-      onClose?.();
-    }
   }
 
   function handleStartEdit(id: string, name: string, event: MouseEvent) {
@@ -201,8 +185,11 @@
 
     let instanceType: string | null = null;
     if (instanceTag === "MlxRingInstance") instanceType = "MLX Ring";
-    else if (instanceTag === "MlxJacclInstance") instanceType = "MLX RDMA";
-    else if (instanceTag === "VllmInstance") instanceType = "vLLM";
+    else if (
+      instanceTag === "MlxIbvInstance" ||
+      instanceTag === "MlxJacclInstance"
+    )
+      instanceType = "MLX RDMA";
 
     let sharding: string | null = null;
     const inst = instance as {
@@ -263,7 +250,9 @@
   }
 </script>
 
-{#snippet sidebarContent()}
+<aside
+  class="flex flex-col h-full bg-exo-dark-gray border-r border-exo-yellow/10 {className}"
+>
   <!-- Header -->
   <div class="p-4">
     <button
@@ -318,7 +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>
@@ -387,37 +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>
@@ -600,30 +591,4 @@
       </button>
     </div>
   </div>
-{/snippet}
-
-{#if isMobileDrawer}
-  <!-- Mobile drawer with overlay -->
-  {#if isOpen}
-    <!-- Overlay backdrop -->
-    <button
-      type="button"
-      class="fixed inset-0 bg-black/60 backdrop-blur-sm z-40 md:hidden"
-      onclick={() => onClose?.()}
-      aria-label="Close sidebar"
-    ></button>
-    <!-- Drawer panel -->
-    <aside
-      class="fixed left-0 top-0 bottom-0 w-72 bg-exo-dark-gray border-r border-exo-yellow/10 z-50 flex flex-col md:hidden"
-    >
-      {@render sidebarContent()}
-    </aside>
-  {/if}
-{:else}
-  <!-- Desktop sidebar -->
-  <aside
-    class="flex flex-col h-full bg-exo-dark-gray border-r border-exo-yellow/10 {className}"
-  >
-    {@render sidebarContent()}
-  </aside>
-{/if}
+</aside>

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

@@ -1,567 +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" | "dgx spark" | "linux" 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;
-
-  // NVIDIA logo SVG path
-  const NVIDIA_LOGO_PATH =
-    "M0.81 0.429V0.299c0.013 -0.001 0.026 -0.002 0.038 -0.002 0.355 -0.011 0.588 0.306 0.588 0.306S1.186 0.952 0.916 0.952c-0.036 0 -0.071 -0.006 -0.105 -0.017V0.542c0.138 0.017 0.166 0.078 0.249 0.216l0.185 -0.155s-0.135 -0.177 -0.362 -0.177c-0.024 -0.001 -0.048 0.001 -0.072 0.003m0 -0.429v0.194l0.038 -0.002c0.494 -0.017 0.816 0.405 0.816 0.405s-0.37 0.45 -0.754 0.45c-0.034 0 -0.066 -0.003 -0.099 -0.009v0.12c0.027 0.003 0.055 0.006 0.082 0.006 0.358 0 0.618 -0.183 0.869 -0.399 0.042 0.034 0.212 0.114 0.247 0.15 -0.238 0.2 -0.794 0.361 -1.11 0.361 -0.03 0 -0.059 -0.002 -0.088 -0.005v0.169h1.362V0zm0 0.935v0.102c-0.331 -0.059 -0.423 -0.404 -0.423 -0.404s0.159 -0.176 0.423 -0.205v0.112h-0.001C0.671 0.524 0.562 0.654 0.562 0.654s0.062 0.218 0.248 0.282m-0.588 -0.316s0.196 -0.29 0.589 -0.32V0.194C0.376 0.229 0 0.597 0 0.597s0.213 0.616 0.81 0.672v-0.112c-0.438 -0.054 -0.588 -0.538 -0.588 -0.538";
-
-  const wireColor = "rgba(179,179,179,0.8)";
-  const strokeWidth = 1.5;
-
-  const modelLower = $derived(deviceType.toLowerCase());
-  const isSpark = $derived(
-    modelLower.includes("dgx") || modelLower.includes("gx10"),
-  );
-  const isLinux = $derived(!isSpark && modelLower.startsWith("linux"));
-  const isLinuxLaptop = $derived(isLinux && modelLower.includes("laptop"));
-
-  // ── DGX Spark dimensions ──
-  const dgxW = $derived(size * 1.55);
-  const dgxH = $derived(size * 0.58);
-  const dgxX = $derived(cx - dgxW / 2);
-  const dgxY = $derived(cy - dgxH / 2);
-  const dgxChassisX = $derived(dgxX - dgxW * 0.03);
-  const dgxChassisW = $derived(dgxW * 1.05);
-  const dgxHandleW = $derived(dgxW * 0.27);
-  const dgxHandleGap = $derived(dgxH * 0.05);
-  const dgxHandleH = $derived(dgxH - dgxHandleGap * 2);
-  const dgxHandleY = $derived(dgxY + dgxHandleGap);
-  const dgxInnerHandleW = $derived(dgxW * 0.12);
-  const dgxInnerHandleH = $derived(dgxHandleH - dgxH * 0.06);
-  const dgxLeftHandleX = $derived(dgxX + 4);
-  const dgxRightHandleX = $derived(dgxX + dgxW - dgxHandleW - 4);
-  const dgxClipId = $derived(`di-dgx-${uid}`);
-  const dgxTextureId = $derived(`di-dgx-tex-${uid}`);
-
-  // ── Linux Desktop dimensions (reuses Mac Studio proportions) ──
-  const linuxDesktopClipId = $derived(`di-linux-desktop-${uid}`);
-
-  // ── Linux Laptop dimensions (reuses MacBook proportions) ──
-  const linuxScreenClipId = $derived(`di-linux-screen-${uid}`);
-
-  // ── 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 isSpark}
