ffs

# Conflicts:
#	openpilot/selfdrive/ui/mici/onroad/model_renderer.py
#	openpilot/sunnypilot/modeld_v2/modeld.py

.github/workflows/test_models.yml

@@ -3,62 +3,9 @@ on:
   pull_request:
     paths:
       - 'tinygrad_repo'
-      - 'openpilot/sunnypilot/modeld_v2/**'
   workflow_dispatch:
 
-env:
-  CI: 1
-  GIT_CONFIG_COUNT: 1
-  GIT_CONFIG_KEY_0: lfs.fetchexclude
-  GIT_CONFIG_VALUE_0: openpilot/selfdrive/modeld/models/big_driving_tinygrad.pkl
-
 jobs:
-  plain-artifact:
-    name: Plain artifact round trip and pickle converter
-    runs-on: ubuntu-24.04
-    env:
-      PYTHONPATH: ${{ github.workspace }}/tinygrad_repo:${{ github.workspace }}
-      TINYGRAD_TESTS: 1
-    steps:
-      - uses: actions/checkout@v7
-      - run: ./tools/op.sh setup
-      - name: Build openpilot
-        run: scons -j$(nproc)
-      - name: Compile, load, cache and fuse a model with the pinned tinygrad
-        env:
-          DEV: CPU
-        run: tools/op.sh test -v openpilot/sunnypilot/modeld_v2/tests/test_plain_artifact.py
-      - name: Install LLVM 20 and ROCm comgr for the amd mock, as tinygrad_repo/.github/actions/setup-tinygrad does
-        run: |
-          . /etc/os-release
-          curl -fsSL https://apt.llvm.org/llvm-snapshot.gpg.key | sudo tee /etc/apt/trusted.gpg.d/apt.llvm.org.asc > /dev/null
-          echo "deb http://apt.llvm.org/$VERSION_CODENAME/ llvm-toolchain-$VERSION_CODENAME-20 main" | sudo tee /etc/apt/sources.list.d/llvm.list
-          sudo mkdir -p /etc/apt/keyrings
-          curl -fsSL https://repo.radeon.com/rocm/rocm.gpg.key | gpg --dearmor | sudo tee /etc/apt/keyrings/rocm.gpg > /dev/null
-          echo "deb [arch=amd64 signed-by=/etc/apt/keyrings/rocm.gpg] https://repo.radeon.com/rocm/apt/7.1 $VERSION_CODENAME main" | sudo tee /etc/apt/sources.list.d/rocm.list
-          printf 'Package: *\nPin: release o=repo.radeon.com\nPin-Priority: 600\n' | sudo tee /etc/apt/preferences.d/rocm-pin-600
-          sudo apt-get -qq update && sudo apt-get -qq install -y --no-install-recommends libllvm20 clang-20 lld-20 comgr
-          printf '/opt/rocm/lib\n/opt/rocm/lib64\n' | sudo tee /etc/ld.so.conf.d/rocm.conf && sudo ldconfig
-          echo "/usr/lib/llvm-20/bin" >> "$GITHUB_PATH"
-      - name: Convert a pickled USB+AMD jit and replay it under tinygrad's amd mock
-        env:
-          DEV: MOCKUSB+AMD
-          CHECK_OOB: 0
-          GMMU: 0
-        run: tools/op.sh test -v openpilot/sunnypilot/modeld_v2/tests/test_convert_upstream_pkl.py
-      - name: Where tinygrad moved, for the helper or failure point named above
-        if: failure() && github.event_name == 'pull_request'
-        run: |
-          git fetch -q --depth=1 origin "${{ github.base_ref }}"
-          old=$(git rev-parse "origin/${{ github.base_ref }}:tinygrad_repo") new=$(git rev-parse HEAD:tinygrad_repo)
-          git -C tinygrad_repo fetch -q origin "$old" || true
-          echo "tinygrad_repo $old -> $new, in what helpers.py and plain_artifact_compiler.py read:"
-          git -C tinygrad_repo diff "$old" "$new" -- tinygrad/uop/ops.py tinygrad/engine/jit.py tinygrad/engine/realize.py tinygrad/device.py \
-            tinygrad/helpers.py tinygrad/dtype.py tinygrad/renderer/__init__.py
-          echo "and in what convert_upstream_pkl.py decodes:"
-          git -C tinygrad_repo diff --stat "$old" "$new" -- tinygrad/runtime/autogen/am/pm4_nv.py tinygrad/runtime/autogen/amd_gpu.py
-          git -C tinygrad_repo diff "$old" "$new" -- tinygrad/runtime/support/hcq2.py tinygrad/runtime/support/usb.py tinygrad/runtime/ops_amd.py
-
   generate-matrix:
     runs-on: ubuntu-latest
     outputs:

openpilot/cereal/custom.capnp

@@ -138,9 +138,6 @@ struct ModelManagerSP @0xaedffd8f31e7b55d {
     status @0 :DownloadStatus;
     progress @1 :Float32;
     eta @2 :UInt32;
-    speed @3 :Float32;
-    canceling @4 :Bool;
-    resuming @5 :Bool;
   }
 
