models: persist model selection per catalog across chestnut state changes (#1960)

* models: preserve user model selection across reboots and power cycles

* no

* again

* idk

* over

.github/workflows/build-default-models.yaml

@@ -10,13 +10,18 @@ on:
         options:
           - small
           - big
+          - dm
   workflow_call:
     inputs:
       target:
-        description: 'Model target to build (small or big)'
+        description: 'Model target to build (small, big, or dm)'
         required: true
         type: string
 
+concurrency:
+  group: build-default-models-${{ inputs.target }}
+  cancel-in-progress: false
+
 env:
   HF_REPO: sunnypilot/sunnypilot_models_v1
 
@@ -28,9 +33,7 @@ jobs:
       onnx_ref: ${{ steps.resolve.outputs.onnx_ref }}
       onnx_path: ${{ steps.resolve.outputs.onnx_path }}
       hf_defaults_path: ${{ steps.resolve.outputs.hf_defaults_path }}
-      target_hardware: ${{ steps.resolve.outputs.target_hardware }}
       tinygrad_ref: ${{ steps.resolve.outputs.tinygrad_ref }}
-      dm_onnx_ref: ${{ steps.resolve.outputs.dm_onnx_ref }}
     steps:
       - uses: actions/checkout@v4
         with:
@@ -44,12 +47,14 @@ jobs:
             NAME=$(python3 -c "from openpilot.sunnypilot.models.model_name import DEFAULT_BIG_MODEL; print(DEFAULT_BIG_MODEL)")
             ONNX_PATH="openpilot/selfdrive/modeld/models/big_driving_supercombo.onnx"
             HF_DEFAULTS_PATH="models/defaults/big"
-            TARGET_HW="usbgpu"
+          elif [ "${{ inputs.target }}" = "dm" ]; then
+            ONNX_PATH="openpilot/selfdrive/modeld/models/dmonitoring_model.onnx"
+            HF_DEFAULTS_PATH="models/defaults/dm"
+            NAME="dmonitoring_model ($(git log -1 --format=%cd --date=format:'%B %d, %Y' -- "$ONNX_PATH"))"
           else
             NAME=$(python3 -c "from openpilot.sunnypilot.models.model_name import DEFAULT_MODEL; print(DEFAULT_MODEL)")
             ONNX_PATH="openpilot/selfdrive/modeld/models/driving_supercombo.onnx"
             HF_DEFAULTS_PATH="models/defaults/small"
-            TARGET_HW="qcom"
           fi
 
           ONNX_REF=$(git log -1 --format='%H' -- "$ONNX_PATH")
@@ -59,65 +64,279 @@ jobs:
             exit 1
           fi
 
-          DM_ONNX_REF=""
-          if [ "${{ inputs.target }}" = "small" ]; then
-            DM_ONNX_REF=$(git log -1 --format='%H' -- openpilot/selfdrive/modeld/models/dmonitoring_model.onnx)
-          fi
-
           echo "model_name=${NAME}" >> $GITHUB_OUTPUT
           echo "onnx_ref=${ONNX_REF}" >> $GITHUB_OUTPUT
           echo "onnx_path=${ONNX_PATH}" >> $GITHUB_OUTPUT
           echo "hf_defaults_path=${HF_DEFAULTS_PATH}" >> $GITHUB_OUTPUT
-          echo "target_hardware=${TARGET_HW}" >> $GITHUB_OUTPUT
           echo "tinygrad_ref=${TINYGRAD_REF}" >> $GITHUB_OUTPUT
-          echo "dm_onnx_ref=${DM_ONNX_REF}" >> $GITHUB_OUTPUT
 
-  build_driving_model:
+  build_small_model:
     needs: resolve
-    uses: ./.github/workflows/sunnypilot-build-model.yaml
-    with:
-      upstream_branch: ${{ needs.resolve.outputs.onnx_ref }}
-      custom_name: ${{ needs.resolve.outputs.model_name }}
-      target_hardware: ${{ needs.resolve.outputs.target_hardware }}
-    secrets: inherit
+    if: ${{ inputs.target == 'small' }}
+    runs-on: [self-hosted, tici]
+    env:
+      SMALL_ONNX: openpilot/selfdrive/modeld/models/driving_supercombo.onnx
+      SMALL_PKL: openpilot/selfdrive/modeld/models/driving_tinygrad.pkl
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          submodules: recursive
+
+      - name: Pull ONNX via LFS
+        run: git lfs pull -I "${{ env.SMALL_ONNX }}"
+
+      - name: Set environment variables
+        run: |
+          source /etc/profile
+          export UV_PROJECT_ENVIRONMENT=${HOME}/venv
+          export UV_PYTHON_PREFERENCE=managed
+          export UV_PYTHON_INSTALL_DIR=${HOME}/uv/python
+          export VIRTUAL_ENV=$UV_PROJECT_ENVIRONMENT
+          uv sync --frozen
+          printenv >> $GITHUB_ENV
+
+      - name: Disable powersave
+        run: |
+          source ${UV_PROJECT_ENVIRONMENT}/bin/activate
+          PYTHONPATH=$PYTHONPATH:${{ github.workspace }}/ ${{ github.workspace }}/scripts/manage-powersave.py --disable
+
+      - name: Compile small model with stock compiler
+        run: |
+          source ${UV_PROJECT_ENVIRONMENT}/bin/activate
+          export PYTHONPATH="${PYTHONPATH}:${{ github.workspace }}/tinygrad_repo:${{ github.workspace }}"
+
+          MODEL_SIZE=$(python3 -c "from openpilot.common.transformations.model import MEDMODEL_INPUT_SIZE as s; print(f'{s[0]}x{s[1]}')")
+          CAMERA_RES=$(python3 -c "from openpilot.common.transformations.camera import _ar_ox_fisheye as a, _os_fisheye as o; print(f'{a.width}x{a.height} {o.width}x{o.height}')")
+          FRAME_SKIP=$(python3 -c "from openpilot.selfdrive.modeld.constants import ModelConstants as MC; print(MC.MODEL_RUN_FREQ // MC.MODEL_CONTEXT_FREQ)")
+
+          TG_FLAGS="DEV=QCOM IMAGE=1 FLOAT16=1 NOLOCALS=1 JIT_BATCH_SIZE=0 OPENPILOT_HACKS=1"
+
+          env ${TG_FLAGS} python3 \
+            ${{ github.workspace }}/openpilot/selfdrive/modeld/compile_modeld.py \
+            --onnx ${{ github.workspace }}/${{ env.SMALL_ONNX }} \
+            --model-size $MODEL_SIZE \
+            --camera-resolutions $CAMERA_RES \
+            --frame-skip $FRAME_SKIP \
+            --output ${{ github.workspace }}/${{ env.SMALL_PKL }}
+
+      - name: Chunk small pkl
+        run: |
+          source ${UV_PROJECT_ENVIRONMENT}/bin/activate
+          export PYTHONPATH=${{ github.workspace }}
+          python3 -c "
+          from openpilot.common.file_chunker import chunk_file, get_chunk_targets
+          import os
+          pkl = '${{ github.workspace }}/${{ env.SMALL_PKL }}'
+          size = os.path.getsize(pkl)
+          targets = get_chunk_targets(pkl, size)
+          chunk_file(pkl, targets)
+          print(f'Chunked into {len(targets)} files')
+          "
+
+      - name: Prepare output
+        env:
+          MODEL_NAME: ${{ needs.resolve.outputs.model_name }}
+        run: |
+          source ${UV_PROJECT_ENVIRONMENT}/bin/activate
+          export PYTHONPATH=${{ github.workspace }}
+          MODELS_DIR="${{ github.workspace }}/openpilot/selfdrive/modeld/models"
+          OUTPUT_DIR="${{ github.workspace }}/small_output"
+          PKL_BASE="driving_tinygrad.pkl"
+          mkdir -p "$OUTPUT_DIR"
+
+          cp "$MODELS_DIR/${PKL_BASE}".chunk* "$OUTPUT_DIR/"
+          cp "$MODELS_DIR/${PKL_BASE}.chunkmanifest" "$OUTPUT_DIR/"
+
+          python3 "${{ github.workspace }}/release/ci/model_generator.py" \
+            --model-dir "$MODELS_DIR" \
+            --output-dir "$OUTPUT_DIR" \
+            --custom-name "$MODEL_NAME" \
+            --upstream-branch "${{ needs.resolve.outputs.onnx_ref }}"
+
+          echo "model-${MODEL_NAME}-${{ github.run_number }}" > "$OUTPUT_DIR/artifact_name.txt"
+
+      - name: Upload small model artifact
+        uses: actions/upload-artifact@v4
+        with:
+          name: model-${{ needs.resolve.outputs.model_name }}-${{ github.run_number }}
+          path: ${{ github.workspace }}/small_output/
+
+      - name: Upload artifact name file
+        uses: actions/upload-artifact@v4
+        with:
+          name: artifact-name-${{ needs.resolve.outputs.model_name }}
+          path: ${{ github.workspace }}/small_output/artifact_name.txt
+
+      - name: Re-enable powersave
+        if: always()
+        run: |
+          source ${UV_PROJECT_ENVIRONMENT}/bin/activate
+          PYTHONPATH=$PYTHONPATH:${{ github.workspace }}/ ${{ github.workspace }}/scripts/manage-powersave.py --enable
+
+  build_big_model:
+    needs: resolve
+    if: ${{ inputs.target == 'big' }}
+    runs-on: [self-hosted, usbgpu]
+    env:
+      BIG_ONNX: openpilot/selfdrive/modeld/models/big_driving_supercombo.onnx
+      BIG_PKL: openpilot/selfdrive/modeld/models/big_driving_tinygrad.pkl
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          submodules: recursive
+
+      - name: Pull big ONNX via LFS
+        run: git lfs pull -I "${{ env.BIG_ONNX }}"
+
+      - name: Set environment variables
+        run: |
+          source /etc/profile
+          export UV_PROJECT_ENVIRONMENT=${HOME}/venv
+          export UV_PYTHON_PREFERENCE=managed
+          export UV_PYTHON_INSTALL_DIR=${HOME}/uv/python
+          export VIRTUAL_ENV=$UV_PROJECT_ENVIRONMENT
+          uv sync --frozen
+          printenv >> $GITHUB_ENV
+
+      - name: Disable powersave
+        run: |
+          source ${UV_PROJECT_ENVIRONMENT}/bin/activate
+          PYTHONPATH=$PYTHONPATH:${{ github.workspace }}/ ${{ github.workspace }}/scripts/manage-powersave.py --disable
+
+      - name: Wait for chestnut PCIe link
+        run: |
+          source ${UV_PROJECT_ENVIRONMENT}/bin/activate
+          export PYTHONPATH="${PYTHONPATH}:${{ github.workspace }}/tinygrad_repo:${{ github.workspace }}"
+          python3 -c "
+          import time
+          from openpilot.system.hardware.chestnut.flash import link_up
+          for i in range(10):
+              if link_up():
+                  print(f'PCIe link up after {i+1} attempt(s)')
+                  break
+              time.sleep(1)
+          else:
+              raise RuntimeError('Chestnut PCIe link not ready after 10 attempts')
+          "
+
+      - name: Compile big model with stock compiler
+        run: |
+          source ${UV_PROJECT_ENVIRONMENT}/bin/activate
+          export PYTHONPATH="${PYTHONPATH}:${{ github.workspace }}/tinygrad_repo:${{ github.workspace }}"
+
+          MODEL_SIZE=$(python3 -c "from openpilot.common.transformations.model import MEDMODEL_INPUT_SIZE as s; print(f'{s[0]}x{s[1]}')")
+          CAMERA_RES=$(python3 -c "from openpilot.common.transformations.camera import _ar_ox_fisheye as a, _os_fisheye as o; print(f'{a.width}x{a.height} {o.width}x{o.height}')")
+          FRAME_SKIP=$(python3 -c "from openpilot.selfdrive.modeld.constants import ModelConstants as MC; print(MC.MODEL_RUN_FREQ // MC.MODEL_CONTEXT_FREQ)")
+
+          TG_FLAGS="DEBUG=2 DEV=USB+AMD:LLVM WARP_DEV=QCOM FLOAT16=1 JIT_BATCH_SIZE=0 GMMU=0 TC_OPT=2"
+
+          env ${TG_FLAGS} python3 \
+            ${{ github.workspace }}/openpilot/selfdrive/modeld/compile_modeld.py \
+            --onnx ${{ github.workspace }}/${{ env.BIG_ONNX }} \
+            --model-size $MODEL_SIZE \
+            --camera-resolutions $CAMERA_RES \
+            --frame-skip $FRAME_SKIP \
+            --output ${{ github.workspace }}/${{ env.BIG_PKL }}
+
+      - name: Chunk big pkl
+        run: |
+          source ${UV_PROJECT_ENVIRONMENT}/bin/activate
+          export PYTHONPATH=${{ github.workspace }}
+          python3 -c "
+          from openpilot.common.file_chunker import chunk_file, get_chunk_targets
+          import os
+          pkl = '${{ github.workspace }}/${{ env.BIG_PKL }}'
+          size = os.path.getsize(pkl)
+          targets = get_chunk_targets(pkl, size)
+          chunk_file(pkl, targets)
+          print(f'Chunked into {len(targets)} files')
+          "
+
+      - name: Prepare output
+        env:
+          MODEL_NAME: ${{ needs.resolve.outputs.model_name }}
+        run: |
+          source ${UV_PROJECT_ENVIRONMENT}/bin/activate
+          export PYTHONPATH=${{ github.workspace }}
+          MODELS_DIR="${{ github.workspace }}/openpilot/selfdrive/modeld/models"
+          OUTPUT_DIR="${{ github.workspace }}/big_output"
+          PKL_BASE="big_driving_tinygrad.pkl"
+          mkdir -p "$OUTPUT_DIR"
+
+          cp "$MODELS_DIR/${PKL_BASE}".chunk* "$OUTPUT_DIR/"
+          cp "$MODELS_DIR/${PKL_BASE}.chunkmanifest" "$OUTPUT_DIR/"
+
+          python3 "${{ github.workspace }}/release/ci/model_generator.py" \
+            --model-dir "$MODELS_DIR" \
+            --output-dir "$OUTPUT_DIR" \
+            --custom-name "$MODEL_NAME" \
+            --upstream-branch "${{ needs.resolve.outputs.onnx_ref }}"
+
+          echo "model-${MODEL_NAME}-${{ github.run_number }}" > "$OUTPUT_DIR/artifact_name.txt"
+
+      - name: Upload big model artifact
+        uses: actions/upload-artifact@v4
+        with:
+          name: model-${{ needs.resolve.outputs.model_name }}-${{ github.run_number }}
+          path: ${{ github.workspace }}/big_output/
+
+      - name: Upload artifact name file
+        uses: actions/upload-artifact@v4
+        with:
+          name: artifact-name-${{ needs.resolve.outputs.model_name }}
+          path: ${{ github.workspace }}/big_output/artifact_name.txt
+
+      - name: Re-enable powersave
+        if: always()
+        run: |
+          source ${UV_PROJECT_ENVIRONMENT}/bin/activate
+          PYTHONPATH=$PYTHONPATH:${{ github.workspace }}/ ${{ github.workspace }}/scripts/manage-powersave.py --enable
 
   upload_defaults:
-    needs: [ resolve, build_driving_model, build_dm_model ]
-    if: ${{ !cancelled() && needs.build_driving_model.result == 'success' && (inputs.target != 'small' || needs.build_dm_model.result == 'success') }}
+    needs: [ resolve, build_small_model, build_big_model, build_dm_model ]
+    if: |
+      ${{
+        !cancelled() &&
+        (inputs.target == 'big' && needs.build_big_model.result == 'success' ||
+         inputs.target == 'small' && needs.build_small_model.result == 'success' ||
+         inputs.target == 'dm' && needs.build_dm_model.result == 'success')
+      }}
     runs-on: ubuntu-24.04
     permissions:
       id-token: write
       contents: write
-    env:
-      DM_ONNX: openpilot/selfdrive/modeld/models/dmonitoring_model.onnx
     steps:
       - uses: actions/checkout@v4
 
       - name: Pull ONNX via LFS
-        run: git lfs pull -I "${{ needs.resolve.outputs.onnx_path }}${{ inputs.target == 'small' && ',openpilot/selfdrive/modeld/models/dmonitoring_model.onnx' || '' }}"
+        run: git lfs pull -I "${{ needs.resolve.outputs.onnx_path }}"
 
       - name: Install huggingface_hub
         run: pip install --upgrade "huggingface_hub>=0.22.0"
 
-      - name: Download driving artifact name
+      - name: Download artifact name
+        if: ${{ inputs.target == 'small' || inputs.target == 'big' }}
         uses: actions/download-artifact@v4
         with:
           name: artifact-name-${{ needs.resolve.outputs.model_name }}
           path: artifact_name
 