-  <!-- DGX Spark -->
-  <defs>
-    <clipPath id={dgxClipId}>
-      <rect x={dgxX} y={dgxY} width={dgxW} height={dgxH} rx="3" />
-    </clipPath>
-    <pattern
-      id={dgxTextureId}
-      patternUnits="userSpaceOnUse"
-      width="8"
-      height="8"
-    >
-      <rect width="8" height="8" fill="#6f6248" />
-      <circle cx="2" cy="2" r="1" fill="#5a4f3b" opacity="0.5" />
-      <circle cx="6" cy="6" r="1" fill="#4a4232" opacity="0.45" />
-    </pattern>
-  </defs>
-
-  <!-- Main body -->
-  <rect
-    x={dgxChassisX}
-    y={dgxY}
-    width={dgxChassisW}
-    height={dgxH}
-    rx="3"
-    fill="url(#{dgxTextureId})"
-    stroke={wireColor}
-    stroke-width={strokeWidth}
-  />
-
-  <!-- Side border accents -->
-  <rect
-    x={dgxChassisX}
-    y={dgxY}
-    width={dgxW * 0.02}
-    height={dgxH}
-    fill="#8a7a56"
-  />
-  <rect
-    x={dgxChassisX + dgxChassisW - dgxW * 0.02}
-    y={dgxY}
-    width={dgxW * 0.02}
-    height={dgxH}
-    fill="#8a7a56"
-  />
-
-  <!-- Memory fill -->
-  {#if ramPercent > 0}
-    <rect
-      x={dgxX}
-      y={dgxY + dgxH - (ramPercent / 100) * dgxH}
-      width={dgxW}
-      height={(ramPercent / 100) * dgxH}
-      fill="rgba(255,215,0,0.45)"
-      clip-path="url(#{dgxClipId})"
-    />
-  {/if}
-
-  <!-- Left handle -->
-  <rect
-    x={dgxLeftHandleX}
-    y={dgxHandleY}
-    width={dgxHandleW}
-    height={dgxHandleH}
-    rx="2.4"
-    fill="#b3a170"
-    stroke="#403723"
-    stroke-width="0.7"
-  />
-  <rect
-    x={dgxLeftHandleX + dgxHandleW * 0.06}
-    y={dgxHandleY + dgxH * 0.03}
-    width={dgxInnerHandleW}
-    height={dgxInnerHandleH}
-    rx="1.6"
-    fill="#8a7a56"
-  />
-
-  <!-- Right handle -->
-  <rect
-    x={dgxRightHandleX}
-    y={dgxHandleY}
-    width={dgxHandleW}
-    height={dgxHandleH}
-    rx="2.4"
-    fill="#b3a170"
-    stroke="#403723"
-    stroke-width="0.7"
-  />
-  <rect
-    x={dgxRightHandleX + dgxHandleW - dgxInnerHandleW - dgxHandleW * 0.08}
-    y={dgxHandleY + dgxH * 0.03}
-    width={dgxInnerHandleW}
-    height={dgxInnerHandleH}
-    rx="1.6"
-    fill="#8a7a56"
-  />
-
-  <!-- NVIDIA logo (rotated 90deg on left handle) -->
-  {@const badgeW = dgxW * 0.09}
-  {@const badgeH = dgxHandleH * 0.5}
-  {@const badgeX = dgxLeftHandleX + dgxHandleW - badgeW - dgxHandleW * 0.06}
-  {@const badgeYPos = dgxHandleY + (dgxHandleH - badgeH) / 2}
-  {@const textSz = badgeW * 0.58}
-  {@const logoW = textSz * 1.2}
-  {@const logoH = logoW * (1.438 / 2.174)}
-  {@const ctrX = badgeX + badgeW / 2 - badgeW * 0.03}
-  {@const ctrY = badgeYPos + badgeH / 2}
-  {@const labelGap = badgeW * 0.15}
-  {@const totalW = logoW + labelGap + textSz * 3.6}
-  <g transform="rotate(90 {ctrX} {ctrY})">
-    <svg
-      x={ctrX - totalW / 2}
-      y={ctrY - logoH / 2}
-      width={logoW}
-      height={logoH}
-      viewBox="0 0 2.174 1.438"
-    >
-      <path d={NVIDIA_LOGO_PATH} fill="#76b900" />
-    </svg>
-    <text
-      x={ctrX - totalW / 2 + logoW + labelGap}
-      y={ctrY}
-      text-anchor="start"
-      dominant-baseline="middle"
-      fill="#8a7a56"
-      font-size={textSz}
-      font-family="monospace"
-      font-weight="700">NVIDIA</text
-    >
-  </g>
-{:else if isLinuxLaptop}
-  <!-- Linux Laptop — MacBook shape with Tux logo -->
-  <defs>
-    <clipPath id={linuxScreenClipId}>
-      <rect
-        x={mbScreenX + mbBezel}
-        y={mbY + mbBezel}
-        width={mbScreenW - mbBezel * 2}
-        height={mbScreenH - mbBezel * 2}
-        rx="2"
-      />
-    </clipPath>
-  </defs>
-
-  <rect
-    x={mbScreenX}
-    y={mbY}
-    width={mbScreenW}
-    height={mbScreenH}
-    rx="3"
-    fill="#1a1a1a"
-    stroke={wireColor}
-    stroke-width={strokeWidth}
-  />
-  <rect
-    x={mbScreenX + mbBezel}
-    y={mbY + mbBezel}
-    width={mbScreenW - mbBezel * 2}
-    height={mbScreenH - mbBezel * 2}
-    rx="2"
-    fill="#0a0a12"
-  />
-  {#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(#{linuxScreenClipId})"
-    />
-  {/if}
-
-  <!-- Terminal prompt on screen -->
-  <text
-    x={cx}
-    y={mbY + mbScreenH / 2}
-    text-anchor="middle"
-    dominant-baseline="middle"
-    fill="#FFFFFF"
-    opacity="0.9"
-    font-size={mbScreenH * 0.25}
-    font-family="SF Mono, Monaco, monospace"
-    font-weight="700">{">_"}</text
-  >
-
-  <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"
-  />
-  <rect
-    x={mbKbX}
-    y={mbKbY}
-    width={mbKbW}
-    height={mbKbH}