   struct Chunk {
@@ -468,6 +465,10 @@ struct ModelDataV2SP @0xa1680744031fdb2d {
   laneTurnDirection @0 :TurnDirection;
   leftLaneChangeEdgeBlock @1 :Bool;
   rightLaneChangeEdgeBlock @2 :Bool;
+  lanefulCurvature @3 :Float32;
+  lanefulTrust @4 :Float32;
+  modelCurvature @5 :Float32;
+  lanefulGoingAround @6 :Bool;
 
   enum TurnDirection {
     none @0;

openpilot/cereal/services.py

@@ -94,7 +94,7 @@ _services: dict[str, tuple] = {
   "carControlSP": (True, 100., 10),
   "carStateSP": (True, 100., 10),
   "liveMapDataSP": (True, 1., 1),
-  "modelDataV2SP": (True, 20., None, QueueSize.BIG),
+  "modelDataV2SP": (True, 20., 10, QueueSize.BIG),
   "liveLocationKalman": (True, 20.),
 
   # debug

openpilot/common/params_keys.h

@@ -256,6 +256,7 @@ inline static std::unordered_map<std::string, ParamKeyAttributes> keys = {
     {"LagdValueCache", {PERSISTENT, FLOAT, "0.2"}},
     {"LaneTurnDesire", {PERSISTENT | BACKUP, BOOL, "0"}},
     {"LaneTurnValue", {PERSISTENT | BACKUP, FLOAT, "19.0"}},
+    {"Laneful", {PERSISTENT | BACKUP, BOOL, "0"}},
     {"PlanplusControl", {PERSISTENT | BACKUP, FLOAT, "1.0"}},
 
     // mapd

openpilot/selfdrive/ui/mici/onroad/augmented_road_view.py

@@ -206,6 +206,8 @@ class AugmentedRoadView(CameraView):
   def _handle_mouse_release(self, mouse_pos: MousePos):
     # Don't trigger click callback if bookmark was triggered
     if not self._bookmark_icon.interacting():
+      if self._model_renderer.laneful.handle_tap(mouse_pos):
+        return
       super()._handle_mouse_release(mouse_pos)
 
   def _render(self, _):

openpilot/selfdrive/ui/mici/onroad/model_renderer.py

@@ -141,6 +141,7 @@ class ModelRenderer(Widget, ModelRendererSP):
     if ui_state.status != UIStatus.DISENGAGED:
       self._draw_lane_lines()
       self._draw_path()
+      self.laneful.draw(self._rect)
 
     if render_lead_indicator:
       self._update_leads(sm)
@@ -219,6 +220,7 @@ class ModelRenderer(Widget, ModelRendererSP):
     # Update road edges using raw points
     for road_edge in self._road_edges:
       road_edge.projected_points = self._map_line_to_polygon(road_edge.raw_points, line_width_factor, 0.0, max_idx)
+    self.laneful.update(self, max_idx)
 
     # Update path using raw points
     if lead and lead.present:

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

@@ -235,8 +235,6 @@ class ModelsLayout(Widget):
     progress = sum(p.progress for p in progresses) / len(progresses)
     ds = custom.ModelManagerSP.DownloadStatus
 
-    if any(p.canceling for p in progresses):
-      return {"name": name, "downloading": True, "progress": progress, "status_text": tr("canceling...")}
     if ds.failed in statuses:
       # close.png is authored black and a tint cannot lift it, hence close2
       return {"name": name, "status_text": tr("download failed"), "text_color": rl.RED, "icon": "icons/close2.png"}

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

@@ -0,0 +1,21 @@
+"""
+Copyright (c) 2021-, 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.mici.widgets.button import BigParamControl
+from openpilot.system.ui.widgets.scroller import NavScroller
+
+
+class LanefulLayoutMici(NavScroller):
+  def __init__(self):
+    super().__init__()
+    self._toggle = BigParamControl("laneful", "Laneful",
+                                   description="Keeps the car centered in its lane.\n" +
+                                               "Leans on the lane lines when they are clear, drives laneless when they are not.")
+    self._scroller.add_widget(self._toggle)
+
+  def show_event(self):
+    super().show_event()
+    self._toggle.refresh()

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

@@ -251,12 +251,11 @@ class ModelsLayoutMici(NavScroller):
       self.current_model_info.info_text.set_text(tr("download failed"))
 
     elif manager.selectedBundle and manager.selectedBundle.status == custom.ModelManagerSP.DownloadStatus.downloading:
-      self.cancel_download_btn.set_visible(ui_state.params.get("ModelManager_DownloadRef") is not None)
+      self.cancel_download_btn.set_visible(True)
       device.set_override_interactive_timeout(5)
       progress = 0.0
       count = 0
       verifying = False
-      canceling = False
       for model in manager.selectedBundle.models:
         count += 1
         p = model.artifact.downloadProgress
@@ -264,13 +263,11 @@ class ModelsLayoutMici(NavScroller):
                         custom.ModelManagerSP.DownloadStatus.verifying):
           progress += p.progress
           verifying = verifying or p.status == custom.ModelManagerSP.DownloadStatus.verifying
-          canceling = canceling or p.canceling
         elif p.status in (custom.ModelManagerSP.DownloadStatus.downloaded,
                           custom.ModelManagerSP.DownloadStatus.cached):
           progress += 100.0
 