-      - name: Read driving artifact name
+      - name: Read artifact name
+        if: ${{ inputs.target == 'small' || inputs.target == 'big' }}
         id: artifact
         run: |
           ARTIFACT_NAME=$(cat artifact_name/artifact_name.txt)
           echo "artifact_name=$ARTIFACT_NAME" >> $GITHUB_OUTPUT
 
-      - name: Download driving model artifact
+      - name: Download model artifact
+        if: ${{ inputs.target == 'small' || inputs.target == 'big' }}
         uses: actions/download-artifact@v4
         with:
           name: ${{ steps.artifact.outputs.artifact_name }}
           path: output
 
-      - name: Upload driving model to HF
+      - name: Upload model to HF
+        if: ${{ inputs.target == 'small' || inputs.target == 'big' }}
         env:
           HF_OIDC_RESOURCE: datasets/${{ env.HF_REPO }}
           ARTIFACT_NAME: ${{ steps.artifact.outputs.artifact_name }}
@@ -136,14 +355,14 @@ jobs:
             --run-number "${{ github.run_number }}"
 
       - name: Download DM artifact
-        if: ${{ inputs.target == 'small' }}
+        if: ${{ inputs.target == 'dm' }}
         uses: actions/download-artifact@v4
         with:
           name: dm-model-${{ github.run_number }}
           path: dm_output
 
       - name: Generate DM metadata and upload to HF
-        if: ${{ inputs.target == 'small' }}
+        if: ${{ inputs.target == 'dm' }}
         env:
           HF_OIDC_RESOURCE: datasets/${{ env.HF_REPO }}
         run: |
@@ -176,8 +395,8 @@ jobs:
           metadata = {
               'bundles': [{
                   'short_name': 'DMMODEL',
-                  'display_name': 'dmonitoring_model',
-                  'ref': '${{ needs.resolve.outputs.dm_onnx_ref }}',
+                  'display_name': '${{ needs.resolve.outputs.model_name }}',
+                  'ref': '${{ needs.resolve.outputs.onnx_ref }}',
                   'runner': 'tinygrad',
                   'build_time': datetime.now(UTC).strftime('%Y-%m-%dT%H:%M:%SZ'),
                   'models': [{
@@ -200,15 +419,15 @@ jobs:
             --hf-defaults-path "${{ needs.resolve.outputs.hf_defaults_path }}" \
             --artifact-name "dm-model-${{ github.run_number }}" \
             --model-dir dm_output \
-            --onnx-path "${{ env.DM_ONNX }}" \
-            --onnx-ref "${{ needs.resolve.outputs.dm_onnx_ref }}" \
-            --model-name "dmonitoring_model" \
+            --onnx-path "${{ needs.resolve.outputs.onnx_path }}" \
+            --onnx-ref "${{ needs.resolve.outputs.onnx_ref }}" \
+            --model-name "${{ needs.resolve.outputs.model_name }}" \
             --tinygrad-ref "${{ needs.resolve.outputs.tinygrad_ref }}" \
             --run-number "${{ github.run_number }}"
 
   build_dm_model:
     needs: resolve
-    if: ${{ inputs.target == 'small' }}
+    if: ${{ inputs.target == 'dm' }}
     runs-on: [self-hosted, tici]
     env:
       DM_ONNX: openpilot/selfdrive/modeld/models/dmonitoring_model.onnx
@@ -218,6 +437,9 @@ jobs:
         with:
           submodules: recursive
 
+      - name: Pull DM ONNX via LFS
+        run: git lfs pull -I "${{ env.DM_ONNX }}"
+
       - name: Set environment variables
         run: |
           source /etc/profile

.github/workflows/download-hf-model-chunks/action.yml

@@ -0,0 +1,66 @@
+name: Download HF model chunks
+description: Resolve and download model chunks from HuggingFace in parallel
+
+inputs:
+  hf_repo:
+    description: HuggingFace dataset repo
+    required: true
+  models:
+    description: 'JSON array of {hf_path, onnx_hash, canonical} objects'
+    required: true
+  dest_dir:
+    description: Destination directory for downloaded chunks
+    required: true
+
+runs:
+  using: composite
+  steps:
+    - name: Download model chunks
+      shell: bash
+      env:
+        HF_REPO: ${{ inputs.hf_repo }}
+        MODELS_JSON: ${{ inputs.models }}
+        DEST_DIR: ${{ inputs.dest_dir }}
+      run: |
+        set -eo pipefail
+        DOWNLOAD_LIST=$(mktemp)
+
+        resolve_chunks() {
+          local HF_PATH="$1" ONNX_HASH="$2" CANONICAL="$3" DEST_DIR="$4"
+          local JSON_URL="https://huggingface.co/datasets/${HF_REPO}/resolve/main/${HF_PATH}/default_models.json"
+          local DEFAULTS BUNDLE ARTIFACT BASE_URL NUM_CHUNKS
+          DEFAULTS=$(curl -fsSL "$JSON_URL")
+          BUNDLE=$(echo "$DEFAULTS" | jq --arg hash "$ONNX_HASH" '.bundles[] | select(.onnx_sha256 == $hash)')
+          ARTIFACT=$(echo "$BUNDLE" | jq -r '.models[0].artifact')
+          BASE_URL=$(echo "$ARTIFACT" | jq -r '.download_uri.url' | sed 's|/[^/]*$||')
+          NUM_CHUNKS=$(echo "$ARTIFACT" | jq -r '.chunks | length')
+
+          mkdir -p "$DEST_DIR"
+          while IFS= read -r CHUNK_NAME; do
+            CHUNK_IDX=$(echo "$CHUNK_NAME" | grep -oP 'chunk\K[0-9]+of[0-9]+' || true)
+            if [ -z "$CHUNK_IDX" ]; then
+              echo "::error::Failed to parse chunk index from: $CHUNK_NAME"
+              return 1
+            fi
+            ENCODED_URL=$(python3 -c "import urllib.parse; print(urllib.parse.quote('${BASE_URL}/${CHUNK_NAME}', safe=':/'))")
+            printf '%s\t%s\n' "$ENCODED_URL" "${DEST_DIR}/${CANONICAL}.chunk${CHUNK_IDX}" >> "$DOWNLOAD_LIST"
+          done < <(echo "$ARTIFACT" | jq -r '.chunks[].file_name')
+          echo "$NUM_CHUNKS" > "${DEST_DIR}/${CANONICAL}.chunkmanifest"
+        }
+
+        echo "$MODELS_JSON" | jq -c '.[]' | while IFS= read -r model; do
+          HF_PATH=$(echo "$model" | jq -r '.hf_path')
+          ONNX_HASH=$(echo "$model" | jq -r '.onnx_hash')
+          CANONICAL=$(echo "$model" | jq -r '.canonical')
+          resolve_chunks "$HF_PATH" "$ONNX_HASH" "$CANONICAL" "$DEST_DIR"
+        done
+
+        TOTAL=$(wc -l < "$DOWNLOAD_LIST")
+        echo "Downloading $TOTAL chunks with 8 parallel connections..."
+        xargs -P8 -d'\n' -I{} bash -c '
+          URL="${1%%	*}"
+          DEST="${1#*	}"
+          echo "Downloading $(basename "$DEST")"
+          curl -fsSL --retry 3 --retry-delay 5 -o "$DEST" "$URL"
+        ' _ {} < "$DOWNLOAD_LIST"
+        rm -f "$DOWNLOAD_LIST"

.github/workflows/sunnypilot-build-model.yaml

@@ -188,7 +188,7 @@ jobs:
           if [ "${{ inputs.target_hardware }}" == "usbgpu" ]; then
             echo "USBGPU build"
             export USBGPU=1
-            TG_FLAGS="DEBUG=2 DEV=USB+AMD:LLVM WARP_DEV=QCOM FLOAT16=1 JIT_BATCH_SIZE=0 GMMU=0 TC_OPT=2"
+            TG_FLAGS="DEBUG=1 DEV=USB+AMD:LLVM WARP_DEV=QCOM FLOAT16=1 JIT_BATCH_SIZE=0 GMMU=0 TC_OPT=2"
             OUTPUT_PKL="${{ env.MODELS_DIR }}/big_driving_tinygrad.pkl"
           else
             echo "QCOM build"

.github/workflows/sunnypilot-build-prebuilt.yaml

@@ -39,6 +39,8 @@ jobs:
       include_big_model: ${{ steps.strategy.outputs.include_big_model }}
     steps:
       - uses: actions/checkout@v4
+        with:
+          fetch-depth: 1
       - name: Extract deploy strategy
         id: strategy
         run: |
@@ -96,6 +98,8 @@ jobs:
       }}
     steps:
       - uses: actions/checkout@v4
+        with:
+          fetch-depth: 1
       - name: Wait for Tests
         uses: ./.github/workflows/wait-for-action # Path to where you place the action
         with:
@@ -119,6 +123,7 @@ jobs:
     steps:
       - uses: actions/checkout@v4
         with:
+          fetch-depth: 1
           submodules: recursive
           ref: ${{ env.SOURCE_BRANCH }}
           repository: ${{ github.event.pull_request.head.repo.fork && github.event.pull_request.head.repo.full_name || github.repository }}
@@ -165,7 +170,7 @@ jobs:
           scons -j1 cache_dir="$SCONS_CACHE" --minimal \
             openpilot/selfdrive/locationd openpilot/sunnypilot/selfdrive/locationd
           echo "Building rest of sunnypilot"
-          /usr/bin/time -v scons -j$(nproc) cache_dir="$SCONS_CACHE" --minimal
+          SKIP_TINYGRAD_COMPILE=1 /usr/bin/time -v scons -j$(nproc) cache_dir="$SCONS_CACHE" --minimal
           touch ${BUILD_DIR}/prebuilt
           if [[ "${{ runner.debug }}" == "1" ]]; then
             ls -la ${BUILD_DIR}
@@ -214,59 +219,174 @@ jobs:
     outputs:
       onnx_sha256: ${{ steps.resolve.outputs.onnx_sha256 }}
     env:
+      GH_REPO: ${{ github.repository }}
       HF_REPO: sunnypilot/sunnypilot_models_v1
       HF_DEFAULTS_PATH: models/defaults/big
     steps:
-      - uses: actions/checkout@v4
-        with:
-          ref: ${{ github.head_ref || github.ref_name }}
-
-      - run: git lfs pull -I "openpilot/selfdrive/modeld/models/big_driving_supercombo.onnx"
-
-      - name: Check HF defaults and build if needed
+      - name: Resolve ONNX hash and tinygrad ref via API
         id: resolve
         run: |
-          ACTUAL_ONNX_HASH=$(sha256sum "openpilot/selfdrive/modeld/models/big_driving_supercombo.onnx" | cut -d' ' -f1)
-          echo "Repo ONNX hash: $ACTUAL_ONNX_HASH"
-          echo "onnx_sha256=$ACTUAL_ONNX_HASH" >> $GITHUB_OUTPUT
+          REF="${{ github.head_ref || github.ref_name }}"
+
+          ONNX_HASH=$(gh api "repos/${GH_REPO}/contents/openpilot/selfdrive/modeld/models/big_driving_supercombo.onnx?ref=${REF}" --jq '.content' | base64 -d | grep '^oid sha256:' | cut -d: -f2)
+          echo "ONNX hash: $ONNX_HASH"
+          echo "onnx_sha256=$ONNX_HASH" >> $GITHUB_OUTPUT
+
+          TINYGRAD_REF=$(gh api "repos/${GH_REPO}/contents/tinygrad_repo?ref=${REF}" --jq '.sha')
+          echo "tinygrad ref: $TINYGRAD_REF"
 
           JSON_URL="https://huggingface.co/datasets/${HF_REPO}/resolve/main/${HF_DEFAULTS_PATH}/default_models.json"
 
-          check_hash() {
+          check_defaults() {
             DEFAULTS=$(curl -fsSL "$JSON_URL" 2>/dev/null) || return 1
-            BUNDLE=$(echo "$DEFAULTS" | jq --arg hash "$ACTUAL_ONNX_HASH" '.bundles[] | select(.onnx_sha256 == $hash)' 2>/dev/null)
+            TINYGRAD_MATCH=$(echo "$DEFAULTS" | jq -r --arg ref "$TINYGRAD_REF" '.tinygrad_ref == $ref' 2>/dev/null)
+            [ "$TINYGRAD_MATCH" = "true" ] || return 1
+            BUNDLE=$(echo "$DEFAULTS" | jq --arg hash "$ONNX_HASH" '.bundles[] | select(.onnx_sha256 == $hash)' 2>/dev/null)
             [ -n "$BUNDLE" ] && [ "$BUNDLE" != "null" ]
           }
 
-          if check_hash; then
-            echo "HF defaults match repo ONNX"
-          else
-            echo "No matching model on HF — triggering build"
-            gh workflow run build-default-models.yaml --ref "${{ github.head_ref || github.ref_name }}" -f target=big
-
-            echo "Waiting for build to start..."
-            sleep 120
-
-            RUN_ID=$(gh run list --workflow=build-default-models.yaml --branch="${{ github.head_ref || github.ref_name }}" --limit=1 --json databaseId --jq '.[0].databaseId')
-            if [ -z "$RUN_ID" ] || [ "$RUN_ID" = "null" ]; then
-              echo "::error::Failed to find build-default-models run"
-              exit 1
-            fi
-
-            echo "Waiting for run $RUN_ID..."
-            gh run watch "$RUN_ID"
-
-            CONCLUSION=$(gh run view "$RUN_ID" --json conclusion --jq '.conclusion')
-            if [ "$CONCLUSION" != "success" ]; then
-              echo "::error::build-default-models failed: $CONCLUSION"
-              exit 1
-            fi
-
-            if ! check_hash; then
-              echo "::error::HF defaults still don't match after build"
-              exit 1
-            fi
+          if check_defaults; then
+            echo "HF defaults match repo ONNX hash and tinygrad ref"
+            exit 0
           fi
+
+          echo "No matching model on HF — dispatching build"
+          gh workflow run build-default-models.yaml --ref "$REF" -f target=big
+
+          echo "Polling HF for big model availability..."
+          for i in $(seq 1 90); do
+            sleep 30
+            if check_defaults; then
+              echo "Big model available on HF after $((i * 30))s"
+              exit 0
+            fi
+            echo "Poll $i/90: not yet available"
+          done
+
+          echo "::error::Big model not available on HF after 45 minutes"
+          exit 1
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Cancel run on failure
+        if: failure()
+        run: gh run cancel ${{ github.run_id }}
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+
+  prepare_small_model:
+    needs: [ prepare_strategy ]
+    runs-on: ubuntu-24.04
+    outputs:
+      driving_onnx_sha256: ${{ steps.resolve.outputs.driving_onnx_sha256 }}
+    env:
+      GH_REPO: ${{ github.repository }}
+      HF_REPO: sunnypilot/sunnypilot_models_v1
+      HF_DEFAULTS_PATH: models/defaults/small
+    steps:
+      - name: Resolve ONNX hash and tinygrad ref via API
+        id: resolve
+        run: |
+          REF="${{ github.head_ref || github.ref_name }}"
+
+          DRIVING_HASH=$(gh api "repos/${GH_REPO}/contents/openpilot/selfdrive/modeld/models/driving_supercombo.onnx?ref=${REF}" --jq '.content' | base64 -d | grep '^oid sha256:' | cut -d: -f2)
+          echo "Driving ONNX hash: $DRIVING_HASH"
+          echo "driving_onnx_sha256=$DRIVING_HASH" >> $GITHUB_OUTPUT
+
+          TINYGRAD_REF=$(gh api "repos/${GH_REPO}/contents/tinygrad_repo?ref=${REF}" --jq '.sha')
+          echo "tinygrad ref: $TINYGRAD_REF"
+
+          JSON_URL="https://huggingface.co/datasets/${HF_REPO}/resolve/main/${HF_DEFAULTS_PATH}/default_models.json"
+
+          check_defaults() {
+            DEFAULTS=$(curl -fsSL "$JSON_URL" 2>/dev/null) || return 1
+            TINYGRAD_MATCH=$(echo "$DEFAULTS" | jq -r --arg ref "$TINYGRAD_REF" '.tinygrad_ref == $ref' 2>/dev/null)
+            [ "$TINYGRAD_MATCH" = "true" ] || return 1
+            DRIVING=$(echo "$DEFAULTS" | jq --arg hash "$DRIVING_HASH" '.bundles[] | select(.onnx_sha256 == $hash)' 2>/dev/null)
+            [ -n "$DRIVING" ] && [ "$DRIVING" != "null" ] || return 1
+          }
+
+          if check_defaults; then
+            echo "HF defaults match repo ONNX hash and tinygrad ref"
+            exit 0
+          fi
+
+          echo "No matching model on HF — dispatching build"
+          gh workflow run build-default-models.yaml --ref "$REF" -f target=small
+
+          echo "Polling HF for model availability..."
+          for i in $(seq 1 60); do
+            sleep 30
+            if check_defaults; then
+              echo "Model available on HF after $((i * 30))s"
+              exit 0
+            fi
+            echo "Poll $i/60: not yet available"
+          done
+
+          echo "::error::Small driving model not available on HF after 30 minutes"
+          exit 1
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Cancel run on failure
+        if: failure()
+        run: gh run cancel ${{ github.run_id }}
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+
+  prepare_dm_model:
+    needs: [ prepare_strategy ]
+    runs-on: ubuntu-24.04
+    outputs:
+      dm_onnx_sha256: ${{ steps.resolve.outputs.dm_onnx_sha256 }}
+    env:
+      GH_REPO: ${{ github.repository }}
+      HF_REPO: sunnypilot/sunnypilot_models_v1
+      HF_DEFAULTS_PATH: models/defaults/dm
+    steps:
+      - name: Resolve ONNX hash and tinygrad ref via API
+        id: resolve
+        run: |
+          REF="${{ github.head_ref || github.ref_name }}"
+
+          DM_HASH=$(gh api "repos/${GH_REPO}/contents/openpilot/selfdrive/modeld/models/dmonitoring_model.onnx?ref=${REF}" --jq '.content' | base64 -d | grep '^oid sha256:' | cut -d: -f2)
+          echo "DM ONNX hash: $DM_HASH"
+          echo "dm_onnx_sha256=$DM_HASH" >> $GITHUB_OUTPUT
+
+          TINYGRAD_REF=$(gh api "repos/${GH_REPO}/contents/tinygrad_repo?ref=${REF}" --jq '.sha')
+          echo "tinygrad ref: $TINYGRAD_REF"
+
+          JSON_URL="https://huggingface.co/datasets/${HF_REPO}/resolve/main/${HF_DEFAULTS_PATH}/default_models.json"
+
+          check_defaults() {
+            DEFAULTS=$(curl -fsSL "$JSON_URL" 2>/dev/null) || return 1
+            TINYGRAD_MATCH=$(echo "$DEFAULTS" | jq -r --arg ref "$TINYGRAD_REF" '.tinygrad_ref == $ref' 2>/dev/null)
+            [ "$TINYGRAD_MATCH" = "true" ] || return 1
+            DM=$(echo "$DEFAULTS" | jq --arg hash "$DM_HASH" '.bundles[] | select(.onnx_sha256 == $hash)' 2>/dev/null)
+            [ -n "$DM" ] && [ "$DM" != "null" ] || return 1
+          }
+
+          if check_defaults; then
+            echo "HF defaults match DM ONNX hash and tinygrad ref"
+            exit 0
+          fi
+
+          echo "No matching DM model on HF — dispatching build"
+          gh workflow run build-default-models.yaml --ref "$REF" -f target=dm
+
+          echo "Polling HF for DM model availability..."
+          for i in $(seq 1 60); do
+            sleep 30
+            if check_defaults; then
+              echo "DM model available on HF after $((i * 30))s"
+              exit 0
+            fi
+            echo "Poll $i/60: not yet available"
+          done
+
+          echo "::error::DM model not available on HF after 30 minutes"
+          exit 1
         env:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
 