-    fill="rgba(0,0,0,0.2)"
-    rx="2"
-  />
-  <rect
-    x={mbTpX}
-    y={mbTpY}
-    width={mbTpW}
-    height={mbTpH}
-    fill="rgba(255,255,255,0.08)"
-    rx="2"
-  />
-{:else if isLinux}
-  <!-- Linux Desktop — Mac Studio shape with Tux logo -->
-  <defs>
-    <clipPath id={linuxDesktopClipId}>
-      <rect
-        x={studioX}
-        y={studioY + studioTopH}
-        width={studioW}
-        height={studioH - studioTopH}
-        rx={studioCorner - 1}
-      />
-    </clipPath>
-  </defs>
-
-  <rect
-    x={studioX}
-    y={studioY}
-    width={studioW}
-    height={studioH}
-    rx={studioCorner}
-    fill="#1a1a1a"
-    stroke={wireColor}
-    stroke-width={strokeWidth}
-  />
-  {#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(#{linuxDesktopClipId})"
-    />
-  {/if}
-
-  <!-- Terminal prompt on front face -->
-  <text
-    x={cx}
-    y={studioY + studioTopH + (studioH - studioTopH) / 2}
-    text-anchor="middle"
-    dominant-baseline="middle"
-    fill="rgba(255,255,255,0.5)"
-    font-size={(studioH - studioTopH) * 0.4}
-    font-family="SF Mono, Monaco, monospace"
-    font-weight="700">{">_"}</text
-  >
-{:else 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/FamilyLogos.svelte

@@ -1,109 +0,0 @@
-<script lang="ts">
-  type FamilyLogoProps = {
-    family: string;
-    class?: string;
-  };
-
-  let { family, class: className = "" }: FamilyLogoProps = $props();
-</script>
-
-{#if family === "favorites"}
-  <svg class="w-6 h-6 {className}" viewBox="0 0 24 24" fill="currentColor">
-    <path
-      d="M12 2l3.09 6.26L22 9.27l-5 4.87 1.18 6.88L12 17.77l-6.18 3.25L7 14.14 2 9.27l6.91-1.01L12 2z"
-    />
-  </svg>
-{:else if family === "recents"}
-  <svg class="w-6 h-6 {className}" viewBox="0 0 24 24" fill="currentColor">
-    <path
-      d="M13 3a9 9 0 0 0-9 9H1l3.89 3.89.07.14L9 12H6c0-3.87 3.13-7 7-7s7 3.13 7 7-3.13 7-7 7c-1.93 0-3.68-.79-4.94-2.06l-1.42 1.42A8.954 8.954 0 0 0 13 21a9 9 0 0 0 0-18zm-1 5v5l4.28 2.54.72-1.21-3.5-2.08V8H12z"
-    />
-  </svg>
-{:else if family === "llama" || family === "meta"}
-  <svg class="w-6 h-6 {className}" viewBox="0 0 24 24" fill="currentColor">
-    <path
-      d="M6.915 4.03c-1.968 0-3.683 1.28-4.871 3.113C.704 9.208 0 11.883 0 14.449c0 .706.07 1.369.21 1.973a6.624 6.624 0 0 0 .265.86 5.297 5.297 0 0 0 .371.761c.696 1.159 1.818 1.927 3.593 1.927 1.497 0 2.633-.671 3.965-2.444.76-1.012 1.144-1.626 2.663-4.32l.756-1.339.186-.325c.061.1.121.196.183.3l2.152 3.595c.724 1.21 1.665 2.556 2.47 3.314 1.046.987 1.992 1.22 3.06 1.22 1.075 0 1.876-.355 2.455-.843a3.743 3.743 0 0 0 .81-.973c.542-.939.861-2.127.861-3.745 0-2.72-.681-5.357-2.084-7.45-1.282-1.912-2.957-2.93-4.716-2.93-1.047 0-2.088.467-3.053 1.308-.652.57-1.257 1.29-1.82 2.05-.69-.875-1.335-1.547-1.958-2.056-1.182-.966-2.315-1.303-3.454-1.303zm10.16 2.053c1.147 0 2.188.758 2.992 1.999 1.132 1.748 1.647 4.195 1.647 6.4 0 1.548-.368 2.9-1.839 2.9-.58 0-1.027-.23-1.664-1.004-.496-.601-1.343-1.878-2.832-4.358l-.617-1.028a44.908 44.908 0 0 0-1.255-1.98c.07-.109.141-.224.211-.327 1.12-1.667 2.118-2.602 3.358-2.602zm-10.201.553c1.265 0 2.058.791 2.675 1.446.307.327.737.871 1.234 1.579l-1.02 1.566c-.757 1.163-1.882 3.017-2.837 4.338-1.191 1.649-1.81 1.817-2.486 1.817-.524 0-1.038-.237-1.383-.794-.263-.426-.464-1.13-.464-2.046 0-2.221.63-4.535 1.66-6.088.454-.687.964-1.226 1.533-1.533a2.264 2.264 0 0 1 1.088-.285z"
-    />
-  </svg>
-{:else if family === "qwen"}
-  <svg class="w-6 h-6 {className}" viewBox="0 0 24 24" fill="currentColor">
-    <path
-      d="M12.604 1.34c.393.69.784 1.382 1.174 2.075a.18.18 0 00.157.091h5.552c.174 0 .322.11.446.327l1.454 2.57c.19.337.24.478.024.837-.26.43-.513.864-.76 1.3l-.367.658c-.106.196-.223.28-.04.512l2.652 4.637c.172.301.111.494-.043.77-.437.785-.882 1.564-1.335 2.34-.159.272-.352.375-.68.37-.777-.016-1.552-.01-2.327.016a.099.099 0 00-.081.05 575.097 575.097 0 01-2.705 4.74c-.169.293-.38.363-.725.364-.997.003-2.002.004-3.017.002a.537.537 0 01-.465-.271l-1.335-2.323a.09.09 0 00-.083-.049H4.982c-.285.03-.553-.001-.805-.092l-1.603-2.77a.543.543 0 01-.002-.54l1.207-2.12a.198.198 0 000-.197 550.951 550.951 0 01-1.875-3.272l-.79-1.395c-.16-.31-.173-.496.095-.965.465-.813.927-1.625 1.387-2.436.132-.234.304-.334.584-.335a338.3 338.3 0 012.589-.001.124.124 0 00.107-.063l2.806-4.895a.488.488 0 01.422-.246c.524-.001 1.053 0 1.583-.006L11.704 1c.341-.003.724.032.9.34zm-3.432.403a.06.06 0 00-.052.03L6.254 6.788a.157.157 0 01-.135.078H3.253c-.056 0-.07.025-.041.074l5.81 10.156c.025.042.013.062-.034.063l-2.795.015a.218.218 0 00-.2.116l-1.32 2.31c-.044.078-.021.118.068.118l5.716.008c.046 0 .08.02.104.061l1.403 2.454c.046.081.092.082.139 0l5.006-8.76.783-1.382a.055.055 0 01.096 0l1.424 2.53a.122.122 0 00.107.062l2.763-.02a.04.04 0 00.035-.02.041.041 0 000-.04l-2.9-5.086a.108.108 0 010-.113l.293-.507 1.12-1.977c.024-.041.012-.062-.035-.062H9.2c-.059 0-.073-.026-.043-.077l1.434-2.505a.107.107 0 000-.114L9.225 1.774a.06.06 0 00-.053-.031zm6.29 8.02c.046 0 .058.02.034.06l-.832 1.465-2.613 4.585a.056.056 0 01-.05.029.058.058 0 01-.05-.029L8.498 9.841c-.02-.034-.01-.052.028-.054l.216-.012 6.722-.012z"