-      header = tr("canceling...") if canceling else tr("verifying") if verifying else tr("downloading")
-      self.current_model_info.current_model_header.set_text(header)
+      self.current_model_info.current_model_header.set_text(tr("verifying") if verifying else tr("downloading"))
       self.cancel_download_btn.set_text(tr("cancel verification") if verifying else tr("cancel download"))
       self.current_model_info.current_model_header._shimmer = True
       name_text = manager.selectedBundle.internalName.lower()

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

@@ -11,6 +11,7 @@ from openpilot.selfdrive.ui.mici.widgets.button import BigCircleButton
 from openpilot.selfdrive.ui.mici.widgets.dialog import BigConfirmationDialog, BigDialog
 from openpilot.selfdrive.ui.sunnypilot.mici.layouts.sunnylink import SunnylinkLayoutMici
 from openpilot.selfdrive.ui.sunnypilot.mici.layouts.models import ModelsLayoutMici
+from openpilot.selfdrive.ui.sunnypilot.mici.layouts.laneful import LanefulLayoutMici
 from openpilot.selfdrive.ui.ui_state import ui_state
 from openpilot.system.ui.lib.application import gui_app, FontWeight
 from openpilot.system.ui.lib.multilang import tr
@@ -50,6 +51,10 @@ class SettingsLayoutSP(OP.SettingsLayout):
     models_btn = SettingsBigButton(tr("models"), "", gui_app.texture("../../sunnypilot/selfdrive/assets/offroad/icon_models.png", ICON_SIZE, ICON_SIZE))
     models_btn.set_click_callback(lambda: gui_app.push_widget(models_panel))
 
+    laneful_panel = LanefulLayoutMici()
+    laneful_btn = SettingsBigButton(tr("laneful"), "", gui_app.texture("icons_mici/settings/device/lkas.png", ICON_SIZE, ICON_SIZE))
+    laneful_btn.set_click_callback(lambda: gui_app.push_widget(laneful_panel))
+
     # onroad: enable button sits at the front (left of toggles)
     self._enable_offroad_btn_onroad = BigCircleButton(self.icon_offroad_enable, red=True)
     self._enable_offroad_btn_onroad.set_click_callback(lambda: self._handle_always_offroad(True))
@@ -67,7 +72,8 @@ class SettingsLayoutSP(OP.SettingsLayout):
     items = self._scroller._items.copy()
 
     items.insert(1, models_btn)
-    items.insert(5, sunnylink_btn)
+    items.insert(2, laneful_btn)
+    items.insert(6, sunnylink_btn)
 
     # front slots (only one ever visible at a time): exit-always-offroad, then enable-onroad
     items.insert(0, self._enable_offroad_btn_onroad)