@@ -278,23 +398,24 @@ jobs:
 
   publish:
     concurrency:
-      # We do a bit of a hack here to avoid canceling the publishing job if a new commit comes in while we're publishing by adding the sha to the group name.
-      # This means that if multiple commits come in while we're publishing, they will be queued up and publish one after the other.
-      # Otherwise, if a job is waiting to be published due to environment wait time, it would be canceled by a new commit and restart the wait time.
       group: ${{ needs.prepare_strategy.outputs.publish_concurrency_group }}
       cancel-in-progress: ${{ needs.prepare_strategy.outputs.cancel_publish_in_progress == 'true' }}
     if: ${{
       always() && !cancelled() &&
       needs.build.result == 'success' &&
       needs.prepare_strategy.result == 'success' &&
+      needs.prepare_small_model.result == 'success' &&
+      needs.prepare_dm_model.result == 'success' &&
       (!contains(github.event_name, 'pull_request') || (github.event.action == 'labeled' && github.event.label.name == 'prebuilt')) &&
       (needs.prepare_strategy.outputs.include_big_model != 'true' || needs.prepare_chestnut.result == 'success')
       }}
-    needs: [ build, prepare_strategy, prepare_chestnut ]
+    needs: [ build, prepare_strategy, prepare_chestnut, prepare_small_model, prepare_dm_model ]
     runs-on: ubuntu-24.04
     environment: ${{ needs.prepare_strategy.outputs.environment }}
     steps:
       - uses: actions/checkout@v4
+        with:
+          fetch-depth: 1
 
       - name: Download prebuilt artifact
         uses: actions/download-artifact@v4
@@ -306,43 +427,16 @@ jobs:
           mkdir -p ${{ env.OUTPUT_DIR }}
           tar xzf prebuilt.tar.gz -C ${{ env.OUTPUT_DIR }}
 
-      - name: Prepare chestnut output
-        if: ${{ needs.prepare_chestnut.result == 'success' }}
-        run: |
-          mkdir -p "${{ github.workspace }}/chestnut_output"
-          tar xzf prebuilt.tar.gz -C "${{ github.workspace }}/chestnut_output"
-
-      - name: Download big model chunks from HF
-        if: ${{ needs.prepare_chestnut.result == 'success' }}
-        env:
-          HF_REPO: sunnypilot/sunnypilot_models_v1
-          HF_DEFAULTS_PATH: models/defaults/big
-        run: |
-          ONNX_HASH="${{ needs.prepare_chestnut.outputs.onnx_sha256 }}"
-          JSON_URL="https://huggingface.co/datasets/${HF_REPO}/resolve/main/${HF_DEFAULTS_PATH}/default_models.json"
-          DEFAULTS=$(curl -fsSL "$JSON_URL")
-          BUNDLE=$(echo "$DEFAULTS" | jq --arg hash "$ONNX_HASH" '.bundles[] | select(.onnx_sha256 == $hash)')
-
-          mkdir -p big_model_chunks
-          ARTIFACT=$(echo "$BUNDLE" | jq -r '.models[0].artifact')
-          BASE_URL=$(echo "$ARTIFACT" | jq -r '.download_uri.url' | sed 's|/[^/]*$||')
-          NUM_CHUNKS=$(echo "$ARTIFACT" | jq -r '.chunks | length')
-
-          CANONICAL="big_driving_tinygrad.pkl"
-          echo "$ARTIFACT" | jq -r '.chunks[].file_name' | while read CHUNK_NAME; do
-            CHUNK_IDX=$(echo "$CHUNK_NAME" | grep -oP 'chunk\K[0-9]+of[0-9]+')
-            CANONICAL_CHUNK="${CANONICAL}.chunk${CHUNK_IDX}"
-            ENCODED_URL=$(python3 -c "import urllib.parse; print(urllib.parse.quote('${BASE_URL}/${CHUNK_NAME}', safe=':/'))")
-            echo "Downloading $CHUNK_NAME -> $CANONICAL_CHUNK"
-            curl -fsSL -o "big_model_chunks/${CANONICAL_CHUNK}" "$ENCODED_URL"
-          done
-
-          echo "$NUM_CHUNKS" > "big_model_chunks/${CANONICAL}.chunkmanifest"
-
-      - name: Inject big model into chestnut
-        if: ${{ needs.prepare_chestnut.result == 'success' }}
-        run: |
-          cp big_model_chunks/* "${{ github.workspace }}/chestnut_output/openpilot/selfdrive/modeld/models/"
+      - name: Download model chunks from HF
+        uses: ./.github/workflows/download-hf-model-chunks
+        with:
+          hf_repo: sunnypilot/sunnypilot_models_v1
+          dest_dir: ${{ env.OUTPUT_DIR }}/openpilot/selfdrive/modeld/models
+          models: |
+            [
+              {"hf_path": "models/defaults/small", "onnx_hash": "${{ needs.prepare_small_model.outputs.driving_onnx_sha256 }}", "canonical": "driving_tinygrad.pkl"},
+              {"hf_path": "models/defaults/dm", "onnx_hash": "${{ needs.prepare_dm_model.outputs.dm_onnx_sha256 }}", "canonical": "dmonitoring_model_tinygrad.pkl"}
+            ]
 
       - name: Configure Git
         run: |
@@ -364,22 +458,6 @@ jobs:
             "https://x-access-token:${{github.token}}@github.com/sunnypilot/sunnypilot.git" \
             "${{ needs.prepare_strategy.outputs.extra_version_identifier }}"
 
-      - name: Publish chestnut branch
-        if: ${{ needs.prepare_chestnut.result == 'success' }}
-        env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-        run: |
-          CHESTNUT_BRANCH="${{ needs.prepare_strategy.outputs.new_branch }}-chestnut"
-          CHESTNUT_DIR="${{ github.workspace }}/chestnut_output"
-
-          ${{ env.CI_DIR }}/publish.sh \
-            "${{ github.workspace }}" \
-            "$CHESTNUT_DIR" \
-            "$CHESTNUT_BRANCH" \
-            "${{ needs.prepare_strategy.outputs.version }}" \
-            "https://x-access-token:${{github.token}}@github.com/sunnypilot/sunnypilot.git" \
-            "${{ needs.prepare_strategy.outputs.extra_version_identifier }}"
-
       - name: Tag ${{ needs.prepare_strategy.outputs.environment }}
         if: ${{ needs.prepare_strategy.outputs.is_stable_branch == 'true' && (github.event_name != 'push' || !startsWith(github.ref, 'refs/tags/')) }}
         run: |
@@ -387,12 +465,77 @@ jobs:
             git tag -f -a ${TAG} -m "${{ needs.prepare_strategy.outputs.environment }} @ ${{ needs.prepare_strategy.outputs.version }} of build ${{ needs.prepare_strategy.outputs.build }}."
             git push -f origin ${TAG}
 
+  publish_chestnut:
+    concurrency:
+      group: ${{ needs.prepare_strategy.outputs.publish_concurrency_group }}-chestnut
+      cancel-in-progress: ${{ needs.prepare_strategy.outputs.cancel_publish_in_progress == 'true' }}
+    if: ${{
+      always() && !cancelled() &&
+      needs.build.result == 'success' &&
+      needs.prepare_strategy.result == 'success' &&
+      needs.prepare_small_model.result == 'success' &&
+      needs.prepare_dm_model.result == 'success' &&
+      needs.prepare_chestnut.result == 'success' &&
+      (!contains(github.event_name, 'pull_request') || (github.event.action == 'labeled' && github.event.label.name == 'prebuilt'))
+      }}
+    needs: [ build, prepare_strategy, prepare_chestnut, prepare_small_model, prepare_dm_model ]
+    runs-on: ubuntu-24.04
+    environment: ${{ needs.prepare_strategy.outputs.environment }}
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          fetch-depth: 1
+
+      - name: Download prebuilt artifact
+        uses: actions/download-artifact@v4
+        with:
+          name: prebuilt
+
+      - name: Untar prebuilt
+        run: |
+          mkdir -p ${{ env.OUTPUT_DIR }}
+          tar xzf prebuilt.tar.gz -C ${{ env.OUTPUT_DIR }}
+
+      - name: Download model chunks from HF
+        uses: ./.github/workflows/download-hf-model-chunks
+        with:
+          hf_repo: sunnypilot/sunnypilot_models_v1
+          dest_dir: ${{ env.OUTPUT_DIR }}/openpilot/selfdrive/modeld/models
+          models: |
+            [
+              {"hf_path": "models/defaults/small", "onnx_hash": "${{ needs.prepare_small_model.outputs.driving_onnx_sha256 }}", "canonical": "driving_tinygrad.pkl"},
+              {"hf_path": "models/defaults/dm", "onnx_hash": "${{ needs.prepare_dm_model.outputs.dm_onnx_sha256 }}", "canonical": "dmonitoring_model_tinygrad.pkl"},
+              {"hf_path": "models/defaults/big", "onnx_hash": "${{ needs.prepare_chestnut.outputs.onnx_sha256 }}", "canonical": "big_driving_tinygrad.pkl"}
+            ]
+
+      - name: Configure Git
+        run: |
+          git config --global user.email "github-actions[bot]@users.noreply.github.com"
+          git config --global user.name "github-actions[bot]"
+
+      - name: Publish chestnut branch
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        run: |
+          CHESTNUT_BRANCH="${{ needs.prepare_strategy.outputs.new_branch }}-chestnut"
+
+          ${{ env.CI_DIR }}/publish.sh \
+            "${{ github.workspace }}" \
+            "${{ env.OUTPUT_DIR }}" \
+            "$CHESTNUT_BRANCH" \
+            "${{ needs.prepare_strategy.outputs.version }}" \
+            "https://x-access-token:${{github.token}}@github.com/sunnypilot/sunnypilot.git" \
+            "${{ needs.prepare_strategy.outputs.extra_version_identifier }}"
+
   notify:
     needs:
     - prepare_strategy
     - build
     - publish
+    - publish_chestnut
     - prepare_chestnut
+    - prepare_small_model
+    - prepare_dm_model
     runs-on: ubuntu-24.04
     if: ${{ (always() && !cancelled() && !failure())
       && needs.publish.result == 'success'
@@ -400,6 +543,8 @@ jobs:
       && (fromJSON(vars.DEV_FEEDBACK_NOTIFICATION_BRANCHES_V2)[github.head_ref || github.ref_name] != null) }}
     steps:
       - uses: actions/checkout@v4
+        with:
+          fetch-depth: 1
 
       - name: Prepare notification message
         id: message

openpilot/common/params_keys.h

@@ -195,10 +195,11 @@ inline static std::unordered_map<std::string, ParamKeyAttributes> keys = {
 
     // Model Manager params
     {"ModelManager_ActiveBundle", {PERSISTENT, JSON}},
-    {"ModelManager_ActiveBundleUSBGPU", {PERSISTENT, JSON}},
-    {"ModelManager_ActiveJson", {CLEAR_ON_MANAGER_START, JSON}},
+    {"ModelManager_ActiveJson", {CLEAR_ON_MANAGER_START, STRING}},
+    {"ModelManager_PrevBundle", {PERSISTENT, JSON}},
+    {"ModelManager_PrevBundle_USBGPU", {PERSISTENT, JSON}},
     {"ModelManager_ClearCache", {CLEAR_ON_MANAGER_START, BOOL}},
-    {"ModelManager_DownloadRef", {CLEAR_ON_MANAGER_START | CLEAR_ON_ONROAD_TRANSITION, STRING}},
+    {"ModelManager_DownloadIndex", {CLEAR_ON_MANAGER_START | CLEAR_ON_ONROAD_TRANSITION, INT}},
     {"ModelManager_Favs", {PERSISTENT | BACKUP, STRING}},
     {"ModelManager_LastSyncTime", {CLEAR_ON_MANAGER_START | CLEAR_ON_OFFROAD_TRANSITION, INT, "0"}},
     {"ModelManager_LastSyncTime_USBGPU", {CLEAR_ON_MANAGER_START | CLEAR_ON_OFFROAD_TRANSITION, INT, "0"}},

openpilot/selfdrive/modeld/SConscript

@@ -73,44 +73,45 @@ compile_modeld_script = [
 model_w, model_h = MEDMODEL_INPUT_SIZE
 frame_skip = ModelConstants.MODEL_RUN_FREQ // ModelConstants.MODEL_CONTEXT_FREQ
 