-    />
-  </svg>
-{:else if family === "deepseek"}
-  <svg class="w-6 h-6 {className}" viewBox="0 0 24 24" fill="currentColor">
-    <path
-      d="M23.748 4.482c-.254-.124-.364.113-.512.234-.051.039-.094.09-.137.136-.372.397-.806.657-1.373.626-.829-.046-1.537.214-2.163.848-.133-.782-.575-1.248-1.247-1.548-.352-.156-.708-.311-.955-.65-.172-.241-.219-.51-.305-.774-.055-.16-.11-.323-.293-.35-.2-.031-.278.136-.356.276-.313.572-.434 1.202-.422 1.84.027 1.436.633 2.58 1.838 3.393.137.093.172.187.129.323-.082.28-.18.552-.266.833-.055.179-.137.217-.329.14a5.526 5.526 0 01-1.736-1.18c-.857-.828-1.631-1.742-2.597-2.458a11.365 11.365 0 00-.689-.471c-.985-.957.13-1.743.388-1.836.27-.098.093-.432-.779-.428-.872.004-1.67.295-2.687.684a3.055 3.055 0 01-.465.137 9.597 9.597 0 00-2.883-.102c-1.885.21-3.39 1.102-4.497 2.623C.082 8.606-.231 10.684.152 12.85c.403 2.284 1.569 4.175 3.36 5.653 1.858 1.533 3.997 2.284 6.438 2.14 1.482-.085 3.133-.284 4.994-1.86.47.234.962.327 1.78.397.63.059 1.236-.03 1.705-.128.735-.156.684-.837.419-.961-2.155-1.004-1.682-.595-2.113-.926 1.096-1.296 2.746-2.642 3.392-7.003.05-.347.007-.565 0-.845-.004-.17.035-.237.23-.256a4.173 4.173 0 001.545-.475c1.396-.763 1.96-2.015 2.093-3.517.02-.23-.004-.467-.247-.588zM11.581 18c-2.089-1.642-3.102-2.183-3.52-2.16-.392.024-.321.471-.235.763.09.288.207.486.371.739.114.167.192.416-.113.603-.673.416-1.842-.14-1.897-.167-1.361-.802-2.5-1.86-3.301-3.307-.774-1.393-1.224-2.887-1.298-4.482-.02-.386.093-.522.477-.592a4.696 4.696 0 011.529-.039c2.132.312 3.946 1.265 5.468 2.774.868.86 1.525 1.887 2.202 2.891.72 1.066 1.494 2.082 2.48 2.914.348.292.625.514.891.677-.802.09-2.14.11-3.054-.614zm1-6.44a.306.306 0 01.415-.287.302.302 0 01.2.288.306.306 0 01-.31.307.303.303 0 01-.304-.308zm3.11 1.596c-.2.081-.399.151-.59.16a1.245 1.245 0 01-.798-.254c-.274-.23-.47-.358-.552-.758a1.73 1.73 0 01.016-.588c.07-.327-.008-.537-.239-.727-.187-.156-.426-.199-.688-.199a.559.559 0 01-.254-.078c-.11-.054-.2-.19-.114-.358.028-.054.16-.186.192-.21.356-.202.767-.136 1.146.016.352.144.618.408 1.001.782.391.451.462.576.685.914.176.265.336.537.445.848.067.195-.019.354-.25.452z"
-    />
-  </svg>
-{:else if family === "openai" || family === "gpt-oss"}
-  <svg class="w-6 h-6 {className}" viewBox="0 0 24 24" fill="currentColor">
-    <path
-      d="M22.2819 9.8211a5.9847 5.9847 0 0 0-.5157-4.9108 6.0462 6.0462 0 0 0-6.5098-2.9A6.0651 6.0651 0 0 0 4.9807 4.1818a5.9847 5.9847 0 0 0-3.9977 2.9 6.0462 6.0462 0 0 0 .7427 7.0966 5.98 5.98 0 0 0 .511 4.9107 6.051 6.051 0 0 0 6.5146 2.9001A5.9847 5.9847 0 0 0 13.2599 24a6.0557 6.0557 0 0 0 5.7718-4.2058 5.9894 5.9894 0 0 0 3.9977-2.9001 6.0557 6.0557 0 0 0-.7475-7.0729zm-9.022 12.6081a4.4755 4.4755 0 0 1-2.8764-1.0408l.1419-.0804 4.7783-2.7582a.7948.7948 0 0 0 .3927-.6813v-6.7369l2.02 1.1686a.071.071 0 0 1 .038.052v5.5826a4.504 4.504 0 0 1-4.4945 4.4944zm-9.6607-4.1254a4.4708 4.4708 0 0 1-.5346-3.0137l.142.0852 4.783 2.7582a.7712.7712 0 0 0 .7806 0l5.8428-3.3685v2.3324a.0804.0804 0 0 1-.0332.0615L9.74 19.9502a4.4992 4.4992 0 0 1-6.1408-1.6464zM2.3408 7.8956a4.485 4.485 0 0 1 2.3655-1.9728V11.6a.7664.7664 0 0 0 .3879.6765l5.8144 3.3543-2.0201 1.1685a.0757.0757 0 0 1-.071 0l-4.8303-2.7865A4.504 4.504 0 0 1 2.3408 7.872zm16.5963 3.8558L13.1038 8.364 15.1192 7.2a.0757.0757 0 0 1 .071 0l4.8303 2.7913a4.4944 4.4944 0 0 1-.6765 8.1042v-5.6772a.79.79 0 0 0-.407-.667zm2.0107-3.0231l-.142-.0852-4.7735-2.7818a.7759.7759 0 0 0-.7854 0L9.409 9.2297V6.8974a.0662.0662 0 0 1 .0284-.0615l4.8303-2.7866a4.4992 4.4992 0 0 1 6.6802 4.66zM8.3065 12.863l-2.02-1.1638a.0804.0804 0 0 1-.038-.0567V6.0742a4.4992 4.4992 0 0 1 7.3757-3.4537l-.142.0805L8.704 5.459a.7948.7948 0 0 0-.3927.6813zm1.0976-2.3654l2.602-1.4998 2.6069 1.4998v2.9994l-2.5974 1.4997-2.6067-1.4997Z"
-    />
-  </svg>
-{:else if family === "glm"}