openpilot/selfdrive/ui/sunnypilot/mici/onroad/laneful.py

@@ -0,0 +1,117 @@
+"""
+Copyright (c) 2021-, 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.
+
+Laneful visuals: cyan lane-center target, thin white "after" path (model path bent by laneful's nudge),
+and a top-center readout of the pull, from the curvature modeld publishes in modelDataV2SP.lanefulCurvature.
+"""
+import numpy as np
+import pyray as rl
+from openpilot.common.filter_simple import FirstOrderFilter
+from openpilot.common.realtime import DT_MDL
+from openpilot.selfdrive.ui.ui_state import ui_state
+from openpilot.sunnypilot.modeld_v2.laneful import LOOKAHEAD_TIME, MIN_LOOKAHEAD, MAX_ERROR
+from openpilot.system.ui.lib.application import gui_app, FontWeight
+from openpilot.system.ui.lib.shader_polygon import draw_polygon
+from openpilot.system.ui.lib.text_measure import measure_text_cached
+
+CENTER_COLOR = (0, 200, 255)
+AFTER_COLOR = (255, 255, 255)
+
+
+class LanefulRenderer:
+  def __init__(self):
+    self._center_points = np.empty((0, 2), dtype=np.float32)
+    self._after_points = np.empty((0, 2), dtype=np.float32)
+    self._trust = 0.0
+    self._font = gui_app.font(FontWeight.BOLD)
+    # smoothed copies for the readout so the numbers don't flicker
+    self._pull_display = FirstOrderFilter(0.0, 0.5, DT_MDL)
+    self._trust_display = FirstOrderFilter(0.0, 0.5, DT_MDL)
+    self._alpha = FirstOrderFilter(0.0, 0.3, DT_MDL) # fades that hoe
+    self._readout_rect: rl.Rectangle | None = None
+    self._settings_page = None
+
+  def update(self, renderer, max_idx: int) -> None:
+    """Called from the model renderer's update with its lane lines and path already in raw points."""
+    laneful_curvature = ui_state.sm['modelDataV2SP'].lanefulCurvature
+    self._alpha.update(float(laneful_curvature != 0.0))
+
+    left, right = renderer._lane_lines[1].raw_points, renderer._lane_lines[2].raw_points
+    stds = list(ui_state.sm['modelV2'].laneLineStds)
+    if self._alpha.x < 0.01 or len(left) == 0 or len(right) != len(left) or len(stds) < 3:
+      self._center_points = np.empty((0, 2), dtype=np.float32)
+      self._after_points = np.empty((0, 2), dtype=np.float32)
+      return
+
+    probs = renderer._lane_line_probs
+    l_prob = float(probs[1] * np.interp(stds[1], [0.15, 0.3], [1.0, 0.0]))
+    r_prob = float(probs[2] * np.interp(stds[2], [0.15, 0.3], [1.0, 0.0]))
+    width = np.clip(right[:, 1] - left[:, 1], 2.8, 4.5) if l_prob * r_prob > 0.5 else 3.7
+    center = left.copy()
+    center[:, 1] = (l_prob * (left[:, 1] + width / 2) + r_prob * (right[:, 1] - width / 2)) / (l_prob + r_prob + 1e-4)
+    self._trust = l_prob + r_prob - l_prob * r_prob
+    self._center_points = renderer._map_line_to_polygon(center, 0.1, 0.0, max_idx)
+
+    # "after" path: model path bent by laneful's curvature, ending at the lookahead
+    path = renderer._path.raw_points
+    lookahead = max(ui_state.sm['carState'].vEgo * LOOKAHEAD_TIME, MIN_LOOKAHEAD)
+    self._pull_display.update(laneful_curvature * lookahead ** 2 / 2)  # how far laneful moves the car at the lookahead
+    self._trust_display.update(self._trust)
+    after = path.copy()
+    after[:, 1] += laneful_curvature * path[:, 0] ** 2 / 2
+    self._after_points = renderer._map_line_to_polygon(after, 0.15, renderer._path_offset_z,
+                                                       renderer._get_path_length_idx(path[:, 0], lookahead))
+
+  def _color(self, rgb, alpha: float) -> rl.Color:
+    return rl.Color(*rgb, int(alpha * self._alpha.x))
+
+  def draw(self, rect: rl.Rectangle) -> None:
+    if self._center_points.size and self._trust > 0.05:
+      draw_polygon(rect, self._center_points, self._color(CENTER_COLOR, np.clip(self._trust, 0.2, 1.0) * 255))
+    self._readout_rect = None
+    if self._after_points.size:
+      draw_polygon(rect, self._after_points, self._color(AFTER_COLOR, 200))
+      self._draw_readout(rect)
+
+  def handle_tap(self, pos) -> bool:
+    """Tapping the readout opens the laneful settings page. Returns True if the tap was consumed."""
+    r = self._readout_rect
+    if r is None or not (r.x - 20 <= pos.x <= r.x + r.width + 20 and r.y - 20 <= pos.y <= r.y + r.height + 20):
+      return False
+    if self._settings_page is None:
+      from openpilot.selfdrive.ui.sunnypilot.mici.layouts.laneful import LanefulLayoutMici
+      self._settings_page = LanefulLayoutMici()
+    gui_app.push_widget(self._settings_page)
+    return True
+
+  def _draw_readout(self, rect: rl.Rectangle) -> None:
+    """Top-center pill: pull toward lane center in cm at the lookahead, arrow = side,
+    bar grows from center toward the pull (full at the cap), brighter with more lane line trust."""
+    pull, trust = self._pull_display.x, self._trust_display.x
+    w, h = 190, 76
+    x, y = rect.x + (rect.width - w) / 2, rect.y + 10
+    cx, cy = x + w / 2, y + 30
+    self._readout_rect = rl.Rectangle(x, y, w, h)
+    rl.draw_rectangle_rounded(self._readout_rect, 0.5, 12, self._color((0, 0, 0), 170))
+
+    text = f"{abs(pull) * 100:.0f}"
+    text_w = measure_text_cached(self._font, text, 44, 0).x
+    rl.draw_text_ex(self._font, text, rl.Vector2(cx - text_w / 2, cy - 24), 44, 0, self._color((255, 255, 255), 255))
+
+    active = self._color(CENTER_COLOR, np.clip(abs(pull) / 0.1, 0.0, 1.0) * 255)
+    idle = self._color((255, 255, 255), 40)
+    lx, rx = x + 18, x + w - 18
+    rl.draw_triangle(rl.Vector2(lx, cy), rl.Vector2(lx + 16, cy + 12), rl.Vector2(lx + 16, cy - 12), active if pull < 0 else idle)
+    rl.draw_triangle(rl.Vector2(rx - 16, cy - 12), rl.Vector2(rx - 16, cy + 12), rl.Vector2(rx, cy), active if pull > 0 else idle)
+
+    bar = rl.Rectangle(x + 24, y + h - 16, w - 48, 6)
+    rl.draw_rectangle_rounded(bar, 1.0, 6, self._color((255, 255, 255), 40))
+    rl.draw_rectangle(int(cx - 1), int(bar.y - 2), 2, int(bar.height + 4), self._color((255, 255, 255), 120))
+    fill = bar.width / 2 * float(np.clip(abs(pull) / MAX_ERROR, 0.0, 1.0))
+    if fill > 1:
+      fill_x = cx if pull > 0 else cx - fill
+      rl.draw_rectangle_rounded(rl.Rectangle(fill_x, bar.y, fill, bar.height), 1.0, 6,
+                                self._color(CENTER_COLOR, np.clip(0.3 + 0.7 * trust, 0.0, 1.0) * 255))