-for usbgpu in [False, True] if USBGPU else [False]:
-  target_pkl_path = File(modeld_pkl_path(usbgpu)).abspath
-  # BIG_INTO_SMALL=1 builds the default target from the big model, e.g. to test it without a USB GPU
-  file_prefix, cmd_flags = ('big_', usbgpu_tg_flags) if usbgpu else ('big_' if os.getenv('BIG_INTO_SMALL') else '', tg_flags)
-  driving_onnx_deps = get_existing_chunks(File(f"models/{file_prefix}driving_supercombo.onnx").abspath)
-  camera_res_args = ' '.join(f'{cw}x{ch}' for cw, ch in CAMERA_CONFIGS)
-  # CPU 7 is isolated with isolcpus on AGNOS, so explicitly pin the compiler to it.
-  taskset = 'taskset -c 7 ' if arch == 'comma_arm64' else ''
-  cmd = (f'{cmd_flags} {mac_brew_string} {taskset}python3 {modeld_dir}/compile_modeld.py '
-        f'--model-size {model_w}x{model_h} '
-        f'--camera-resolutions {camera_res_args} '
-        f'--onnx {File(f"models/{file_prefix}driving_supercombo.onnx").abspath} '
-        f'--output {target_pkl_path} --frame-skip {frame_skip}')
-  onnx_sizes_sum = sum(os.path.getsize(f) for f in driving_onnx_deps)
-  chunk_targets = get_chunk_targets(target_pkl_path, estimate_pickle_max_size(onnx_sizes_sum))
-  def do_compile(target, source, env, command=cmd, pkl=target_pkl_path, chunks=chunk_targets):
-    from openpilot.system.hardware.chestnut.flash import link_up
-    # chestnut can enumerate before its PCIe link is up due to varying 12V power behavior across cars
-    for _ in range(10):
-      if link_up():
-        break
-      time.sleep(1)
-    else:
-      print("Chestnut not ready, skipping big model build")
-      return
-    if ret := env.Execute(command):
-      return ret
-    chunk_file(pkl, chunks)
-  def do_chunk(target, source, env, pkl=target_pkl_path, chunks=chunk_targets):
-    chunk_file(pkl, chunks)
-  actions = Action(do_compile, "  [USBGPU] $TARGET") if usbgpu else [cmd, Action(do_chunk, "  [CHUNK] $TARGET")]
-  node = lenv.Command(
-    chunk_targets,
-    tinygrad_files + compile_modeld_script + driving_onnx_deps + [Value(chunk_targets), chunker_file],
-    actions,
-  )
-  if usbgpu:
-    lenv.SideEffect(usbgpu_lock, node)
+if not os.getenv('SKIP_TINYGRAD_COMPILE'):
+  for usbgpu in [False, True] if USBGPU else [False]:
+    target_pkl_path = File(modeld_pkl_path(usbgpu)).abspath
+    # BIG_INTO_SMALL=1 builds the default target from the big model, e.g. to test it without a USB GPU
+    file_prefix, cmd_flags = ('big_', usbgpu_tg_flags) if usbgpu else ('big_' if os.getenv('BIG_INTO_SMALL') else '', tg_flags)
+    driving_onnx_deps = get_existing_chunks(File(f"models/{file_prefix}driving_supercombo.onnx").abspath)
+    camera_res_args = ' '.join(f'{cw}x{ch}' for cw, ch in CAMERA_CONFIGS)
+    # CPU 7 is isolated with isolcpus on AGNOS, so explicitly pin the compiler to it.
+    taskset = 'taskset -c 7 ' if arch == 'comma_arm64' else ''
+    cmd = (f'{cmd_flags} {mac_brew_string} {taskset}python3 {modeld_dir}/compile_modeld.py '
+          f'--model-size {model_w}x{model_h} '
+          f'--camera-resolutions {camera_res_args} '
+          f'--onnx {File(f"models/{file_prefix}driving_supercombo.onnx").abspath} '
+          f'--output {target_pkl_path} --frame-skip {frame_skip}')
+    onnx_sizes_sum = sum(os.path.getsize(f) for f in driving_onnx_deps)
+    chunk_targets = get_chunk_targets(target_pkl_path, estimate_pickle_max_size(onnx_sizes_sum))
+    def do_compile(target, source, env, command=cmd, pkl=target_pkl_path, chunks=chunk_targets):
+      from openpilot.system.hardware.chestnut.flash import link_up
+      # chestnut can enumerate before its PCIe link is up due to varying 12V power behavior across cars
+      for _ in range(10):
+        if link_up():
+          break
+        time.sleep(1)
+      else:
+        print("Chestnut not ready, skipping big model build")
+        return
+      if ret := env.Execute(command):
+        return ret
+      chunk_file(pkl, chunks)
+    def do_chunk(target, source, env, pkl=target_pkl_path, chunks=chunk_targets):
+      chunk_file(pkl, chunks)
+    actions = Action(do_compile, "  [USBGPU] $TARGET") if usbgpu else [cmd, Action(do_chunk, "  [CHUNK] $TARGET")]
+    node = lenv.Command(
+      chunk_targets,
+      tinygrad_files + compile_modeld_script + driving_onnx_deps + [Value(chunk_targets), chunker_file],
+      actions,
+    )
+    if usbgpu:
+      lenv.SideEffect(usbgpu_lock, node)
 
 # get model metadata
 fn = File(f"models/dmonitoring_model").abspath
@@ -142,4 +143,5 @@ def tg_compile(flags, model_name):
      Action(do_chunk, "  [CHUNK] $TARGET")],
   )
 
-tg_compile(tg_flags, 'dmonitoring_model')
+if not os.getenv('SKIP_TINYGRAD_COMPILE'):
+  tg_compile(tg_flags, 'dmonitoring_model')

openpilot/selfdrive/ui/sunnypilot/layouts/settings/models.py

@@ -10,11 +10,9 @@ import time
 import pyray as rl
 
 from openpilot.cereal import custom
-from openpilot.sunnypilot.models.fetcher import ModelFetcher, get_cached_bundles
-from openpilot.sunnypilot.models.helpers import ACTIVE_BUNDLE_KEYS, get_selected_bundle, resolve_bundle_by_ref
+from openpilot.sunnypilot.models.default_model import get_default_model
 from openpilot.common.constants import CV
 from openpilot.selfdrive.ui.ui_state import device, ui_state
-from openpilot.selfdrive.ui.sunnypilot.model_info import model_info
 from openpilot.system.ui.lib.multilang import tr
 from openpilot.system.ui.lib.application import gui_app
 from openpilot.system.ui.widgets import DialogResult, Widget
@@ -38,7 +36,6 @@ class ModelsLayout(Widget):
     super().__init__()
     self.model_manager = None
     self.model_dialog = None
-    self._selection_source = None
     self._downloading = False
     self.last_cache_calc_time = 0
 
@@ -52,23 +49,16 @@ class ModelsLayout(Widget):
 
   def _initialize_items(self):
     self.current_model_item = ListItemSP(
-      title=tr("Active Model"),
+      title=tr("Current Model"),
       description="",
       action_item=ScrollingButtonAction(tr("SELECT")),
       callback=self._handle_current_model_clicked
     )
 
-    self.other_model_item = ListItemSP(
-      title=tr("Big Model"),
-      action_item=ScrollingButtonAction(tr("SELECT")),
-      callback=self._handle_other_model_clicked
-    )
-
     self.download_item = download_status_item(lambda: tr("Download") if self._downloading else tr("Model Status"))
 
     self.refresh_item = button_item(tr("Refresh Model List"), tr("REFRESH"), "",
                                     lambda: (ui_state.params.put("ModelManager_LastSyncTime", 0),
-                                             ui_state.params.put("ModelManager_LastSyncTime_USBGPU", 0),
                                              gui_app.push_widget(alert_dialog(tr("Fetching Latest Models")))))
 
     self.clear_cache_item = ListItemSP(
@@ -78,8 +68,7 @@ class ModelsLayout(Widget):
       callback=self._clear_cache
     )
 
-    self.cancel_download_item = button_item(tr("Cancel Download"), tr("Cancel"), "",
-                                            lambda: ui_state.params.remove("ModelManager_DownloadRef"))
+    self.cancel_download_item = button_item(tr("Cancel Download"), tr("Cancel"), "", lambda: ui_state.params.remove("ModelManager_DownloadIndex"))
 
     self.lane_turn_value_control = option_item_sp(tr("Adjust Lane Turn Speed"), "LaneTurnValue", 500, 2000,
                                                   tr("Set the maximum speed for lane turn desires. Default is 19 mph."),
@@ -104,7 +93,7 @@ class ModelsLayout(Widget):
                                         1, None, True, "", style.BUTTON_ACTION_WIDTH, None, True,
                                         lambda v: f"{v / 100:.2f} m")
 
-    self.items = [self.current_model_item, self.other_model_item, self.cancel_download_item, self.download_item, self.refresh_item, self.clear_cache_item,
+    self.items = [self.current_model_item, self.cancel_download_item, self.download_item, self.refresh_item, self.clear_cache_item,
                   self.lane_turn_desire_toggle, self.lane_turn_value_control, self.lagd_toggle, self.delay_control, self.camera_offset]
 
   def _update_lagd_description(self, lagd_toggle: bool):
@@ -126,8 +115,12 @@ class ModelsLayout(Widget):
   def calculate_cache_size():
     cache_size = 0.0
     if os.path.exists(CUSTOM_MODEL_PATH):
-      cache_size = sum(os.path.getsize(os.path.join(CUSTOM_MODEL_PATH, file)) for file in os.listdir(CUSTOM_MODEL_PATH)) / (1024**2)
-    return cache_size
+      for file in os.listdir(CUSTOM_MODEL_PATH):
+        try:
+          cache_size += os.path.getsize(os.path.join(CUSTOM_MODEL_PATH, file))
+        except OSError:
+          continue
+    return cache_size / (1024**2)
 
   def _clear_cache(self):
     def _callback(response):
@@ -153,7 +146,7 @@ class ModelsLayout(Widget):
     if not bundle:
       return
 
-    self.cancel_download_item.set_visible(bool(self.model_manager.selectedBundle) and ui_state.params.get("ModelManager_DownloadRef") is not None)
+    self.cancel_download_item.set_visible(bool(self.model_manager.selectedBundle) and ui_state.params.get("ModelManager_DownloadIndex") is not None)
 
     if (current_time := time.monotonic()) - self.last_cache_calc_time > 0.5:
       self.last_cache_calc_time = current_time
@@ -191,37 +184,26 @@ class ModelsLayout(Widget):
 
   def _on_model_selected(self, result):
     if result != DialogResult.CONFIRM:
-      self.model_dialog = None
       return
     selected_ref = self.model_dialog.selection_ref
-    self.model_dialog = None
     if selected_ref == "Default":
-      if self._selection_source in ACTIVE_BUNDLE_KEYS:
-        ui_state.params.remove(ACTIVE_BUNDLE_KEYS[self._selection_source])
-      return
-    if selected_bundle := self._resolve_selected_bundle(selected_ref):
-      ui_state.params.put("ModelManager_DownloadRef", selected_bundle.ref)
-
-  def _resolve_selected_bundle(self, ref):
-    """Finds the bundle for a ref across both hardware manifests."""
-    active = ModelFetcher.active_source(ui_state.sm["deviceState"].chestnutPresent)
-    source_bundles = {
-      source: self.model_manager.availableBundles if source == active else get_cached_bundles(ui_state.params, source)
-      for source in ("qcom", "usbgpu")
-    }
-    resolved = resolve_bundle_by_ref(ref, source_bundles)
-    return resolved[0] if resolved else None
+      ui_state.params.remove("ModelManager_ActiveBundle")
+    elif selected_bundle := next((bundle for bundle in self.model_manager.availableBundles if bundle.ref == selected_ref), None):
+      ui_state.params.put("ModelManager_DownloadIndex", selected_bundle.index)
+    self.model_dialog = None
 
   @staticmethod
   def _bundle_to_node(bundle):
     return TreeNode(bundle.ref, {'display_name': bundle.displayName, 'short_name': bundle.internalName})
 
-  def _get_folders(self, favorites, bundles):
+  def _get_folders(self, favorites):
+    bundles = self.model_manager.availableBundles
     folders = {}
     for bundle in bundles:
       folders.setdefault(next((ov_ride.value for ov_ride in bundle.overrides if ov_ride.key == "folder"), ""), []).append(bundle)
 
-    folders_list = []
+    folders_list = [TreeFolder("", [TreeNode("Default", {'display_name': f"{get_default_model()} (Default)",
+                                                         'short_name': "Default"})])]
     for folder, folder_bundles in sorted(folders.items(), key=lambda x: max((bundle.index for bundle in x[1]), default=-1), reverse=True):
       folder_bundles.sort(key=lambda bundle: bundle.index, reverse=True)
       name = folder + (f" - (Updated: {m.group(1)})" if folder_bundles and (m := re.search(r'\(([^)]*)\)[^(]*$', folder_bundles[0].displayName)) else "")
@@ -232,45 +214,20 @@ class ModelsLayout(Widget):
     return folders_list
 
   def _handle_current_model_clicked(self):
-    self._open_source_dialog(ModelFetcher.active_source(ui_state.sm["deviceState"].chestnutPresent))
-
-  def _handle_other_model_clicked(self):
-    active = ModelFetcher.active_source(ui_state.sm["deviceState"].chestnutPresent)
-    self._open_source_dialog("qcom" if active == "usbgpu" else "usbgpu")
-
-  def _open_source_dialog(self, source):
-    """Opens the picker for one hardware: its model folders plus the Default reset entry."""
-    self._selection_source = source
     favs = ui_state.params.get("ModelManager_Favs")
     favorites = set(favs.split(';')) if favs else set()
-    folders_list = self._source_folders(favorites, source)
-    if not folders_list:
-      gui_app.push_widget(alert_dialog(tr("No models are available for this hardware yet. Connect to the internet and refresh the model list.")))
-      return
-    self.model_dialog = TreeOptionDialog(tr("Select a Model"), folders_list, self._slot_active_ref(source), "ModelManager_Favs",
-                                         get_folders_fn=lambda favs: self._source_folders(favs, source), on_exit=self._on_model_selected)
+    folders_list = self._get_folders(favorites)
+
+    active_ref = self.model_manager.activeBundle.ref if self.model_manager.activeBundle else "Default"
+    self.model_dialog = TreeOptionDialog(tr("Select a Model"), folders_list, active_ref, "ModelManager_Favs",
+                                         get_folders_fn=self._get_folders, on_exit=self._on_model_selected)
     gui_app.push_widget(self.model_dialog)
 
-  def _source_folders(self, favorites, source):
-    """Default reset entry on top, then the hardware's model folders."""
-    active = ModelFetcher.active_source(ui_state.sm["deviceState"].chestnutPresent)
-    bundles = self.model_manager.availableBundles if source == active else get_cached_bundles(ui_state.params, source)
-    if not bundles:
-      return []
-    folders_list = [TreeFolder("", [TreeNode("Default", {'display_name': "Default"})])]
-    folders_list.extend(self._get_folders(favorites, bundles))
-    return folders_list
-
-  @staticmethod
-  def _slot_active_ref(source: str) -> str:
-    bundle = get_selected_bundle(ui_state.params, source)
-    return bundle.ref if bundle else "Default"
-
   def _update_state(self):
     advanced_controls: bool = ui_state.params.get_bool("ShowAdvancedControls")
     turn_desire: bool = ui_state.params.get_bool("LaneTurnDesire")
     live_delay: bool = ui_state.params.get_bool("LagdToggle")
-    camera_offset: bool = ui_state.active_bundle is not None
+    camera_offset: bool = ui_state.params.get("ModelManager_ActiveBundle") is not None
 
     self.lane_turn_desire_toggle.action_item.set_state(turn_desire)
     self.lane_turn_value_control.set_visible(turn_desire and advanced_controls)
@@ -284,10 +241,9 @@ class ModelsLayout(Widget):
     self._update_lagd_description(live_delay)
     self.model_manager = ui_state.sm["modelManagerSP"]
     self._handle_bundle_download_progress()
-    source, active_name, other_name = model_info()
+    default_label = f"{get_default_model()} (Default)"
+    active_name = self.model_manager.activeBundle.displayName if self.model_manager and self.model_manager.activeBundle.ref else default_label
     self.current_model_item.action_item.set_value(active_name)
-    self.other_model_item.set_title(tr("Big Model") if source == "qcom" else tr("Small Model"))
-    self.other_model_item.action_item.set_value(other_name)
 
     if not ui_state.is_offroad():
       self.current_model_item.action_item.set_enabled(False)

openpilot/selfdrive/ui/sunnypilot/mici/layouts/models.py

@@ -7,25 +7,16 @@ See the LICENSE.md file in the root directory for more details.
 import pyray as rl
 
 from openpilot.cereal import custom
-from openpilot.selfdrive.ui.mici.widgets.dialog import BigDialog
-from openpilot.sunnypilot.models.fetcher import ModelFetcher, get_cached_bundles
-from openpilot.sunnypilot.models.helpers import ACTIVE_BUNDLE_KEYS
+from openpilot.sunnypilot.models.default_model import get_default_model
 from openpilot.selfdrive.ui.mici.widgets.button import BigButton
+from openpilot.selfdrive.ui.sunnypilot.layouts.settings.models import ModelsLayout
 from openpilot.selfdrive.ui.ui_state import ui_state, device
-from openpilot.selfdrive.ui.sunnypilot.model_info import model_info
 from openpilot.system.ui.lib.application import FontWeight, gui_app
 from openpilot.system.ui.lib.multilang import tr
 from openpilot.system.ui.widgets import Widget
 from openpilot.system.ui.widgets.label import UnifiedLabel
 from openpilot.system.ui.widgets.scroller import NavScroller
 