-  <svg class="w-6 h-6 {className}" viewBox="0 0 24 24" fill="currentColor">
-    <path
-      d="M11.991 23.503a.24.24 0 00-.244.248.24.24 0 00.244.249.24.24 0 00.245-.249.24.24 0 00-.22-.247l-.025-.001zM9.671 5.365a1.697 1.697 0 011.099 2.132l-.071.172-.016.04-.018.054c-.07.16-.104.32-.104.498-.035.71.47 1.279 1.186 1.314h.366c1.309.053 2.338 1.173 2.286 2.523-.052 1.332-1.152 2.38-2.478 2.327h-.174c-.715.018-1.274.64-1.239 1.368 0 .124.018.23.053.337.209.373.54.658.96.8.75.23 1.517-.125 1.9-.782l.018-.035c.402-.64 1.17-.96 1.92-.711.854.284 1.378 1.226 1.099 2.167a1.661 1.661 0 01-2.077 1.102 1.711 1.711 0 01-.907-.711l-.017-.035c-.2-.323-.463-.58-.851-.711l-.056-.018a1.646 1.646 0 00-1.954.746 1.66 1.66 0 01-1.065.764 1.677 1.677 0 01-1.989-1.279c-.209-.906.332-1.83 1.257-2.043a1.51 1.51 0 01.296-.035h.018c.68-.071 1.151-.622 1.116-1.333a1.307 1.307 0 00-.227-.693 2.515 2.515 0 01-.366-1.403 2.39 2.39 0 01.366-1.208c.14-.195.21-.444.227-.693.018-.71-.506-1.261-1.186-1.332l-.07-.018a1.43 1.43 0 01-.299-.07l-.05-.019a1.7 1.7 0 01-1.047-2.114 1.68 1.68 0 012.094-1.101zm-5.575 10.11c.26-.264.639-.367.994-.27.355.096.633.379.728.74.095.362-.007.748-.267 1.013-.402.41-1.053.41-1.455 0a1.062 1.062 0 010-1.482zm14.845-.294c.359-.09.738.024.992.297.254.274.344.665.237 1.025-.107.36-.396.634-.756.718-.551.128-1.1-.22-1.23-.781a1.05 1.05 0 01.757-1.26zm-.064-4.39c.314.32.49.753.49 1.206 0 .452-.176.886-.49 1.206-.315.32-.74.5-1.185.5-.444 0-.87-.18-1.184-.5a1.727 1.727 0 010-2.412 1.654 1.654 0 012.369 0zm-11.243.163c.364.484.447 1.128.218 1.691a1.665 1.665 0 01-2.188.923c-.855-.36-1.26-1.358-.907-2.228a1.68 1.68 0 011.33-1.038c.593-.08 1.183.169 1.547.652zm11.545-4.221c.368 0 .708.2.892.524.184.324.184.724 0 1.048a1.026 1.026 0 01-.892.524c-.568 0-1.03-.47-1.03-1.048 0-.579.462-1.048 1.03-1.048zm-14.358 0c.368 0 .707.2.891.524.184.324.184.724 0 1.048a1.026 1.026 0 01-.891.524c-.569 0-1.03-.47-1.03-1.048 0-.579.461-1.048 1.03-1.048zm10.031-1.475c.925 0 1.675.764 1.675 1.706s-.75 1.705-1.675 1.705-1.674-.763-1.674-1.705c0-.942.75-1.706 1.674-1.706zm-2.626-.684c.362-.082.653-.356.761-.718a1.062 1.062 0 00-.238-1.028 1.017 1.017 0 00-.996-.294c-.547.14-.881.7-.752 1.257.13.558.675.907 1.225.783zm0 16.876c.359-.087.644-.36.75-.72a1.062 1.062 0 00-.237-1.019 1.018 1.018 0 00-.985-.301 1.037 1.037 0 00-.762.717c-.108.361-.017.754.239 1.028.245.263.606.377.953.305l.043-.01zM17.19 3.5a.631.631 0 00.628-.64c0-.355-.279-.64-.628-.64a.631.631 0 00-.628.64c0 .355.28.64.628.64zm-10.38 0a.631.631 0 00.628-.64c0-.355-.28-.64-.628-.64a.631.631 0 00-.628.64c0 .355.279.64.628.64zm-5.182 7.852a.631.631 0 00-.628.64c0 .354.28.639.628.639a.63.63 0 00.627-.606l.001-.034a.62.62 0 00-.628-.64zm5.182 9.13a.631.631 0 00-.628.64c0 .355.279.64.628.64a.631.631 0 00.628-.64c0-.355-.28-.64-.628-.64zm10.38.018a.631.631 0 00-.628.64c0 .355.28.64.628.64a.631.631 0 00.628-.64c0-.355-.279-.64-.628-.64zm5.182-9.148a.631.631 0 00-.628.64c0 .354.279.639.628.639a.631.631 0 00.628-.64c0-.355-.28-.64-.628-.64zm-.384-4.992a.24.24 0 00.244-.249.24.24 0 00-.244-.249.24.24 0 00-.244.249c0 .142.122.249.244.249zM11.991.497a.24.24 0 00.245-.248A.24.24 0 0011.99 0a.24.24 0 00-.244.249c0 .133.108.236.223.247l.021.001zM2.011 6.36a.24.24 0 00.245-.249.24.24 0 00-.244-.249.24.24 0 00-.244.249.24.24 0 00.244.249zm0 11.263a.24.24 0 00-.243.248.24.24 0 00.244.249.24.24 0 00.244-.249.252.252 0 00-.244-.248zm19.995-.018a.24.24 0 00-.245.248.24.24 0 00.245.25.24.24 0 00.244-.25.252.252 0 00-.244-.248z"
-    />
-  </svg>
-{:else if family === "minimax"}
-  <svg class="w-6 h-6 {className}" viewBox="0 0 24 24" fill="currentColor">
-    <path
-      d="M16.278 2c1.156 0 2.093.927 2.093 2.07v12.501a.74.74 0 00.744.709.74.74 0 00.743-.709V9.099a2.06 2.06 0 012.071-2.049A2.06 2.06 0 0124 9.1v6.561a.649.649 0 01-.652.645.649.649 0 01-.653-.645V9.1a.762.762 0 00-.766-.758.762.762 0 00-.766.758v7.472a2.037 2.037 0 01-2.048 2.026 2.037 2.037 0 01-2.048-2.026v-12.5a.785.785 0 00-.788-.753.785.785 0 00-.789.752l-.001 15.904A2.037 2.037 0 0113.441 22a2.037 2.037 0 01-2.048-2.026V18.04c0-.356.292-.645.652-.645.36 0 .652.289.652.645v1.934c0 .263.142.506.372.638.23.131.514.131.744 0a.734.734 0 00.372-.638V4.07c0-1.143.937-2.07 2.093-2.07zm-5.674 0c1.156 0 2.093.927 2.093 2.07v11.523a.648.648 0 01-.652.645.648.648 0 01-.652-.645V4.07a.785.785 0 00-.789-.78.785.785 0 00-.789.78v14.013a2.06 2.06 0 01-2.07 2.048 2.06 2.06 0 01-2.071-2.048V9.1a.762.762 0 00-.766-.758.762.762 0 00-.766.758v3.8a2.06 2.06 0 01-2.071 2.049A2.06 2.06 0 010 12.9v-1.378c0-.357.292-.646.652-.646.36 0 .653.29.653.646V12.9c0 .418.343.757.766.757s.766-.339.766-.757V9.099a2.06 2.06 0 012.07-2.048 2.06 2.06 0 012.071 2.048v8.984c0 .419.343.758.767.758.423 0 .766-.339.766-.758V4.07c0-1.143.937-2.07 2.093-2.07z"