openpilot/selfdrive/ui/sunnypilot/mici/onroad/model_renderer.py

@@ -6,6 +6,7 @@ See the LICENSE.md file in the root directory for more details.
 """
 import pyray as rl
 from openpilot.selfdrive.ui.ui_state import UIStatus
+from openpilot.selfdrive.ui.sunnypilot.mici.onroad.laneful import LanefulRenderer
 from openpilot.selfdrive.ui.sunnypilot.onroad.rainbow_path import RainbowPath
 
 LANE_LINE_COLORS_SP = {
@@ -17,3 +18,4 @@ LANE_LINE_COLORS_SP = {
 class ModelRendererSP:
   def __init__(self):
     self.rainbow_path = RainbowPath()
+    self.laneful = LanefulRenderer()

openpilot/selfdrive/ui/sunnypilot/ui_state.py

@@ -36,7 +36,7 @@ class UIStateSP:
     self.is_sp_release: bool = self.params.get_bool("IsReleaseSpBranch")
     self.sm_services_ext = [
       "modelManagerSP", "selfdriveStateSP", "longitudinalPlanSP", "backupManagerSP",
-      "lateralTorqueParameters", "carStateSP", "liveMapDataSP", "carParamsSP", "lateralDelay"
+      "lateralTorqueParameters", "carStateSP", "liveMapDataSP", "carParamsSP", "lateralDelay", "modelDataV2SP"
     ]
 
     self.sunnylink_state = SunnylinkState()

openpilot/sunnypilot/modeld_v2/convert_upstream_pkl.py

@@ -7,7 +7,6 @@ See the LICENSE.md file in the root directory for more details.
 """
 import argparse
 import dataclasses
-import inspect
 import itertools
 import mmap
 import re
@@ -46,11 +45,6 @@ def _address(v):
   return _root(v.src[0]), add + start, size
 
 
-def _buffer(u):
-  from tinygrad.uop.ops import Ops
-  return u.buffer if u.op is Ops.BUFFER else getattr(u.arg, "buffer", None)
-
-
 def _patched(buf, topo) -> tuple[bytearray, dict]:
   from tinygrad.uop.ops import Ops
   blob, rows = bytearray(buf.max_numel() * buf.dtype.itemsize), {}
@@ -78,7 +72,7 @@ def _evaluate(u, env):
     table, index = _root(u.src[0].src[0]), _evaluate(u.src[0].src[1], env)
     return struct.unpack_from(u.dtype.fmt, table.arg, index * u.dtype.itemsize)[0] if table.op is Ops.BINARY and index is not None else None
   if u.op in GroupOp.ALU and None not in (values := [_evaluate(x, env) for x in u.src]):
-    return exec_alu(u.op, u.dtype, values, *([False] if "truncate_output" in inspect.signature(exec_alu).parameters else []))
+    return exec_alu(u.op, u.dtype, values, False)
   return None
 