-def _model_info() -> tuple[str, str, str]:
-  """(active model, other-model header, other-model text) for the panel."""
-  source, active_name, other_name = model_info()
-  header = tr("small model") if source == "usbgpu" else tr("big model")
-  return active_name.lower(), header, other_name.lower()
-
-
 class CurrentModelInfo(Widget):
   def __init__(self):
     super().__init__()
@@ -35,12 +26,12 @@ class CurrentModelInfo(Widget):
     header_color = rl.Color(255, 255, 255, int(255 * 0.9))
     subheader_color = rl.Color(255, 255, 255, int(255 * 0.9 * 0.65))
     max_width = int(self._rect.width - 20)
-    active_text, info_header, info_text = _model_info()
     self.current_model_header = UnifiedLabel(tr("active model"), 48, max_width=max_width, text_color=header_color, font_weight=FontWeight.DISPLAY)
-    self.current_model_text = UnifiedLabel(active_text, 32, max_width=max_width, text_color=subheader_color, font_weight=FontWeight.ROMAN, scroll=True)
+    default_text = f"{get_default_model()} (Default)".lower()
+    self.current_model_text = UnifiedLabel(default_text, 32, max_width=max_width, text_color=subheader_color, font_weight=FontWeight.ROMAN, scroll=True)
 
-    self.info_header = UnifiedLabel(info_header, 48, max_width=max_width, text_color=header_color, font_weight=FontWeight.DISPLAY)
-    self.info_text = UnifiedLabel(info_text, 32, max_width=max_width, text_color=subheader_color, font_weight=FontWeight.ROMAN, scroll=True)
+    self.info_header = UnifiedLabel("cache size", 48, max_width=max_width, text_color=header_color, font_weight=FontWeight.DISPLAY)
+    self.info_text = UnifiedLabel("0 mb", 32, max_width=max_width, text_color=subheader_color, font_weight=FontWeight.ROMAN)
 
   def _render(self, _):
     self.current_model_header.set_position(self._rect.x + 20, self._rect.y - 10)
@@ -64,13 +55,12 @@ class ModelsLayoutMici(NavScroller):
     self._download_progress = "."
     self._download_frame = 0
     self._was_downloading = False
-    self._selection_source: str | None = None
 
     self.select_model_btn = BigButton(tr("select model"))
     self.select_model_btn.set_click_callback(self._show_folders)
 
     self.cancel_download_btn = BigButton(tr("cancel download"))
-    self.cancel_download_btn.set_click_callback(lambda: ui_state.params.remove("ModelManager_DownloadRef"))
+    self.cancel_download_btn.set_click_callback(lambda: ui_state.params.remove("ModelManager_DownloadIndex"))
 
     self.main_items = [self.current_model_info, self.select_model_btn, self.cancel_download_btn]
     self._scroller.add_widgets(self.main_items)
@@ -79,7 +69,8 @@ class ModelsLayoutMici(NavScroller):
   def model_manager(self):
     return ui_state.sm["modelManagerSP"]
 
-  def _get_grouped_bundles(self, bundles, favorites = None):
+  def _get_grouped_bundles(self, favorites = None):
+    bundles = self.model_manager.availableBundles
     folders = {}
     for bundle in bundles:
       folder = next((override.value for override in bundle.overrides if override.key == "folder"), "")
@@ -99,74 +90,47 @@ class ModelsLayoutMici(NavScroller):
   def _show_folders(self):
     self.focused_widget = self.select_model_btn
 
-    hardware_btns = []
-    for source, label in (("qcom", tr("small models")), ("usbgpu", tr("big models"))):
-      btn = BigButton(label.lower())
-      btn.set_click_callback(lambda s=source: self._select_hardware(s))
-      hardware_btns.append(btn)
-    self._push_selection_view(hardware_btns)
-
-  def _select_hardware(self, source):
-    self._selection_source = source
-
     favs = ui_state.params.get("ModelManager_Favs")
     favorites = set(favs.split(';')) if favs else set()
-    active = ModelFetcher.active_source(ui_state.sm["deviceState"].chestnutPresent)
-
-    if source != active:
-      bundles = get_cached_bundles(ui_state.params, source)
-      if not bundles:
-        gui_app.push_widget(BigDialog(title=tr("No models available"),
-                                      description=tr("No models are available for this hardware yet. Connect to the internet and refresh the model list.")))
-        return
-    else:
-      bundles = self.model_manager.availableBundles
-    folders = self._get_grouped_bundles(bundles, favorites)
 
+    folders = self._get_grouped_bundles(favorites)
     folder_buttons = []
-    default_btn = BigButton(tr("default"))
-    default_btn.set_click_callback(lambda s=source: self._select_default(s))
+    default_btn = BigButton(f"{get_default_model()} (Default)".lower())
+    default_btn.set_click_callback(self._select_default)
     folder_buttons.append(default_btn)
 
     for folder in sorted(folders.keys(), key=lambda f: max((bundle.index for bundle in folders[f]), default=-1), reverse=True):
-      btn = BigButton(folder.lower())
-      btn.set_click_callback(lambda f=folder: self._select_folder(f))
-      if folder.lower() == "favorites":
-        folder_buttons.insert(0, btn)
-      else:
-        folder_buttons.append(btn)
+      if folder.lower() in ["release models", "master models", "favorites"]:
+        btn = BigButton(folder.lower())
+        btn.set_click_callback(lambda f=folder: self._select_folder(f))
+        if folder.lower() == "favorites":
+          folder_buttons.insert(0, btn)
+        else:
+          folder_buttons.append(btn)
     self._push_selection_view(folder_buttons)
 
   def _pop_to_main(self):
     gui_app.pop_widgets_to(self)
-    self._scroller.scroll_panel.set_offset(0.0)
 
   def _select_model(self, bundle):
-    ui_state.params.put("ModelManager_DownloadRef", bundle.ref)
+    ui_state.params.put("ModelManager_DownloadIndex", bundle.index)
     self._pop_to_main()
 
-  def _select_default(self, source):
-    ui_state.params.remove(ACTIVE_BUNDLE_KEYS[source])
+  def _select_default(self):
+    ui_state.params.remove("ModelManager_ActiveBundle")
     self._pop_to_main()
 
   def _select_folder(self, folder_name):
-    source = self._selection_source
-    if source is None:  # folders are only reachable after picking a hardware
-      return
     favs = ui_state.params.get("ModelManager_Favs")
     favorites = set(favs.split(';')) if favs else set()
-    active = ModelFetcher.active_source(ui_state.sm["deviceState"].chestnutPresent)
 
-    if source != active:
-      bundles = get_cached_bundles(ui_state.params, source)
-    else:
-      bundles = self.model_manager.availableBundles
-    folders = self._get_grouped_bundles(bundles, favorites)
+    folders = self._get_grouped_bundles(favorites)
     bundles = sorted(folders.get(folder_name, []), key=lambda b: b.index, reverse=True)
 
     btns = []
     for bundle in bundles:
-      btn = BigButton(bundle.displayName.lower())
+      txt = bundle.displayName.lower()
+      btn = BigButton(txt)
       btn.set_click_callback(lambda b=bundle: self._select_model(b))
       btns.append(btn)
     self._push_selection_view(btns)
@@ -198,10 +162,11 @@ class ModelsLayoutMici(NavScroller):
     self._was_downloading = is_downloading
 
     self.current_model_info.current_model_header.set_text(tr("active model"))
-    active_text, info_header, info_text = _model_info()
-    self.current_model_info.current_model_text.set_text(active_text)
-    self.current_model_info.info_header.set_text(info_header)
-    self.current_model_info.info_text.set_text(info_text)
+    default_model_text = f"{get_default_model()} (Default)".lower()
+    model_text = manager.activeBundle.displayName.lower() if manager.activeBundle.ref else default_model_text
+    self.current_model_info.current_model_text.set_text(model_text)
+    self.current_model_info.info_header.set_text(tr("cache size"))
+    self.current_model_info.info_text.set_text(f"{ModelsLayout.calculate_cache_size():.2f} MB")
 
     if manager.selectedBundle and manager.selectedBundle.status == custom.ModelManagerSP.DownloadStatus.failed:
       self.current_model_info.info_header.set_text(tr("error") + self._download_progress)
@@ -227,7 +192,3 @@ class ModelsLayoutMici(NavScroller):
       self.current_model_info.info_header.set_text(tr("progress") + self._download_progress)
       self.current_model_info.info_header._shimmer = True
       self.current_model_info.info_text.set_text(f"{progress/count:.2f}%")
-
-    elif manager.selectedBundle and manager.selectedBundle.status == custom.ModelManagerSP.DownloadStatus.downloaded:
-      self.current_model_info.info_header.set_text(tr("downloaded"))
-      self.current_model_info.info_text.set_text(tr("downloaded"))

openpilot/selfdrive/ui/sunnypilot/model_info.py

@@ -1,25 +0,0 @@
-"""
-Copyright (c) 2021-, Haibin Wen, sunnypilot, and a number of other contributors.
-
-This file is part of sunnypilot and is licensed under the MIT License.
-See the LICENSE.md file in the root directory for more details.
-"""
-from openpilot.selfdrive.ui.ui_state import ui_state
-from openpilot.sunnypilot.models.helpers import get_active_source, get_selected_bundle
-from openpilot.sunnypilot.models.model_name import DEFAULT_BIG_MODEL, DEFAULT_MODEL
-
-
-def model_info() -> tuple[str, str, str]:
-  """returns (active source, active model name, other model name)"""
-  source = get_active_source(usbgpu=ui_state.usbgpu,
-                             usbgpu_active=ui_state.usbgpu_active, usbgpu_loading=ui_state.usbgpu_loading,
-                             offroad=ui_state.is_offroad())
-  other = "qcom" if source == "usbgpu" else "usbgpu"
-  active_bundle = get_selected_bundle(ui_state.params, source)
-  other_bundle = get_selected_bundle(ui_state.params, other)
-
-  active_name = active_bundle.displayName if active_bundle \
-    else f"{DEFAULT_BIG_MODEL if source == 'usbgpu' else DEFAULT_MODEL} (Default)"
-  other_name = other_bundle.displayName if other_bundle \
-    else f"{DEFAULT_MODEL if source == 'usbgpu' else DEFAULT_BIG_MODEL} (Default)"
-  return source, active_name, other_name

openpilot/selfdrive/ui/sunnypilot/ui_state.py

@@ -10,7 +10,6 @@ from openpilot.cereal import messaging, log, custom
 from opendbc.car.structs import car
 from openpilot.common.params import Params
 from openpilot.selfdrive.ui.sunnypilot.layouts.settings.display import OnroadBrightness
-from openpilot.sunnypilot.models.helpers import get_active_bundle
 from openpilot.sunnypilot.sunnylink.sunnylink_state import SunnylinkState
 from openpilot.system.ui.lib.application import gui_app
 from openpilot.system.ui.sunnypilot.widgets.screen_saver import ScreenSaverSP
@@ -151,7 +150,7 @@ class UIStateSP:
       self.has_icbm = self.CP_SP.intelligentCruiseButtonManagementAvailable and self.params.get_bool("IntelligentCruiseButtonManagement")
 
     self._enforce_constraints()
-    self.active_bundle = get_active_bundle(self.params)
+    self.active_bundle = self.params.get("ModelManager_ActiveBundle")
     self.blindspot = self.params.get_bool("BlindSpot")
     self.chevron_metrics = self.params.get("ChevronInfo")
     self.custom_interactive_timeout = self.params.get("InteractivityTimeout", return_default=True)

openpilot/sunnypilot/modeld_v2/compile_modeld.py

@@ -7,6 +7,7 @@ See the LICENSE.md file in the root directory for more details.
 """
 
 import argparse
+import math
 import os
 import tempfile
 import time
@@ -66,14 +67,15 @@ def get_policy_npy_shapes(input_shapes: dict, is_supercombo: bool = False) -> tu
   if desire_key:
     shapes['desire'] = (input_shapes[desire_key][2],)
 
-  if is_supercombo and 'features_buffer' in input_shapes:
-    fb = input_shapes['features_buffer']
-    shapes['prev_feat'] = (fb[0], fb[2])
-
   for key, shape in input_shapes.items():
     if key not in (desire_key, 'features_buffer') and 'img' not in key:
       shapes[key] = tuple(shape)
 
+  if is_supercombo and 'features_buffer' in input_shapes:
+    fb = input_shapes['features_buffer']
+    feat_dim = math.prod(fb[2:])
+    shapes['prev_feat'] = (fb[0], feat_dim)
+
   sizes = [int(np.prod(size)) for size in shapes.values()]
   return shapes, sizes
 
@@ -117,8 +119,9 @@ def generate_queues_and_npy(input_shapes: dict, frame_skip: int, device: str = D
   }
 
   if features_buffer:
+    feat_dim = math.prod(features_buffer[2:])
     feat_q_len = frame_skip * features_buffer[1] if is_supercombo else frame_skip * (features_buffer[1] - 1) + 1
-    queues['feat_q'] = Tensor(np.zeros((feat_q_len, features_buffer[0], features_buffer[2]),
+    queues['feat_q'] = Tensor(np.zeros((feat_q_len, features_buffer[0], feat_dim),
                        dtype=np.float32), device=device).contiguous().realize()
 
   queues.update({key: Tensor(value, device='NPY').realize() for key, value in npy_arrays.items() if key in ('tfm', 'big_tfm')})
@@ -183,14 +186,14 @@ def make_run_policy(vision_runner, policy_runners: list, features_slice: slice,
     warped_dev = warped.to(Device.DEFAULT)
     Tensor.realize(packed_npy_inputs_dev, warped_dev)
 
-    img = shift_and_sample(img_q, warped_dev[0:1], sample_skip_fn).realize()
-    big_img = shift_and_sample(big_img_q, warped_dev[1:2], sample_skip_fn).realize()
+    img = shift_and_sample(img_q, warped_dev[0:1], sample_skip_fn)
+    big_img = shift_and_sample(big_img_q, warped_dev[1:2], sample_skip_fn)
 
     unpacked_tensors = [tensor.reshape(shape) for tensor, shape in zip(packed_npy_inputs_dev.split(npy_sizes), npy_shapes.values(), strict=True)]
     unpacked_dict = dict(zip(npy_shapes.keys(), unpacked_tensors, strict=True))
 
     desire_dev = unpacked_dict['desire']
-    desire_buf = shift_and_sample(desire_q, desire_dev.reshape(1, 1, -1), sample_desire_fn).realize()
+    desire_buf = shift_and_sample(desire_q, desire_dev.reshape(1, 1, -1), sample_desire_fn)
 
     inputs = {desire_key: desire_buf}
     for key, tensor_val in unpacked_dict.items():
@@ -199,7 +202,7 @@ def make_run_policy(vision_runner, policy_runners: list, features_slice: slice,
 
     if 'prev_feat' in unpacked_dict:
       prev_feat_dev = unpacked_dict['prev_feat']
-      inputs['features_buffer'] = shift_and_sample(feat_q, prev_feat_dev.reshape(1, 1, -1), sample_skip_fn).realize()
+      inputs['features_buffer'] = shift_and_sample(feat_q, prev_feat_dev.reshape(1, 1, -1), sample_skip_fn).reshape(input_shapes['features_buffer'])
 
     if vision_runner:
       vision_out_cast = next(iter(vision_runner({road_key: img, wide_key: big_img}).values())).cast('float32').realize()
@@ -211,7 +214,7 @@ def make_run_policy(vision_runner, policy_runners: list, features_slice: slice,
 
     inputs.update({road_key: img, wide_key: big_img})
     if 'features_buffer' not in inputs:
-      inputs['features_buffer'] = sample_skip_fn(feat_q)
+      inputs['features_buffer'] = sample_skip_fn(feat_q).reshape(input_shapes['features_buffer'])
 
     policy_out = next(iter(policy_runners[0](inputs).values())).cast('float32').realize()
     if 'features_buffer' not in inputs and features_slice is not None:

openpilot/sunnypilot/modeld_v2/tests/test_compile_modeld.py

@@ -195,3 +195,85 @@ class TestReadFileChunkedToDisk(OpenpilotTestCase):
 