-    />
-  </svg>
-{:else if family === "kimi"}
-  <svg class="w-6 h-6 {className}" viewBox="0 0 24 24" fill="currentColor">
-    <path
-      d="M19.738 5.776c.163-.209.306-.4.457-.585.07-.087.064-.153-.004-.244-.655-.861-.717-1.817-.34-2.787.283-.73.909-1.072 1.674-1.145.477-.045.945.004 1.379.236.57.305.902.77 1.01 1.412.086.512.07 1.012-.075 1.508-.257.878-.888 1.333-1.753 1.448-.718.096-1.446.108-2.17.157-.056.004-.113 0-.178 0z"
-    />
-    <path
-      d="M17.962 1.844h-4.326l-3.425 7.81H5.369V1.878H1.5V22h3.87v-8.477h6.824a3.025 3.025 0 002.743-1.75V22h3.87v-8.477a3.87 3.87 0 00-3.588-3.86v-.01h-2.125a3.94 3.94 0 002.323-2.12l2.545-5.689z"
-    />
-  </svg>
-{:else if family === "flux"}
-  <svg class="w-6 h-6 {className}" viewBox="0 0 24 24" fill="currentColor">
-    <path
-      d="M12 2L2 19h7.5l2.5-4.5L14.5 19H22L12 2zm0 4.5L16.5 17h-3l-1.5-2.7L10.5 17h-3L12 6.5z"
-    />
-  </svg>
-{:else if family === "qwen-image"}
-  <svg class="w-6 h-6 {className}" viewBox="0 0 24 24" fill="currentColor">
-    <path
-      d="M12.604 1.34c.393.69.784 1.382 1.174 2.075a.18.18 0 00.157.091h5.552c.174 0 .322.11.446.327l1.454 2.57c.19.337.24.478.024.837-.26.43-.513.864-.76 1.3l-.367.658c-.106.196-.223.28-.04.512l2.652 4.637c.172.301.111.494-.043.77-.437.785-.882 1.564-1.335 2.34-.159.272-.352.375-.68.37-.777-.016-1.552-.01-2.327.016a.099.099 0 00-.081.05 575.097 575.097 0 01-2.705 4.74c-.169.293-.38.363-.725.364-.997.003-2.002.004-3.017.002a.537.537 0 01-.465-.271l-1.335-2.323a.09.09 0 00-.083-.049H4.982c-.285.03-.553-.001-.805-.092l-1.603-2.77a.543.543 0 01-.002-.54l1.207-2.12a.198.198 0 000-.197 550.951 550.951 0 01-1.875-3.272l-.79-1.395c-.16-.31-.173-.496.095-.965.465-.813.927-1.625 1.387-2.436.132-.234.304-.334.584-.335a338.3 338.3 0 012.589-.001.124.124 0 00.107-.063l2.806-4.895a.488.488 0 01.422-.246c.524-.001 1.053 0 1.583-.006L11.704 1c.341-.003.724.032.9.34zm-3.432.403a.06.06 0 00-.052.03L6.254 6.788a.157.157 0 01-.135.078H3.253c-.056 0-.07.025-.041.074l5.81 10.156c.025.042.013.062-.034.063l-2.795.015a.218.218 0 00-.2.116l-1.32 2.31c-.044.078-.021.118.068.118l5.716.008c.046 0 .08.02.104.061l1.403 2.454c.046.081.092.082.139 0l5.006-8.76.783-1.382a.055.055 0 01.096 0l1.424 2.53a.122.122 0 00.107.062l2.763-.02a.04.04 0 00.035-.02.041.041 0 000-.04l-2.9-5.086a.108.108 0 010-.113l.293-.507 1.12-1.977c.024-.041.012-.062-.035-.062H9.2c-.059 0-.073-.026-.043-.077l1.434-2.505a.107.107 0 000-.114L9.225 1.774a.06.06 0 00-.053-.031zm6.29 8.02c.046 0 .058.02.034.06l-.832 1.465-2.613 4.585a.056.056 0 01-.05.029.058.058 0 01-.05-.029L8.498 9.841c-.02-.034-.01-.052.028-.054l.216-.012 6.722-.012z"
-    />
-  </svg>
-{:else if family === "huggingface"}
-  <svg class="w-6 h-6 {className}" viewBox="0 0 24 24" fill="currentColor">
-    <path
-      d="M12.025 1.13c-5.77 0-10.449 4.647-10.449 10.378 0 1.112.178 2.181.503 3.185.064-.222.203-.444.416-.577a.96.96 0 0 1 .524-.15c.293 0 .584.124.84.284.278.173.48.408.71.694.226.282.458.611.684.951v-.014c.017-.324.106-.622.264-.874s.403-.487.762-.543c.3-.047.596.06.787.203s.31.313.4.467c.15.257.212.468.233.542.01.026.653 1.552 1.657 2.54.616.605 1.01 1.223 1.082 1.912.055.537-.096 1.059-.38 1.572.637.121 1.294.187 1.967.187.657 0 1.298-.063 1.921-.178-.287-.517-.44-1.041-.384-1.581.07-.69.465-1.307 1.081-1.913 1.004-.987 1.647-2.513 1.657-2.539.021-.074.083-.285.233-.542.09-.154.208-.323.4-.467a1.08 1.08 0 0 1 .787-.203c.359.056.604.29.762.543s.247.55.265.874v.015c.225-.34.457-.67.683-.952.23-.286.432-.52.71-.694.257-.16.547-.284.84-.285a.97.97 0 0 1 .524.151c.228.143.373.388.43.625l.006.04a10.3 10.3 0 0 0 .534-3.273c0-5.731-4.678-10.378-10.449-10.378M8.327 6.583a1.5 1.5 0 0 1 .713.174 1.487 1.487 0 0 1 .617 2.013c-.183.343-.762-.214-1.102-.094-.38.134-.532.914-.917.71a1.487 1.487 0 0 1 .69-2.803m7.486 0a1.487 1.487 0 0 1 .689 2.803c-.385.204-.536-.576-.916-.71-.34-.12-.92.437-1.103.094a1.487 1.487 0 0 1 .617-2.013 1.5 1.5 0 0 1 .713-.174m-10.68 1.55a.96.96 0 1 1 0 1.921.96.96 0 0 1 0-1.92m13.838 0a.96.96 0 1 1 0 1.92.96.96 0 0 1 0-1.92M8.489 11.458c.588.01 1.965 1.157 3.572 1.164 1.607-.007 2.984-1.155 3.572-1.164.196-.003.305.12.305.454 0 .886-.424 