 
@@ -118,7 +112,7 @@ def convert(jit, kwargs: dict, frame: dict, target) -> tuple[dict, memoryview]:
   from tinygrad.uop.ops import Ops
   submit = jit.captured._linear.src[0].without_after
   kernels, topo = submit.arg.aux.kernels, list(jit.captured._linear.toposort(enter_calls=True))
-  allocs = {str(name): u for u in topo if u.op is Ops.ALLOC and (name := getattr(u, "tag", None) or u.arg.name) is not None}
+  allocs = {str(u.tag): u for u in topo if u.op is Ops.ALLOC and u.tag is not None}
   (commands, patched), kernargs = _patched(allocs["cmdbuf_compute_0"], topo), allocs["kernargs_compute_0"]
   argument_words, pokes = _patched(kernargs, topo)[1], _input_pokes(submit, kernargs)
   sh = {name: getattr(amd_gpu, f"reg{name}") + amd_gpu.GC_BASE__INST0_SEG0 - pm4.PACKET3_SET_SH_REG_START
@@ -164,7 +158,7 @@ def convert(jit, kwargs: dict, frame: dict, target) -> tuple[dict, memoryview]:
         args.append({"input": pokes[slot][0]})
       elif slot in argument_words:
         base, at, nbytes = _address(argument_words[slot])
-        args.append({"buffer": buffers.setdefault(base, len(buffers)), "offset": at, "nbytes": nbytes or base.max_numel() * base.dtype.itemsize, "dtype": u8})
+        args.append({"buffer": buffers.setdefault(base, len(buffers)), "offset": at, "nbytes": nbytes or base.arg.buffer.nbytes, "dtype": u8})
     outs, ins = kernel[6]
     calls.append({"kind": "program", "name": re.sub(r"\x1b\[[0-9;]*m", "", kernel[1]), "lib": programs[image_alloc], "target": dataclasses.asdict(target),
                   "signature": [[f"data{i}", i, u8, [a.get("nbytes", 1)]] for i, a in enumerate(args)], "global_size": grid, "local_size": local,
@@ -172,13 +166,12 @@ def convert(jit, kwargs: dict, frame: dict, target) -> tuple[dict, memoryview]:
     needs_init |= {args[i]["buffer"] for i in ins if "buffer" in args[i] and args[i]["buffer"] not in written}
     written |= {args[i]["buffer"] for i in outs if "buffer" in args[i]}
 
-  assert all(_buffer(b) is not None for b, i in buffers.items() if i in needs_init), "a kernel reads a scratch before any kernel writes it"
   names = list(jit.captured.expected_names)
   inputs = [{"slot": slot, "name": names[slot] if slot < len(names) else None, "dtype": repr(u.dtype), "numel": int(u.max_numel()), "device": u.device}
             for slot, u in enumerate(_prepare_jit_inputs((), kwargs)[0])]
   header = {"input_names": names, "calls": calls, "returns": {"kind": "NoneType", "tensors": []}, "inputs": inputs,
-            "buffers": [{"nbytes": bb.nbytes if (bb := _buffer(b)) else b.max_numel() * b.dtype.itemsize, "device": bb.device if bb else b.device, "dtype": u8}
-                        | ({"init": blob.add(bb.ensure_allocated().as_memoryview())} if i in needs_init else {}) for b, i in buffers.items()],
+            "buffers": [{"nbytes": b.arg.buffer.nbytes, "device": b.arg.buffer.device, "dtype": u8}
+                        | ({"init": blob.add(b.arg.buffer.ensure_allocated().as_memoryview())} if i in needs_init else {}) for b, i in buffers.items()],
             "check": {"inputs": [[path, store(array), device] for path, array, device in frame["inputs"]],
                       "outputs": [store(array) for array in frame["outputs"]], "output_container": frame["output_container"]}}
   with sink:

openpilot/sunnypilot/modeld_v2/helpers.py

@@ -250,12 +250,6 @@ def _allocate_buffers(header: dict, blob: memoryview, device_map: dict | None, s
   return buffers
 
 
-def _fields(what, /, **values):  # a tinygrad dataclass built or replaced with the fields it has today: a dropped field is fine, a new required one is not
-  known = {field.name for field in dataclasses.fields(what)}
-  values = {name: value for name, value in values.items() if name in known}
-  return what(**values) if isinstance(what, type) else dataclasses.replace(what, **values)
-
-
 def _program_uop(call: dict, lib: bytes):
   from tinygrad.helpers import Target
   from tinygrad.uop.ops import KernelInfo, Ops, ProgramInfo, UOp
@@ -263,9 +257,9 @@ def _program_uop(call: dict, lib: bytes):
   for name, compact_slot, dtype, shape in call["signature"]:
     parameter = UOp.param(call["globals"][compact_slot], _dtype(dtype), math.prod(shape))
     image = (shape[0], shape[1]) if len(shape) == 3 and shape[2] == 4 else None
-    parameters.append(parameter.replace(arg=_fields(parameter.arg, name=name, image=image)))
-  info = _fields(ProgramInfo, global_size=tuple(call["global_size"]), local_size=tuple(call["local_size"]), globals=tuple(call["globals"]),
-                 outs=tuple(call["outs"]), ins=tuple(call["ins"]), target=_fields(Target, **call["target"]))
+    parameters.append(parameter.replace(arg=dataclasses.replace(parameter.arg, name=name, image=image)))
+  info = ProgramInfo(global_size=tuple(call["global_size"]), local_size=tuple(call["local_size"]), vars=(), globals=tuple(call["globals"]),
+                     outs=tuple(call["outs"]), ins=tuple(call["ins"]), target=Target(**call["target"]))
   return UOp(Ops.PROGRAM, src=(UOp(Ops.SINK, arg=KernelInfo(name=call["name"])), UOp(Ops.LINEAR, src=tuple(parameters)),
                                UOp(Ops.SOURCE, arg=""), UOp(Ops.BINARY, arg=lib)), arg=info)
 