       assert out.parent == Path(d)
       assert out.read_bytes() == payload
+
+
+class Test4DFeaturesBuffer(OpenpilotTestCase):
+  def test_get_policy_npy_shapes_4d(self):
+    from openpilot.sunnypilot.modeld_v2.compile_modeld import get_policy_npy_shapes
+    input_shapes = {
+      'desire_pulse': (1, 25, 8),
+      'features_buffer': (1, 24, 32, 512),  # compare 4d to 3d for regression
+      'traffic_convention': (1, 2),
+      'action_t': (1, 2)
+    }
+    shapes, sizes = get_policy_npy_shapes(input_shapes, is_supercombo=True)
+    assert shapes['prev_feat'] == (1, 16384)
+    assert sizes == [8, 2, 2, 16384]
+
+  def test_get_policy_npy_shapes_3d(self):
+    from openpilot.sunnypilot.modeld_v2.compile_modeld import get_policy_npy_shapes
+    input_shapes = {
+      'desire_pulse': (1, 25, 8),
+      'features_buffer': (1, 24, 512),
+      'traffic_convention': (1, 2),
+      'action_t': (1, 2)
+    }
+    shapes, sizes = get_policy_npy_shapes(input_shapes, is_supercombo=True)
+    assert shapes['prev_feat'] == (1, 512)
+    assert sizes == [8, 2, 2, 512]
+
+
+class TestStockCompileModeldEquivalence(OpenpilotTestCase):
+  def test_get_policy_npy_shapes_matches_stock(self):
+    from openpilot.selfdrive.modeld.compile_modeld import get_policy_npy_shapes as stock_get_policy_npy_shapes
+    from openpilot.sunnypilot.modeld_v2.compile_modeld import get_policy_npy_shapes as sunny_get_policy_npy_shapes
+
+    stock_input_shapes = {
+      'desire_pulse': (1, 25, 8),
+      'features_buffer': (1, 24, 512), # see below comment
+      'traffic_convention': (1, 2),
+      'action_t': (1, 2),
+    }
+
+    stock_shapes, stock_sizes = stock_get_policy_npy_shapes(stock_input_shapes)
+    sunny_shapes, sunny_sizes = sunny_get_policy_npy_shapes(stock_input_shapes, is_supercombo=True)
+
+    assert sunny_shapes == stock_shapes
+    assert sunny_sizes == stock_sizes
+    assert sunny_shapes['prev_feat'] == (1, 512)
+
+  def test_make_input_queues_full_stock_equivalence(self):
+    from openpilot.selfdrive.modeld.compile_modeld import make_input_queues as stock_make_input_queues
+    from openpilot.sunnypilot.modeld_v2.compile_modeld import make_supercombo_input_queues as sunny_make_supercombo_input_queues
+    input_shapes = {
+      'img': (1, 12, 128, 256),
+      'desire_pulse': (1, 25, 8),
+      'features_buffer': (1, 24, 512),  # when https://github.com/commaai/openpilot/pull/38681 merges, update to 1,24,32,512
+      'traffic_convention': (1, 2),
+      'action_t': (1, 2),
+    }
+    frame_skip = 4
+
+    stock_queues, stock_npy = stock_make_input_queues(input_shapes, frame_skip, device='NPY')
+    sunny_queues, sunny_npy = sunny_make_supercombo_input_queues(input_shapes, frame_skip, device='NPY')
+    assert set(sunny_queues.keys()) == set(stock_queues.keys())
+    for key in stock_queues:
+      assert sunny_queues[key].shape == stock_queues[key].shape, \
+        f"Queue shape mismatch for {key}: sunny {sunny_queues[key].shape} != stock {stock_queues[key].shape}"
+    assert set(sunny_npy.keys()) == set(stock_npy.keys())
+    for key in stock_npy:
+      assert sunny_npy[key].shape == stock_npy[key].shape, \
+        f"Numpy array shape mismatch for {key}: sunny {sunny_npy[key].shape} != stock {stock_npy[key].shape}"
+
+  def test_make_warp_queues_stock_equivalence(self):
+    from openpilot.selfdrive.modeld.compile_modeld import make_warp_input_queues as stock_make_warp_queues
+    from openpilot.sunnypilot.modeld_v2.compile_modeld import make_warp_queues as sunny_make_warp_queues
+    stock_vision_shapes = {'img': (1, 12, 128, 256)}  # for now?
+    stock_queues, stock_npy = stock_make_warp_queues(stock_vision_shapes, frame_skip=4, device='NPY')
+    sunny_queues, sunny_npy = sunny_make_warp_queues(device='NPY')
+
+    assert set(sunny_npy.keys()) == set(stock_npy.keys()) == {'tfm', 'big_tfm'}
+    for key in sunny_npy:
+      assert sunny_npy[key].shape == stock_npy[key].shape == (3, 3)
+
+

openpilot/sunnypilot/models/fetcher.py

@@ -138,60 +138,44 @@ class ModelCache:
 
 class ModelFetcher:
   """Handles fetching and caching of model data from remote source"""
-  MODEL_URL = "https://raw.githubusercontent.com/sunnypilot/sunnypilot-models/refs/heads/gh-pages/docs/driving_models_v20.json"
-  MODEL_URL_USBGPU = "https://raw.githubusercontent.com/sunnypilot/sunnypilot-models/refs/heads/gh-pages/docs/driving_models_usbgpu_v21.json"
-
-  MODEL_SOURCES = {
-    "qcom": (MODEL_URL, ""),
-    "usbgpu": (MODEL_URL_USBGPU, "_USBGPU"),
-  }
+  MODEL_URL = "https://raw.githubusercontent.com/sunnypilot/sunnypilot-models/refs/heads/gh-pages/docs/driving_models_v21.json"
+  MODEL_URL_USBGPU = "https://raw.githubusercontent.com/sunnypilot/sunnypilot-models/refs/heads/gh-pages/docs/driving_models_usbgpu_v22.json"
 
   def __init__(self, params: Params):
     self.params = params
     self.model_parser = ModelParser()
-    self._active_json_published = False
-    self.model_caches = {
-      source: ModelCache(params, suffix=suffix)
-      for source, (_, suffix) in self.MODEL_SOURCES.items()
-    }
+    self._is_usbgpu: bool | None = None
+    self.model_cache = ModelCache(params)
     self.model_url = self.MODEL_URL
-    self._update_model_source()
 
-  @staticmethod
-  def active_source(chestnut_present: bool) -> str:
-    return "usbgpu" if chestnut_present else "qcom"
+  def _update_model_source(self, chestnut_present: bool) -> None:
+    """Updates what json to use based on chestnut hardware presence via deviceState"""
+    is_usbgpu = chestnut_present
+    if is_usbgpu != self._is_usbgpu:
+      self._is_usbgpu = is_usbgpu
+      self.model_cache = ModelCache(self.params, suffix="_USBGPU" if is_usbgpu else "")
+      self.model_url = self.MODEL_URL_USBGPU if is_usbgpu else self.MODEL_URL
+      self.params.put("ModelManager_ActiveJson", self.model_url, block=True)
 
-  def _update_model_source(self) -> None:
-    """Publishes the manifest URLs for both sources"""
-    if not self._active_json_published:
-      self._active_json_published = True
-      self.params.put("ModelManager_ActiveJson", {
-        "qcom": self.MODEL_URL,
-        "usbgpu": self.MODEL_URL_USBGPU,
-      }, block=True)
-
-  def _fetch_and_cache_models(self, source: str) -> list[custom.ModelManagerSP.ModelBundle] | None:
+  def _fetch_and_cache_models(self) -> list[custom.ModelManagerSP.ModelBundle] | None:
     """Fetches fresh model data from remote and updates cache.
     Returns None on transport errors. Raises on 404 and other fatal HTTP errors.
     """
-    model_url, _ = self.MODEL_SOURCES[source]
     try:
-      response = requests.get(model_url, timeout=10)
+      response = requests.get(self.model_url, timeout=10)
 
       # Explicitly handle 404 differently
       if response.status_code == 404:
-        cloudlog.error(f"Models URL returned 404 Not Found: {model_url}")
-        raise HTTPError(f"404 Not Found: {model_url}", response=response)
+        cloudlog.error(f"Models URL returned 404 Not Found: {self.model_url}")
+        raise HTTPError(f"404 Not Found: {self.model_url}", response=response)
 
       # Raise for any other 4xx/5xx
       response.raise_for_status()
 
       json_data = response.json()
-      parsed = self.model_parser.parse_models(json_data)
-      if parsed:
-        self.model_caches[source].set(json_data)
-        cloudlog.debug(f"Successfully updated models cache for {source}")
-      return parsed
+      self.model_cache.set(json_data)
+      cloudlog.debug("Successfully updated models cache")
+      return self.model_parser.parse_models(json_data)
 
     except ConnectionError as e:
       cloudlog.warning(f"DNS/connection error while fetching models: {e}")
@@ -204,34 +188,16 @@ class ModelFetcher:
 
     return None
 
-  @staticmethod
-  def _cache_matches_source(source: str, cached_data: dict) -> bool:
-    """Confirms a cached manifest contains requested source's models."""
-    bundles = cached_data.get("bundles", [])
-    if source == "usbgpu":
-      return any(bundle.get("is_big") is True for bundle in bundles)
-    return not any(bundle.get("is_big") is True for bundle in bundles)
-
-  def _get_source_bundles(self, source: str) -> list[custom.ModelManagerSP.ModelBundle]:
-    cached_data, is_expired = self.model_caches[source].get()
+  def get_available_bundles(self, chestnut_present: bool = False) -> list[custom.ModelManagerSP.ModelBundle]:
+    """Gets the list of available models, with smart cache handling"""
+    self._update_model_source(chestnut_present)
+    cached_data, is_expired = self.model_cache.get()
 
     if cached_data and not is_expired:
-      if self._cache_matches_source(source, cached_data):
-        try:
-          parsed = self.model_parser.parse_models(cached_data)
-        except Exception:
-          cloudlog.warning(f"Failed to parse cached models for {source}; refetching", exc_info=True)
-        else:
-          if parsed:
-            cloudlog.debug(f"Using valid cached models data for source {source}")
-            return parsed
-          # a source-matching cache that yields no valid bundles is stale (e.g. an old
-          # manifest version) - do not trust it, refetch so the source is repopulated
-          cloudlog.warning(f"Cached models for {source} have no valid bundles; refetching")
-      else:
-        cloudlog.warning(f"Cached models for {source} not valid; refetching")
+      cloudlog.debug("Using valid cached models data")
+      return self.model_parser.parse_models(cached_data)
 
-    fetched_bundles = self._fetch_and_cache_models(source)
+    fetched_bundles = self._fetch_and_cache_models()
     if fetched_bundles is not None:
       return fetched_bundles
 
@@ -239,41 +205,14 @@ class ModelFetcher:
       cloudlog.warning("Failed to fetch fresh data and no cache available")
 
     cloudlog.warning("Failed to fetch fresh data. Using expired cache as fallback")
-    try:
-      return self.model_parser.parse_models(cached_data)
-    except Exception:
-      return []
-
-  def get_bundles_for_source(self, source: str) -> list[custom.ModelManagerSP.ModelBundle]:
-    """Gets the list of available models for a specific source, with smart cache handling."""
-    if source not in self.MODEL_SOURCES:
-      cloudlog.warning(f"Unknown model source: {source}")
-      return []
-    return self._get_source_bundles(source)
-
-
-def get_cached_bundles(params: Params, source: str) -> list[custom.ModelManagerSP.ModelBundle]:
-  """Reads a source's cached manifest from params and parses it into bundles."""
-
-  if source not in ModelFetcher.MODEL_SOURCES:
-    cloudlog.warning(f"Unknown model source: {source}")
-    return []
-  _, suffix = ModelFetcher.MODEL_SOURCES[source]
-  cached_data = params.get(f"ModelManager_ModelsCache{suffix}")
-  if not cached_data:
-    return []
-  try:
-    return ModelParser.parse_models(cached_data)
-  except Exception as e:
-    cloudlog.warning(f"Failed to parse cached models for source {source}: {e}")
-    return []
+    return self.model_parser.parse_models(cached_data)
 
 
 if __name__ == "__main__":
   from openpilot.selfdrive.modeld.helpers import usbgpu_present
   params = Params()
   model_fetcher = ModelFetcher(params)
-  bundles = model_fetcher.get_bundles_for_source(ModelFetcher.active_source(usbgpu_present()))
+  bundles = model_fetcher.get_available_bundles(chestnut_present=usbgpu_present())
   for bundle in bundles:
     for model in bundle.models:
       model_overrides = {override.key: override.value for override in bundle.overrides}

openpilot/sunnypilot/models/helpers.py

@@ -16,21 +16,14 @@ from openpilot.common.params import Params
 from openpilot.common.swaglog import cloudlog
 from openpilot.sunnypilot.models.constants import Meta, MetaSimPose, MetaTombRaider
 from openpilot.common.hardware.hw import Paths
-from openpilot.selfdrive.modeld.helpers import usbgpu_present
 
 # SET ME TO THE EXACT JSON VERSION WE SET IN SUNNYPILOT_MODELS REPO
-REQUIRED_JSON_VERSION = 17
+REQUIRED_JSON_VERSION = 18
 
 CUSTOM_MODEL_PATH = Paths.model_root()
 METADATA_PATH = Path(__file__).parent / '../models/supercombo_metadata.pkl'
 ModelManager = custom.ModelManagerSP
 
-ACTIVE_BUNDLE_KEYS = {
-  "qcom": "ModelManager_ActiveBundle",
-  "usbgpu": "ModelManager_ActiveBundleUSBGPU",
-}
-_LAST_VALIDATED_RAW: dict[str, bytes | None] = {}
-
 
 def _compute_hash(file_path: str) -> str | None:
   from openpilot.common.file_chunker import open_file_chunked
@@ -92,11 +85,11 @@ def _bundle_needs_reset(active_bundle: custom.ModelManagerSP.ModelBundle, availa
   if available_bundles is not None:
     matching_bundle = None
     for bundle in available_bundles:
-      if getattr(active_bundle, 'ref', None) and getattr(bundle, 'ref', None):
+      if active_bundle.ref and bundle.ref:
         if active_bundle.ref == bundle.ref:
           matching_bundle = bundle
           break
-      elif getattr(active_bundle, 'internalName', None) == getattr(bundle, 'internalName', None):
+      elif active_bundle.internalName == bundle.internalName:
         matching_bundle = bundle
         break
 
@@ -104,86 +97,55 @@ def _bundle_needs_reset(active_bundle: custom.ModelManagerSP.ModelBundle, availa
       return True
     if active_bundle.minimumSelectorVersion != matching_bundle.minimumSelectorVersion:
       return True
-
-    active_runner = getattr(active_bundle, 'runner', None)
-    matching_runner = getattr(matching_bundle, 'runner', None)
-    if active_runner is not None and matching_runner is not None:
-      if getattr(active_runner, 'raw', active_runner) != getattr(matching_runner, 'raw', matching_runner):
-        return True
+    if active_bundle.runner.raw != matching_bundle.runner.raw:
+      return True
     if set(_bundle_artifacts(active_bundle)) != set(_bundle_artifacts(matching_bundle)):
       return True
 
-  return not _bundle_is_valid_locally(active_bundle)
+  # missing files trigger re-download, not selection reset
+  return False
 
 
-def _parse_active_bundle(raw_bundle) -> "custom.ModelManagerSP.ModelBundle | None":
+def _prev_bundle_key(is_usbgpu: bool) -> str:
+  return "ModelManager_PrevBundle_USBGPU" if is_usbgpu else "ModelManager_PrevBundle"
+
+
+def validate_active_bundle(params: Params, available_bundles: list[custom.ModelManagerSP.ModelBundle] | None = None,
+                           is_usbgpu: bool = False) -> None:
+  raw_bundle = params.get("ModelManager_ActiveBundle")
+  if not raw_bundle:
+    prev = params.get(_prev_bundle_key(is_usbgpu))
+    if prev and (prev_bundle := get_active_bundle(params, raw_bundle_dict=prev)) is not None:
+      if not _bundle_needs_reset(prev_bundle, available_bundles):
+        params.put("ModelManager_ActiveBundle", prev, block=True)
+    return
+
+  active_bundle = get_active_bundle(params, raw_bundle_dict=raw_bundle)
+  if active_bundle is None or _bundle_needs_reset(active_bundle, available_bundles):
+    cloudlog.warning("Active model bundle invalid; resetting to default")
+    params.put(_prev_bundle_key(not is_usbgpu), raw_bundle, block=True)
+
+    prev = params.get(_prev_bundle_key(is_usbgpu))
+    if prev and (prev_bundle := get_active_bundle(params, raw_bundle_dict=prev)) is not None:
+      if not _bundle_needs_reset(prev_bundle, available_bundles):
+        params.put("ModelManager_ActiveBundle", prev, block=True)
+        return
+
+    params.remove("ModelManager_ActiveBundle")
+    params.put("ModelRunnerTypeCache", int(custom.ModelManagerSP.Runner.stock), block=True)
+
+
+def get_active_bundle(params: Params | None = None, raw_bundle_dict: dict | bytes | None = None) -> "custom.ModelManagerSP.ModelBundle | None":
+  params = params or Params()
   try:
-    if isinstance(raw_bundle, dict) and raw_bundle and is_bundle_version_compatible(raw_bundle):
-      return custom.ModelManagerSP.ModelBundle(**raw_bundle)
+    active_bundle_dict = raw_bundle_dict if raw_bundle_dict is not None else (params.get("ModelManager_ActiveBundle") or {})
+    if isinstance(active_bundle_dict, dict) and active_bundle_dict and is_bundle_version_compatible(active_bundle_dict):
+      return custom.ModelManagerSP.ModelBundle(**active_bundle_dict)
   except Exception:
     pass
   return None
 