2.328-1.563 3.202-.22-.756-1.396-1.366-1.63-1.32q-.011.001-.02.006l-.044.026-.01.008-.03.024q-.018.017-.035.036l-.032.04a1 1 0 0 0-.058.09l-.014.025q-.049.088-.11.19a1 1 0 0 1-.083.116 1.2 1.2 0 0 1-.173.18q-.035.029-.075.058a1.3 1.3 0 0 1-.251-.243 1 1 0 0 1-.076-.107c-.124-.193-.177-.363-.337-.444-.034-.016-.104-.008-.2.022q-.094.03-.216.087-.06.028-.125.063l-.13.074q-.067.04-.136.086a3 3 0 0 0-.135.096 3 3 0 0 0-.26.219 2 2 0 0 0-.12.121 2 2 0 0 0-.106.128l-.002.002a2 2 0 0 0-.09.132l-.001.001a1.2 1.2 0 0 0-.105.212q-.013.036-.024.073c-1.139-.875-1.563-2.317-1.563-3.203 0-.334.109-.457.305-.454m.836 10.354c.824-1.19.766-2.082-.365-3.194-1.13-1.112-1.789-2.738-1.789-2.738s-.246-.945-.806-.858-.97 1.499.202 2.362c1.173.864-.233 1.45-.685.64-.45-.812-1.683-2.896-2.322-3.295s-1.089-.175-.938.647 2.822 2.813 2.562 3.244-1.176-.506-1.176-.506-2.866-2.567-3.49-1.898.473 1.23 2.037 2.16c1.564.932 1.686 1.178 1.464 1.53s-3.675-2.511-4-1.297c-.323 1.214 3.524 1.567 3.287 2.405-.238.839-2.71-1.587-3.216-.642-.506.946 3.49 2.056 3.522 2.064 1.29.33 4.568 1.028 5.713-.624m5.349 0c-.824-1.19-.766-2.082.365-3.194 1.13-1.112 1.789-2.738 1.789-2.738s.246-.945.806-.858.97 1.499-.202 2.362c-1.173.864.233 1.45.685.64.451-.812 1.683-2.896 2.322-3.295s1.089-.175.938.647-2.822 2.813-2.562 3.244 1.176-.506 1.176-.506 2.866-2.567 3.49-1.898-.473 1.23-2.037 2.16c-1.564.932-1.686 1.178-1.464 1.53s3.675-2.511 4-1.297c.323 1.214-3.524 1.567-3.287 2.405.238.839 2.71-1.587 3.216-.642.506.946-3.49 2.056-3.522 2.064-1.29.33-4.568 1.028-5.713-.624"
-    />
-  </svg>
-{:else if family === "step"}
-  <svg class="w-6 h-6 {className}" viewBox="0 0 24 24" fill="currentColor">
-    <path
-      d="M22.012 0h1.032v.927H24v.968h-.956V3.78h-1.032V1.896h-1.878v-.97h1.878V0zM2.6 12.371V1.87h.969v10.502h-.97zm10.423.66h10.95v.918h-6.208v9.579h-4.742V13.03zM5.629 3.333v12.356H0v4.51h10.386V8L20.859 8l-.003-4.668-15.227.001z"
-    />
-  </svg>
-{:else if family === "nemotron"}
-  <svg class="w-6 h-6 {className}" viewBox="0 0 24 24" fill="currentColor">
-    <path
-      d="M8.948 8.798v-1.43a6.7 6.7 0 0 1 .424-.018c3.922-.124 6.493 3.374 6.493 3.374s-2.774 3.851-5.75 3.851c-.398 0-.787-.062-1.158-.185v-4.346c1.528.185 1.837.857 2.747 2.385l2.04-1.714s-1.492-1.952-4-1.952a6.016 6.016 0 0 0-.796.035m0-4.735v2.138l.424-.027c5.45-.185 9.01 4.47 9.01 4.47s-4.08 4.964-8.33 4.964c-.37 0-.733-.035-1.095-.097v1.325c.3.035.61.062.91.062 3.957 0 6.82-2.023 9.593-4.408.459.371 2.34 1.263 2.73 1.652-2.633 2.208-8.772 3.984-12.253 3.984-.335 0-.653-.018-.971-.053v1.864H24V4.063zm0 10.326v1.131c-3.657-.654-4.673-4.46-4.673-4.46s1.758-1.944 4.673-2.262v1.237H8.94c-1.528-.186-2.73 1.245-2.73 1.245s.68 2.412 2.739 3.11M2.456 10.9s2.164-3.197 6.5-3.533V6.201C4.153 6.59 0 10.653 0 10.653s2.35 6.802 8.948 7.42v-1.237c-4.84-.6-6.492-5.936-6.492-5.936z"
-    />
-  </svg>
-{:else if family === "gemma"}
-  <svg class="w-6 h-6 {className}" viewBox="0 0 24 24" fill="currentColor">
-    <path
-      d="M12.48 10.92v3.28h7.84c-.24 1.84-.853 3.187-1.787 4.133-1.147 1.147-2.933 2.4-6.053 2.4-4.827 0-8.6-3.893-8.6-8.72s3.773-8.72 8.6-8.72c2.6 0 4.507 1.027 5.907 2.347l2.307-2.307C18.747 1.44 16.133 0 12.48 0 5.867 0 .307 5.387.307 12s5.56 12 12.173 12c3.573 0 6.267-1.173 8.373-3.36 2.16-2.16 2.84-5.213 2.84-7.667 0-.76-.053-1.467-.173-2.053H12.48z"
-    />
-  </svg>
-{:else}
-  <svg class="w-6 h-6 {className}" 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 2zm-2 15l-5-5 1.41-1.41L10 14.17l7.59-7.59L19 8l-9 9z"
-    />
-  </svg>
-{/if}

dashboard/src/lib/components/FamilySidebar.svelte

@@ -1,167 +0,0 @@
-<script lang="ts">
-  import FamilyLogos from "./FamilyLogos.svelte";
-
-  type FamilySidebarProps = {
-    families: string[];
-    selectedFamily: string | null;
-    hasFavorites: boolean;
-    hasRecents: boolean;
-    onSelect: (family: string | null) => void;
-  };
-
-  let {
-    families,
-    selectedFamily,
-    hasFavorites,
-    hasRecents,
-    onSelect,
-  }: FamilySidebarProps = $props();
-
-  // Family display names
-  const familyNames: Record<string, string> = {
-    favorites: "Favorites",
-    recents: "Recent",
-    huggingface: "Hub",
-    llama: "Meta",
-    qwen: "Qwen",
-    deepseek: "DeepSeek",
-    "gpt-oss": "OpenAI",
-    glm: "GLM",
-    minimax: "MiniMax",
-    kimi: "Kimi",
-    flux: "FLUX",
-    "qwen-image": "Qwen Img",
-    nemotron: "NVIDIA",
-    gemma: "Google",
-  };
-
-  function getFamilyName(family: string): string {