openpilot/sunnypilot/modeld_v2/laneful.py

@@ -0,0 +1,125 @@
+"""
+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.
+"""
+import numpy as np
+
+from openpilot.common.filter_simple import FirstOrderFilter
+from openpilot.common.realtime import DT_MDL
+from openpilot.sunnypilot.modeld_v2.constants import ModelConstants
+
+LANE_WIDTH_DEFAULT = 3.6  # m (reseeded to model's lane width upon initialization)
+LANE_WIDTH_CLIP = (2.8, 4.5)  # m
+LOOKAHEAD_TIME = 1.5  # s
+MIN_LOOKAHEAD = 10.0  # m
+MIN_SPEED = 5.0  # m/s
+LINE_STD = (0.2, 0.6)
+POINT_STD = 0.1
+MAX_ERROR = 1.0
+YIELD = (0.2, 0.45)
+X_IDXS = np.array(ModelConstants.X_IDXS)
+
+
+class Laneful: # TODO-SP: Rename this to blendful or something similar because it is not pure laneful anymore.
+  def __init__(self):
+    self.lane_width = FirstOrderFilter(LANE_WIDTH_DEFAULT, 10.0, DT_MDL, initialized=False)
+    self.line_gone = FirstOrderFilter(np.zeros(2), 2.0, DT_MDL)
+    self.line_probs_slow = FirstOrderFilter(np.zeros(2), 3.0, DT_MDL)
+    self.line_probs = FirstOrderFilter(np.zeros(2), 0.5, DT_MDL)
+    self.usual_offset = FirstOrderFilter(0.0, 10.0, DT_MDL, initialized=False)
+    self.going_around = False
+    self.since_turning = 0.0
+    self.trust = 0.0
+    self.model_curvature = 0.0
+    self.smooth = 0.0 # smoothens lanelines below .53 lat accel
+    self.curvature = 0.0
+
+  def update(self, model_output: dict[str, np.ndarray], v_ego: float, active: bool, model_curvature: float) -> float:
+    fading = not active or v_ego < MIN_SPEED
+    if fading:
+      self.trust = 0.0
+      self.usual_offset.initialized = False
+      self.lane_width.initialized = False
+      self.going_around = False
+    self.model_curvature = model_curvature
+    target = 0.0 if fading else self._target(model_output, v_ego, model_curvature)
+    target = self.smooth = self.smooth + (target - self.smooth) * DT_MDL / (DT_MDL + np.interp(abs(model_curvature) * v_ego ** 2, [0.18, 0.53], [0.25, 0.0]))
+    releasing = not fading and (abs(target) < abs(self.curvature) or target * self.curvature < 0)
+    step = (2.0 if releasing else 0.5) / max(v_ego, 1.0) ** 2 * DT_MDL  # jerk over 1 second
+    self.curvature = float(np.clip(target, self.curvature - step, self.curvature + step))
+    return self.curvature
+
+  def _target(self, model_output: dict[str, np.ndarray], v_ego: float, model_curvature: float) -> float:
+    if v_ego < MIN_SPEED or 'lane_lines' not in model_output:
+      return 0.0
+
+    lookahead = max(v_ego * LOOKAHEAD_TIME, MIN_LOOKAHEAD)
+    lines = model_output['lane_lines'][0, :, :, 0]
+    stds = model_output['lane_lines_stds'][0, :, :, 0]
+
+    probs = self.line_probs.update(model_output['lane_lines_prob'][0, 1::2][1:3])
+    gone = self.line_gone.update((model_output['lane_lines_prob'][0, 1::2][1:3] < 0.3).astype(float))
+    dropping = bool(np.any(probs < 0.6 * self.line_probs_slow.update(model_output['lane_lines_prob'][0, 1::2][1:3])))
+    l_prob = float(probs[0] * np.interp(np.interp(0.5 * lookahead, X_IDXS, stds[1]), LINE_STD, [1.0, 0.0]))
+    r_prob = float(probs[1] * np.interp(np.interp(0.5 * lookahead, X_IDXS, stds[2]), LINE_STD, [1.0, 0.0]))
+    # one line steadily on its own still centers at half say conf. a line that is disappearing gives control back to laneless
+    if gone[1] > 0.8 and l_prob > 0.5:
+      lane_trust = l_prob / 2
+    elif gone[0] > 0.8 and r_prob > 0.5:
+      lane_trust = r_prob / 2
+    elif dropping:
+      lane_trust = min(l_prob, r_prob)
+    else:
+      lane_trust = l_prob + r_prob - l_prob * r_prob
+    if lane_trust <= 0.0:
+      self.trust = 0.0
+      return 0.0
+
+    win = (X_IDXS >= 0.5 * lookahead) & (X_IDXS <= 1.5 * lookahead)
+    x = X_IDXS[win]
+    half_width = self.lane_width.x / 2
+    if l_prob * r_prob > 0.5:
+      width = np.interp(lookahead, X_IDXS, lines[2]) - np.interp(lookahead, X_IDXS, lines[1])
+      self.lane_width.update(float(np.clip(width, *LANE_WIDTH_CLIP)))
+      half_width = np.clip(lines[2, win] - lines[1, win], *LANE_WIDTH_CLIP) / 2
+    l_var = stds[1, win] ** 2 / max(l_prob, 1e-4)
+    r_var = stds[2, win] ** 2 / max(r_prob, 1e-4)
+    center = (r_var * (lines[1, win] + half_width) + l_var * (lines[2, win] - half_width)) / (l_var + r_var)
+    weight = 1.0 / (l_var * r_var / (l_var + r_var) + POINT_STD ** 2)
+
+    # Fit curvature to place the plant in center: e ~ dk x^2 / 2
+    plan_x = np.interp(x, model_output['plan'][0, :, 0], model_output['plan'][0, :, 1])
+    plan_share = np.interp(abs(model_curvature) * lookahead ** 2 / 2, [0.5, 2.0], [0.3, 0.5]) # blending up to 50% plan with action during sharp curvature
+    error = np.clip(center - ((1 - plan_share) * model_curvature * x ** 2 / 2 + plan_share * plan_x), -1.0, 1.0)
+    dk = 2.0 * np.sum(weight * error * x ** 2) / np.sum(weight * x ** 4)
+
+    # A model planning to end up further from its usual spot in the lane than the plant is now is likely going around something
+    hw_now = np.clip(lines[2, 0] - lines[1, 0], *LANE_WIDTH_CLIP) / 2 if l_prob * r_prob > 0.5 else self.lane_width.x / 2
+    center_now = (l_prob * (lines[1, 0] + hw_now) + r_prob * (lines[2, 0] - hw_now)) / (l_prob + r_prob)
+    plan_y = np.interp(lookahead, model_output['plan'][0, :, 0], model_output['plan'][0, :, 1])
+    offset = plan_y - np.interp(lookahead, x, center)
+    if min(gone) > 0.5:  # both lines gone: turns, intersections, relearn ideal model position
+      self.usual_offset.initialized = False
+    usual = self.usual_offset.x if self.usual_offset.initialized else offset
+    swerve = abs(offset - usual) - 0.25 * abs(model_curvature) * lookahead ** 2 / 2
+    away = swerve - abs(-center_now - usual)
+    lane_curvature = 2.0 * np.polyfit(x, center, 2)[0]
+    inside_curve = abs(lane_curvature) * lookahead ** 2 / 2 > 0.1 and (offset - usual) * lane_curvature > 0
+    self.since_turning = 0.0 if abs(model_curvature) * lookahead ** 2 / 2 > 0.5 else self.since_turning + DT_MDL
+    if inside_curve:
+      self.going_around = False
+    elif away > YIELD[0] and self.since_turning > 2.0:
+      self.going_around = True
+    elif swerve < YIELD[0] / 2:
+      self.going_around = False
+    self.usual_offset.update_alpha(20.0 if self.going_around else 10.0)
+    self.usual_offset.update(offset)
+    if inside_curve:
+      lane_trust *= np.interp(abs(offset) - abs(center_now) - 0.25 * abs(model_curvature) * lookahead ** 2 / 2, (0.5, 1.0), [1.0, 0.0])
+    else:
+      lane_trust *= np.interp(swerve, (YIELD[0] / 2, YIELD[0]), [1.0, 0.0]) if self.going_around else np.interp(away, YIELD, [1.0, 0.0])
+
+    self.trust = lane_trust if lane_trust < self.trust else self.trust + (lane_trust - self.trust) * DT_MDL / (1.5 + DT_MDL)
+    return float(self.trust * dk)