 
-def get_selected_bundle(params: Params | None = None, source: str = "qcom") -> "custom.ModelManagerSP.ModelBundle | None":
-  params = params or Params()
-  return _parse_active_bundle(params.get(ACTIVE_BUNDLE_KEYS.get(source, "ModelManager_ActiveBundle")))
-
-
-def get_active_source(usbgpu: bool | None = None, usbgpu_active: bool | None = None,
-                      usbgpu_loading: bool | None = None, offroad: bool | None = None) -> str:
-  if usbgpu is None:
-    usbgpu = usbgpu_present()
-  state_valid = usbgpu_active is not None or usbgpu_loading is not None or offroad is not None
-  big_active = usbgpu and (not state_valid or usbgpu_active or usbgpu_loading or offroad)
-  return "usbgpu" if big_active else "qcom"
-
-
-def get_active_bundle(params: Params | None = None, *, usbgpu: bool | None = None) -> "custom.ModelManagerSP.ModelBundle | None":
-  params = params or Params()
-  if get_active_source(usbgpu=usbgpu) == "usbgpu":
-    if bundle := get_selected_bundle(params, "usbgpu"):
-      return bundle
-  return get_selected_bundle(params, "qcom")
-
-
-def resolve_bundle_by_ref(
-  ref: str, source_bundles: dict[str, list[custom.ModelManagerSP.ModelBundle]],
-) -> "tuple[custom.ModelManagerSP.ModelBundle, str] | None":
-  """Finds the bundle matching a ref across all sources."""
-  for source, bundles in source_bundles.items():
-    for bundle in bundles:
-      if bundle.ref == ref:
-        return bundle, source
-  return None
-
-
-def _validate_active_bundle(params: Params, source: str, available_bundles: list[custom.ModelManagerSP.ModelBundle] | None = None) -> None:
-  global _LAST_VALIDATED_RAW
-
-  key = ACTIVE_BUNDLE_KEYS[source]
-  raw_bundle = params.get(key)
-  if not raw_bundle:
-    return
-
-  if _LAST_VALIDATED_RAW.get(key) == raw_bundle:
-    return
-
-  active_bundle = _parse_active_bundle(raw_bundle)
-  if active_bundle is None or _bundle_needs_reset(active_bundle, available_bundles):
-    cloudlog.warning(f"Active model bundle invalid for {source}; resetting to default")
-    params.remove(key)
-    params.put("ModelRunnerTypeCache", int(custom.ModelManagerSP.Runner.stock), block=True)
-    _LAST_VALIDATED_RAW[key] = None
-  else:
-    _LAST_VALIDATED_RAW[key] = raw_bundle
-
-
-def validate_active_bundles(params: Params, source_bundles: dict[str, list[custom.ModelManagerSP.ModelBundle]]) -> None:
-  for source, bundles in source_bundles.items():
-    _validate_active_bundle(params, source, bundles)
-
-
 def get_active_model_runner(params: Params | None = None, force_check: bool = False) -> int:
   params = params or Params()
   cached_runner_type = params.get("ModelRunnerTypeCache")

openpilot/sunnypilot/models/manager.py

@@ -17,8 +17,7 @@ from openpilot.common.hardware.hw import Paths
 
 from openpilot.cereal import messaging, custom
 from openpilot.sunnypilot.models.fetcher import ModelFetcher
-from openpilot.sunnypilot.models.helpers import (ACTIVE_BUNDLE_KEYS, get_active_bundle, get_selected_bundle,
-                                                  resolve_bundle_by_ref, validate_active_bundles, verify_file)
+from openpilot.sunnypilot.models.helpers import get_active_bundle, validate_active_bundle, verify_file
 
 # (connect, read) seconds. read is per-request inactivity, not a total cap
 DOWNLOAD_TIMEOUT = (30, 30)
@@ -32,11 +31,9 @@ class ModelManagerSP:
     self.model_fetcher = ModelFetcher(self.params)
     self.pm = messaging.PubMaster(["modelManagerSP"])
     self.sm = messaging.SubMaster(["deviceState"])
-    self.chestnut_present = False
     self.available_models: list[custom.ModelManagerSP.ModelBundle] = []
-    self.source_models: dict[str, list[custom.ModelManagerSP.ModelBundle]] = {}
     self.selected_bundle: custom.ModelManagerSP.ModelBundle = None
-    self.active_bundle: custom.ModelManagerSP.ModelBundle = get_active_bundle(self.params, usbgpu=self.chestnut_present)
+    self.active_bundle: custom.ModelManagerSP.ModelBundle = get_active_bundle(self.params)
     self._chunk_size = 128 * 1000  # 128 KB chunks
     self._download_start_times: dict[str, float] = {}  # Track start time per model
 
@@ -80,7 +77,7 @@ class ModelManagerSP:
           f.write(chunk)
           bytes_downloaded += len(chunk)
 
-          if self.params.get("ModelManager_DownloadRef") is None:
+          if self.params.get("ModelManager_DownloadIndex") is None:
             raise Exception("Download cancelled")
 
           if total_size > 0:
@@ -118,7 +115,7 @@ class ModelManagerSP:
             for data in response.iter_content(chunk_size=self._chunk_size):
               f.write(data)
               chunk_downloaded += len(data)
-              if self.params.get("ModelManager_DownloadRef") is None:
+              if self.params.get("ModelManager_DownloadIndex") is None:
                 raise Exception("Download cancelled")
               intra = chunk_downloaded / max(chunk_size, 1)
               progress = min(99.0, ((i + intra) / num_chunks) * 100)
@@ -220,8 +217,8 @@ class ModelManagerSP:
     model_manager_state.availableBundles = self.available_models
     self.pm.send('modelManagerSP', msg)
 
-  async def _download_bundle(self, model_bundle: custom.ModelManagerSP.ModelBundle, destination_path: str, source: str) -> None:
-    """Downloads a bundle and sets it as the active bundle for its source"""
+  async def _download_bundle(self, model_bundle: custom.ModelManagerSP.ModelBundle, destination_path: str) -> None:
+    """Downloads all models in a bundle"""
     self.selected_bundle = model_bundle
     self.selected_bundle.status = custom.ModelManagerSP.DownloadStatus.downloading
     for model in self.selected_bundle.models:
@@ -243,9 +240,10 @@ class ModelManagerSP:
           seen_artifacts.add(artifact.fileName)
           await self._process_artifact(artifact, destination_path)
 
-      self.selected_bundle.status = custom.ModelManagerSP.DownloadStatus.downloaded
-      self.params.put(ACTIVE_BUNDLE_KEYS[source], model_bundle.to_dict(), block=True)
-      self.active_bundle = get_active_bundle(self.params, usbgpu=self.chestnut_present)
+      self.active_bundle = self.selected_bundle
+      self.active_bundle.status = custom.ModelManagerSP.DownloadStatus.downloaded
+      self.params.put("ModelManager_ActiveBundle", self.active_bundle.to_dict(), block=True)
+      self.selected_bundle = None
 
     except Exception:
       if self.selected_bundle is not None:
@@ -255,32 +253,37 @@ class ModelManagerSP:
     finally:
       self._report_status()
 
-  def download(self, model_bundle: custom.ModelManagerSP.ModelBundle, destination_path: str, source: str) -> None:
+  def download(self, model_bundle: custom.ModelManagerSP.ModelBundle, destination_path: str) -> None:
     """Main entry point for downloading a model bundle"""
-    asyncio.run(self._download_bundle(model_bundle, destination_path, source))
+    asyncio.run(self._download_bundle(model_bundle, destination_path))
+
+  BOOT_SETTLE_TICKS = 10  # seconds at 1 Hz before validating active bundle
 
   def main_thread(self) -> None:
     """Main thread for model management"""
     rk = Ratekeeper(1, print_delay_threshold=None)
+    boot_ticks = 0
 
     while True:
       try:
         self.sm.update(0)
-        self.chestnut_present = self.sm['deviceState'].chestnutPresent
-        self.source_models = {source: self.model_fetcher.get_bundles_for_source(source) for source in ModelFetcher.MODEL_SOURCES}
-        self.available_models = self.source_models[ModelFetcher.active_source(self.chestnut_present)]
-        validate_active_bundles(self.params, self.source_models)
-        self.active_bundle = get_active_bundle(self.params, usbgpu=self.chestnut_present)
+        chestnut_present = self.sm['deviceState'].chestnutPresent
+        self.available_models = self.model_fetcher.get_available_bundles(chestnut_present)
+        if boot_ticks >= self.BOOT_SETTLE_TICKS:
+          validate_active_bundle(self.params, self.available_models, is_usbgpu=chestnut_present)
+        boot_ticks = min(boot_ticks + 1, self.BOOT_SETTLE_TICKS)
+        self.active_bundle = get_active_bundle(self.params)
 
-        if (ref_to_download := self.params.get("ModelManager_DownloadRef")) is not None:
-          if resolved := resolve_bundle_by_ref(ref_to_download, self.source_models):
-            model_to_download, source = resolved
+        if (index_to_download := self.params.get("ModelManager_DownloadIndex")) is not None:
+          if self.active_bundle and self.active_bundle.index == index_to_download:
+            self.params.remove("ModelManager_DownloadIndex")
+          elif model_to_download := next((model for model in self.available_models if model.index == index_to_download), None):
             try:
-              self.download(model_to_download, Paths.model_root(), source)
+              self.download(model_to_download, Paths.model_root())
             except Exception as e:
               cloudlog.exception(e)
             finally:
-              self.params.remove("ModelManager_DownloadRef")
+              self.params.remove("ModelManager_DownloadIndex")
               self.selected_bundle = None
 
         if self.params.get("ModelManager_ClearCache"):
@@ -299,14 +302,12 @@ class ModelManagerSP:
     Clears the model cache directory of all files except those in the active model bundle.
     """
 
-    # Get list of files used by both slots' selected bundles (either may become
-    # the truly active bundle depending on hardware availability)
+    # Get list of files used by active model bundle
     active_files = []
-    for source in ACTIVE_BUNDLE_KEYS:
-      if selected_bundle := get_selected_bundle(self.params, source):
-        for model in selected_bundle.models:
-          if hasattr(model, 'artifact') and model.artifact.fileName:
-            active_files.append(model.artifact.fileName)
+    if self.active_bundle is not None: # When the default model is active
+      for model in self.active_bundle.models:
+        if hasattr(model, 'artifact') and model.artifact.fileName:
+          active_files.append(model.artifact.fileName)
 
     # Remove all files except active ones (including their chunk files)
     model_dir = Paths.model_root()

openpilot/sunnypilot/models/tests/test_manager_download.py

@@ -11,7 +11,6 @@ import http.server
 import os
 import tempfile
 import threading
-import time
 import unittest
 from typing import Any
 from unittest import mock
@@ -24,8 +23,6 @@ from openpilot.common.test import OpenpilotTestCase
 from openpilot.common.file_chunker import get_chunk_name, get_manifest_path
 from openpilot.selfdrive.test.helpers import http_server_context
 from openpilot.sunnypilot.models import manager as manager_module
-from openpilot.sunnypilot.models.fetcher import ModelFetcher, get_cached_bundles
-from openpilot.sunnypilot.models.helpers import get_active_bundle, get_active_source, get_selected_bundle, resolve_bundle_by_ref
 from openpilot.sunnypilot.models.manager import ModelManagerSP
 
 CHUNK_BODIES = [b'A' * 5000, b'B' * 5000, b'C' * 3000]
@@ -106,7 +103,6 @@ class ManagerDownloadTestBase(OpenpilotTestCase):
     self.manager.selected_bundle = None
     self.manager.active_bundle = None
     self.manager.available_models = []
-    self.manager.chestnut_present = False
     self.manager._chunk_size = 1024
     self.manager._download_start_times = {}
 
@@ -253,85 +249,6 @@ class TestManagerDownload(ManagerDownloadTestBase):
         assert self.manager._download_start_times == {}
     self.run_with_server(body)
 
-  def test_download_ref_present_keeps_download_alive(self):
-    """A pending download request (DownloadRef set) must not be cancelled mid-transfer."""
-    def body():
-      artifact = self.make_artifact(chunked=True)
-      base_path = os.path.join(self.dest, artifact.fileName)
-      self.manager.params.get.side_effect = lambda key: b"ref" if key == "ModelManager_DownloadRef" else None
-      asyncio.run(self.manager._download_chunked(artifact.downloadUri.uri, base_path, artifact))
-      assert os.path.isfile(get_manifest_path(base_path))
-    self.run_with_server(body)
-
-  def test_cancellation_via_download_ref(self):
-    """Removing DownloadRef mid-transfer cancels the download."""
-    def body():
-      artifact = self.make_artifact(chunked=True)
-      base_path = os.path.join(self.dest, artifact.fileName)
-      checks = {"n": 0}
-
-      def get(key):
-        if key == "ModelManager_DownloadRef":
-          checks["n"] += 1
-          return b"ref" if checks["n"] <= 2 else None
-        return b"0"
-
-      self.manager.params.get.side_effect = get
-      with self.assertRaises(Exception) as ctx:
-        asyncio.run(self.manager._download_chunked(artifact.downloadUri.uri, base_path, artifact))
-      assert 'cancelled' in str(ctx.exception).lower()
-      assert not os.path.isfile(get_manifest_path(base_path))
-    self.run_with_server(body)
-
-  def _make_params_with_store(self):
-    params = mock.MagicMock()
-    store = {}
-
-    def get(key, *args, **kwargs):
-      return store.get(key, b"0")  # b"0" -> download not cancelled
-
-    def put(key, value, *args, **kwargs):
-      store[key] = value
-
-    params.get.side_effect = get
-    params.put.side_effect = put
-    return params, store
-
-  def test_download_writes_qcom_slot(self):
-    """A download resolved to the qcom source writes the qcom active bundle slot only."""
-    def body():
-      artifact = self.make_artifact(chunked=True)
-      self._bundle.ref = "test-ref"
-      self._bundle.minimumSelectorVersion = 17
-      params, store = self._make_params_with_store()
-      self.manager.params = params
-      asyncio.run(self.manager._download_bundle(self._bundle, self.dest, "qcom"))
-
-      assert "ModelManager_ActiveBundle" in store, "qcom download must write the qcom slot"
-      assert "ModelManager_ActiveBundleUSBGPU" not in store, "qcom download must not touch the usbgpu slot"
-      assert self.manager.selected_bundle.status == custom.ModelManagerSP.DownloadStatus.downloaded
-      assert self.manager.active_bundle is not None and self.manager.active_bundle.ref == "test-ref"
-      assert self.manager.active_bundle.status == custom.ModelManagerSP.DownloadStatus.downloaded
-      chunk_names = [get_chunk_name(artifact.fileName, i, len(artifact.chunks)) for i in range(len(artifact.chunks))]
-      missing = [c for c in chunk_names if not os.path.isfile(os.path.join(self.dest, c))]
-      assert missing == [], f"chunks missing from the cache: {missing}"
-    self.run_with_server(body)
-
-  def test_download_writes_usbgpu_slot(self):
-    """A download resolved to the usbgpu source writes the usbgpu active bundle slot only."""
-    def body():
-      self.make_artifact(chunked=True)
-      self._bundle.ref = "big-ref"
-      self._bundle.minimumSelectorVersion = 17
-      params, store = self._make_params_with_store()
-      self.manager.params = params
-      asyncio.run(self.manager._download_bundle(self._bundle, self.dest, "usbgpu"))
-
-      assert "ModelManager_ActiveBundleUSBGPU" in store, "usbgpu download must write the usbgpu slot"
-      assert "ModelManager_ActiveBundle" not in store, "usbgpu download must not touch the qcom slot"
-      assert self.manager.selected_bundle.status == custom.ModelManagerSP.DownloadStatus.downloaded
-    self.run_with_server(body)
-
 
 class TestManagerImports(OpenpilotTestCase):
   """Catches undeclared dependencies. aiohttp lived only in the AGNOS venv; 19.6 dropped
@@ -350,292 +267,6 @@ class TestManagerImports(OpenpilotTestCase):
     assert connect > 0 and read > 0, "requests defaults to no timeout; downloads would hang forever"
 