-    return (
-      familyNames[family] || family.charAt(0).toUpperCase() + family.slice(1)
-    );
-  }
-</script>
-
-<div
-  class="flex flex-col gap-1 py-2 px-1 border-r border-exo-yellow/10 bg-exo-medium-gray/30 min-w-[80px] sm:min-w-[72px] overflow-y-auto scrollbar-hide"
->
-  <!-- All models (no filter) -->
-  <button
-    type="button"
-    onclick={() => onSelect(null)}
-    class="group flex items-center justify-center px-3 py-2.5 rounded transition-all duration-200 cursor-pointer min-h-[44px] sm:min-h-0 {selectedFamily ===
-    null
-      ? 'bg-exo-yellow/20 border-l-2 border-exo-yellow'
-      : 'hover:bg-white/5 border-l-2 border-transparent'}"
-    title="All models"
-  >
-    <span
-      class="text-[12px] font-mono font-medium {selectedFamily === null
-        ? 'text-exo-yellow'
-        : 'text-white/40 group-hover:text-white/60'}">All</span
-    >
-  </button>
-
-  <!-- Favorites (only show if has favorites) -->
-  {#if hasFavorites}
-    <button
-      type="button"
-      onclick={() => onSelect("favorites")}
-      class="group flex flex-col items-center justify-center p-2 rounded transition-all duration-200 cursor-pointer {selectedFamily ===
-      'favorites'
-        ? 'bg-exo-yellow/20 border-l-2 border-exo-yellow'
-        : 'hover:bg-white/5 border-l-2 border-transparent'}"
-      title="Show favorited models"
-    >
-      <FamilyLogos
-        family="favorites"
-        class={selectedFamily === "favorites"
-          ? "text-amber-400"
-          : "text-white/50 group-hover:text-amber-400/70"}
-      />
-      <span
-        class="text-[11px] font-mono mt-0.5 {selectedFamily === 'favorites'
-          ? 'text-amber-400'
-          : 'text-white/40 group-hover:text-white/60'}">Faves</span
-      >
-    </button>
-  {/if}
-
-  <!-- Recent (only show if has recent models) -->
-  {#if hasRecents}
-    <button
-      type="button"
-      onclick={() => onSelect("recents")}
-      class="group flex flex-col items-center justify-center p-2 rounded transition-all duration-200 cursor-pointer {selectedFamily ===
-      'recents'
-        ? 'bg-exo-yellow/20 border-l-2 border-exo-yellow'
-        : 'hover:bg-white/5 border-l-2 border-transparent'}"
-      title="Recently launched models"
-    >
-      <FamilyLogos
-        family="recents"
-        class={selectedFamily === "recents"
-          ? "text-exo-yellow"
-          : "text-white/50 group-hover:text-white/70"}
-      />
-      <span
-        class="text-[11px] font-mono mt-0.5 {selectedFamily === 'recents'
-          ? 'text-exo-yellow'
-          : 'text-white/40 group-hover:text-white/60'}">Recent</span
-      >
-    </button>
-  {/if}
-
-  <!-- HuggingFace Hub -->
-  <button
-    type="button"
-    onclick={() => onSelect("huggingface")}
-    class="group flex flex-col items-center justify-center p-2 rounded transition-all duration-200 cursor-pointer {selectedFamily ===
-    'huggingface'
-      ? 'bg-orange-500/20 border-l-2 border-orange-400'
-      : 'hover:bg-white/5 border-l-2 border-transparent'}"
-    title="Browse and add models from Hugging Face"
-  >
-    <FamilyLogos
-      family="huggingface"
-      class={selectedFamily === "huggingface"
-        ? "text-orange-400"
-        : "text-white/50 group-hover:text-orange-400/70"}
-    />
-    <span
-      class="text-[11px] font-mono mt-0.5 {selectedFamily === 'huggingface'
-        ? 'text-orange-400'
-        : 'text-white/40 group-hover:text-white/60'}">Hub</span
-    >
-  </button>
-
-  <div class="h-px bg-exo-yellow/10 my-1"></div>
-
-  <!-- Model families -->
-  {#each families as family}
-    <button
-      type="button"
-      onclick={() => onSelect(family)}
-      class="group flex flex-col items-center justify-center p-2 rounded transition-all duration-200 cursor-pointer {selectedFamily ===
-      family
-        ? 'bg-exo-yellow/20 border-l-2 border-exo-yellow'
-        : 'hover:bg-white/5 border-l-2 border-transparent'}"
-      title={getFamilyName(family)}
-    >
-      <FamilyLogos
-        {family}
-        class={selectedFamily === family
-          ? "text-exo-yellow"
-          : "text-white/50 group-hover:text-white/70"}
-      />
-      <span
-        class="text-[11px] font-mono mt-0.5 truncate max-w-full {selectedFamily ===
-        family
-          ? 'text-exo-yellow'
-          : 'text-white/40 group-hover:text-white/60'}"
-      >
-        {getFamilyName(family)}
-      </span>
-    </button>
-  {/each}
-</div>