 
-class TestResolveBundleByRef(OpenpilotTestCase):
-  """A ref resolves to (bundle, source) across both hardware manifests. Refs are
-  unique per manifest and never overlap across sources, so a ref maps to exactly
-  one slot. Shared by the manager's download flow and the settings UI."""
-
-  @staticmethod
-  def _bundle(ref: str):
-    bundle = custom.ModelManagerSP.ModelBundle.new_message()
-    bundle.ref = ref
-    return bundle
-
-  def test_qcom_ref_resolves_to_qcom_slot(self):
-    small = self._bundle("small")
-    assert resolve_bundle_by_ref("small", {"qcom": [small], "usbgpu": []}) == (small, "qcom")
-
-  def test_usbgpu_ref_resolves_to_usbgpu_slot(self):
-    big = self._bundle("big")
-    assert resolve_bundle_by_ref("big", {"qcom": [], "usbgpu": [big]}) == (big, "usbgpu")
-
-  def test_unknown_ref_returns_none(self):
-    source_bundles = {"qcom": [self._bundle("small")], "usbgpu": []}
-    assert resolve_bundle_by_ref("nope", source_bundles) is None
-
-
-def manifest_bundle(short_name: str, ref: str, index: int = 0, is_big: bool = False) -> dict:
-  """Minimal manifest bundle dict, version-compatible (no chunks to avoid disk side effects).
-  Big (usbgpu) bundles carry `is_big: true` in the manifest JSON."""
-  return {
-    "index": index,
-    "short_name": short_name,
-    "display_name": short_name.upper(),
-    "generation": 1,
-    "environment": "release",
-    "runner": "tinygrad",
-    "is_big": is_big,
-    "minimum_selector_version": "17",
-    "ref": ref,
-    "models": [{
-      "type": "supercombo",
-      "artifact": {
-        "file_name": f"{short_name}.pkl",
-        "download_uri": {"url": f"https://example.com/{short_name}.pkl", "sha256": "s"},
-      },
-    }],
-  }
-
-
-def fresh_sync_time() -> int:
-  return int(time.monotonic() * 1e9)
-
-
-class TestModelFetcherSources(OpenpilotTestCase):
-  """Both manifests are always maintained: get_bundles_for_source exposes either
-  source by name, and active_source picks which one matches the attached hardware."""
-
-  def _make_params(self, qcom_manifest, usbgpu_manifest):
-    params = mock.MagicMock()
-
-    def get(key):
-      if key == "ModelManager_ModelsCache":
-        return qcom_manifest
-      if key == "ModelManager_ModelsCache_USBGPU":
-        return usbgpu_manifest
-      if key in ("ModelManager_LastSyncTime", "ModelManager_LastSyncTime_USBGPU"):
-        return fresh_sync_time()
-      return None
-
-    params.get.side_effect = get
-    return params
-
-  def test_active_source_follows_chestnut_presence(self):
-    assert ModelFetcher.active_source(False) == "qcom"
-    assert ModelFetcher.active_source(True) == "usbgpu"
-
-  def test_get_bundles_for_source_returns_each_source(self):
-    params = self._make_params({"bundles": [manifest_bundle("small", "aaa")]},
-                               {"bundles": [manifest_bundle("big", "bbb", is_big=True)]})
-    fetcher = ModelFetcher(params)
-    assert [bundle.ref for bundle in fetcher.get_bundles_for_source("qcom")] == ["aaa"]
-    assert [bundle.ref for bundle in fetcher.get_bundles_for_source("usbgpu")] == ["bbb"]
-
-  def test_get_bundles_for_source_unknown(self):
-    assert ModelFetcher(mock.MagicMock()).get_bundles_for_source("bogus") == []
-
-  def test_get_cached_bundles_parses_source(self):
-    params = self._make_params({"bundles": [manifest_bundle("small", "aaa")]},
-                               {"bundles": [manifest_bundle("big", "bbb", is_big=True)]})
-    qcom_bundles = get_cached_bundles(params, "qcom")
-    usbgpu_bundles = get_cached_bundles(params, "usbgpu")
-    assert [b.ref for b in qcom_bundles] == ["aaa"]
-    assert [b.ref for b in usbgpu_bundles] == ["bbb"]
-    assert qcom_bundles[0].displayName == "SMALL"
-
-  def test_get_cached_bundles_empty_when_missing(self):
-    params = mock.MagicMock()
-    params.get.return_value = None
-    assert get_cached_bundles(params, "qcom") == []
-    assert get_cached_bundles(params, "usbgpu") == []
-
-  def test_get_cached_bundles_unknown_source(self):
-    assert get_cached_bundles(mock.MagicMock(), "bogus") == []
-
-  def test_active_json_has_both_urls(self):
-    params = mock.MagicMock()
-    ModelFetcher(params)
-    active_json_calls = [call for call in params.put.call_args_list if call.args[0] == "ModelManager_ActiveJson"]
-    assert active_json_calls, "expected ModelManager_ActiveJson to be written"
-    assert active_json_calls[-1].args[1] == {
-      "qcom": ModelFetcher.MODEL_URL,
-      "usbgpu": ModelFetcher.MODEL_URL_USBGPU,
-    }
-
-
-
-class TestSourceCacheIntegrity(OpenpilotTestCase):
-  """Each source's cached manifest must contain only that source's models; the
-  `is_big` flag in the JSON marks the big (usbgpu) models. A mismatched cache is
-  legacy data from before the per-source split (the active manifest was cached
-  under the unsuffixed key regardless of hardware) and is refetched. This
-  replaces the old one-time bundle migration."""
-
-  def _make_params(self, qcom_manifest, usbgpu_manifest):
-    params = mock.MagicMock()
-
-    def get(key):
-      if key == "ModelManager_ModelsCache":
-        return qcom_manifest
-      if key == "ModelManager_ModelsCache_USBGPU":
-        return usbgpu_manifest
-      if key in ("ModelManager_LastSyncTime", "ModelManager_LastSyncTime_USBGPU"):
-        return fresh_sync_time()
-      return None
-
-    params.get.side_effect = get
-    return params
-
-  def _fetched(self, *bundles):
-    return ModelFetcher(mock.MagicMock()).model_parser.parse_models({"bundles": list(bundles)})
-
-  def test_qcom_cache_with_big_models_is_refetched(self):
-    """Legacy: the unsuffixed cache holds the big manifest. is_big confirms it is
-    the wrong set for qcom, so a fresh fetch replaces it."""
-    params = self._make_params({"bundles": [manifest_bundle("big", "bbb", is_big=True)]},
-                               {"bundles": [manifest_bundle("big2", "ccc", is_big=True)]})
-    fetcher = ModelFetcher(params)
-    fetched = self._fetched(manifest_bundle("small", "aaa"))
-    with mock.patch.object(fetcher, "_fetch_and_cache_models", return_value=fetched):
-      bundles = fetcher.get_bundles_for_source("qcom")
-    assert [bundle.ref for bundle in bundles] == ["aaa"]
-
-  def test_usbgpu_cache_without_big_models_is_refetched(self):
-    params = self._make_params({"bundles": [manifest_bundle("small", "aaa")]},
-                               {"bundles": [manifest_bundle("big2", "ccc")]})
-    fetcher = ModelFetcher(params)
-    fetched = self._fetched(manifest_bundle("big", "bbb", is_big=True))
-    with mock.patch.object(fetcher, "_fetch_and_cache_models", return_value=fetched):
-      bundles = fetcher.get_bundles_for_source("usbgpu")
-    assert [bundle.ref for bundle in bundles] == ["bbb"]
-
-  def test_matching_caches_are_used_without_fetch(self):
-    params = self._make_params({"bundles": [manifest_bundle("small", "aaa")]},
-                               {"bundles": [manifest_bundle("big", "bbb", is_big=True)]})
-    fetcher = ModelFetcher(params)
-    with mock.patch.object(fetcher, "_fetch_and_cache_models", side_effect=AssertionError("cache should be used")):
-      assert [bundle.ref for bundle in fetcher.get_bundles_for_source("qcom")] == ["aaa"]
-      assert [bundle.ref for bundle in fetcher.get_bundles_for_source("usbgpu")] == ["bbb"]
-
-  def test_stale_version_cache_is_refetched(self):
-    """A source-matching cache whose bundles are all filtered by the selector version
-    check parses to zero valid bundles; it is stale (e.g. an old manifest) and must be
-    refetched instead of silently returning an empty list forever."""
-    stale = manifest_bundle("small", "aaa")
-    stale["minimum_selector_version"] = "16"
-    params = self._make_params({"bundles": [stale]},
-                               {"bundles": [manifest_bundle("big", "bbb", is_big=True)]})
-    fetcher = ModelFetcher(params)
-    fetched = self._fetched(manifest_bundle("small2", "ddd"))
-    with mock.patch.object(fetcher, "_fetch_and_cache_models", return_value=fetched) as fetch:
-      bundles = fetcher.get_bundles_for_source("qcom")
-    fetch.assert_called_once_with("qcom")
-    assert [bundle.ref for bundle in bundles] == ["ddd"]
-
-  def test_corrupt_cache_is_refetched(self):
-    """A cache that fails to parse (e.g. truncated/foreign JSON) must trigger a
-    refetch instead of raising every loop and never recovering."""
-    corrupt = {"bundles": [{"short_name": "broken"}]}  # missing required fields
-    params = self._make_params(corrupt, {"bundles": [manifest_bundle("big", "bbb", is_big=True)]})
-    fetcher = ModelFetcher(params)
-    fetched = self._fetched(manifest_bundle("small", "aaa"))
-    with mock.patch.object(fetcher, "_fetch_and_cache_models", return_value=fetched) as fetch:
-      bundles = fetcher.get_bundles_for_source("qcom")
-    fetch.assert_called_once_with("qcom")
-    assert [bundle.ref for bundle in bundles] == ["aaa"]
-
-
-class TestActiveBundleSelection(OpenpilotTestCase):
-  """The effective active bundle follows the hardware: the usbgpu slot wins when a GPU
-  is present and compiled, otherwise the qcom slot. Each slot keeps its own selection."""
-
-  @staticmethod
-  def _raw_bundle(ref: str) -> dict:
-    bundle = custom.ModelManagerSP.ModelBundle.new_message()
-    bundle.ref = ref
-    bundle.minimumSelectorVersion = 17
-    return bundle.to_dict()
-
-  def _params(self, qcom=None, usbgpu=None):
-    params = mock.MagicMock()
-
-    def get(key, *args, **kwargs):
-      if key == "ModelManager_ActiveBundle":
-        return qcom
-      if key == "ModelManager_ActiveBundleUSBGPU":
-        return usbgpu
-      return None
-
-    params.get.side_effect = get
-    return params
-
-  def test_selected_bundle_is_per_slot(self):
-    params = self._params(qcom=self._raw_bundle("small"), usbgpu=self._raw_bundle("big"))
-    assert get_selected_bundle(params, "qcom").ref == "small"
-    assert get_selected_bundle(params, "usbgpu").ref == "big"
-
-  def test_no_gpu_uses_qcom_slot(self):
-    params = self._params(qcom=self._raw_bundle("small"), usbgpu=self._raw_bundle("big"))
-    with mock.patch("openpilot.sunnypilot.models.helpers.usbgpu_present", return_value=False):
-      assert get_active_bundle(params).ref == "small"
-
-  def test_gpu_uses_usbgpu_slot(self):
-    params = self._params(qcom=self._raw_bundle("small"), usbgpu=self._raw_bundle("big"))
-    with mock.patch("openpilot.sunnypilot.models.helpers.usbgpu_present", return_value=True):
-      assert get_active_bundle(params).ref == "big"
-
-  def test_gpu_without_big_selection_falls_back_to_small(self):
-    params = self._params(qcom=self._raw_bundle("small"), usbgpu=None)
-    with mock.patch("openpilot.sunnypilot.models.helpers.usbgpu_present", return_value=True):
-      assert get_active_bundle(params).ref == "small"
-
-
-class TestEffectiveSource(OpenpilotTestCase):
-  """One gate decides the active source. With no flags it is runtime truth (GPU
-  attached); display callers (mici) pass the ui_state flags, which additionally
-  require the big model to be loading, active, or the device offroad. The active
-  bundle is simply the selected bundle of that source."""
-
-  @staticmethod
-  def _raw_bundle(ref: str) -> dict:
-    bundle = custom.ModelManagerSP.ModelBundle.new_message()
-    bundle.ref = ref
-    bundle.minimumSelectorVersion = 17
-    return bundle.to_dict()
-
-  def test_runtime_no_gpu(self):
-    with mock.patch("openpilot.sunnypilot.models.helpers.usbgpu_present", return_value=False):
-      assert get_active_source() == "qcom"
-
-  def test_runtime_gpu_present(self):
-    with mock.patch("openpilot.sunnypilot.models.helpers.usbgpu_present", return_value=True):
-      assert get_active_source() == "usbgpu"
-
-  def test_display_offroad_gpu_present_shows_big(self):
-    assert get_active_source(usbgpu=True, usbgpu_active=False, usbgpu_loading=False, offroad=True) == "usbgpu"
-
-  def test_display_onroad_gpu_loading_shows_big(self):
-    assert get_active_source(usbgpu=True, usbgpu_active=False, usbgpu_loading=True, offroad=False) == "usbgpu"
-
-  def test_display_onroad_gpu_active_shows_big(self):
-    assert get_active_source(usbgpu=True, usbgpu_active=True, usbgpu_loading=False, offroad=False) == "usbgpu"
-
-  def test_display_onroad_gpu_idle_shows_small(self):
-    assert get_active_source(usbgpu=True, usbgpu_active=False, usbgpu_loading=False, offroad=False) == "qcom"
-
-  def test_display_active_none_is_idle(self):
-    assert get_active_source(usbgpu=True, usbgpu_active=None, usbgpu_loading=False, offroad=False) == "qcom"
-
-  def test_active_bundle_follows_source(self):
-    params = mock.MagicMock()
-    params.get.side_effect = lambda key: {"ModelManager_ActiveBundle": self._raw_bundle("small"),
-                                          "ModelManager_ActiveBundleUSBGPU": self._raw_bundle("big")}.get(key)
-    with mock.patch("openpilot.sunnypilot.models.helpers.usbgpu_present", return_value=False):
-      assert get_active_bundle(params).ref == "small"
-    assert get_selected_bundle(params, get_active_source(usbgpu=True, usbgpu_active=False,
-                                                         usbgpu_loading=False, offroad=True)).ref == "big"
-
-
 @unittest.skipUnless(os.environ.get('RUN_INTEGRATION_TESTS'), 'requires external network')
 class TestLiveModelManifest(OpenpilotTestCase):
   """Every artifact and chunk URL in the published manifest must resolve."""

openpilot/sunnypilot/sunnylink/statsd.py

@@ -65,7 +65,6 @@ def sp_stats(end_event):
     'MadsSteeringMode',
     'MadsUnifiedEngagementMode',
     'ModelManager_ActiveBundle',
-    'ModelManager_ActiveBundleUSBGPU',
     'ModelManager_Favs',
     'EnableSunnylinkUploader',
     'SunnylinkEnabled',

release/ci/model_generator.py

@@ -136,7 +136,7 @@ def generate_chunked_model(driving_pkl: Path) -> dict:
 
 
 def create_metadata_json(models: list, output_dir: Path, custom_name=None, short_name=None, is_20hz=False, upstream_branch="unknown",
-                         onnx_sha256=None) -> None:
+                         onnx_sha256=None, is_big=False) -> None:
   bundle_json = {
     "short_name": short_name,
     "display_name": custom_name or upstream_branch,
@@ -149,6 +149,7 @@ def create_metadata_json(models: list, output_dir: Path, custom_name=None, short
     "generation": "-1",
     "build_time": datetime.now(UTC).strftime("%Y-%m-%dT%H:%M:%SZ"),
     "overrides": {},
+    "is_big": is_big,
     "models": models,
   }
 
@@ -186,6 +187,8 @@ if __name__ == "__main__":
     print(f"No driving_tinygrad.pkl found in {_output_dir}", file=sys.stderr)
     sys.exit(1)
 
+  is_big = _driving_pkl.name.startswith('big_')
+
   if _pkl:
     new_pkl = _output_dir / f"driving_{_pkl}_tinygrad.pkl"
     if not new_pkl.exists():
@@ -196,4 +199,4 @@ if __name__ == "__main__":
   _model_metadata = generate_chunked_model(_driving_pkl)
   _onnx_sha256 = _hash_onnx_files(Path(args.model_dir))
   create_metadata_json([_model_metadata], _output_dir, args.custom_name, _short_name, args.is_20hz, args.upstream_branch,
-                       onnx_sha256=_onnx_sha256)
+                       onnx_sha256=_onnx_sha256, is_big=is_big)

release/ci/publish.sh

@@ -47,7 +47,7 @@ git rm -rf $OUTPUT_DIR/.git || true # Doing cleanup, but it might fail if the .g
 git remote remove origin || true # ensure cleanup
 git remote add origin $GIT_ORIGIN
 #git push origin -d $DEV_BRANCH || true # Ensuring we delete the remote branch if it exists as we are wiping it out
-git fetch origin $DEV_BRANCH || (git checkout -b $DEV_BRANCH && git commit --allow-empty -m "sunnypilot v$VERSION release" && git push -u origin $DEV_BRANCH)
+git fetch --depth 1 origin $DEV_BRANCH || (git checkout -b $DEV_BRANCH && git commit --allow-empty -m "sunnypilot v$VERSION release" && git push -u origin $DEV_BRANCH)
 
 echo "[-] committing version $VERSION T=$SECONDS"
 git add -f .