openpilot/sunnypilot/modeld_v2/modeld.py

@@ -7,6 +7,7 @@ See the LICENSE.md file in the root directory for more details.
 """
 
 from collections.abc import Callable
+from functools import partial
 import gc
 import os
 os.environ['GMMU'] = '0'
@@ -39,6 +40,7 @@ from openpilot.selfdrive.modeld.modeld import ChestnutGpuState
 
 from openpilot.sunnypilot.modeld_v2.fill_model_msg import fill_model_msg, fill_pose_msg, PublishState, get_curvature_from_output
 from openpilot.sunnypilot.modeld_v2.parse_model_outputs import Parser
+from openpilot.sunnypilot.modeld_v2.laneful import Laneful
 from openpilot.sunnypilot.modeld_v2.constants import ModelConstants, Plan
 from openpilot.sunnypilot.modeld_v2.meta_helper import load_meta_constants
 from openpilot.sunnypilot.modeld_v2.camera_offset_helper import CameraOffsetHelper
@@ -228,7 +230,8 @@ class ModelState(ModelStateBase):
     return outputs
 
   def get_action_from_model(self, model_output: dict[str, np.ndarray], prev_action: log.ModelDataV2.Action,
-                            lat_action_t: float, long_action_t: float, v_ego: float) -> log.ModelDataV2.Action:
+                            lat_action_t: float, long_action_t: float, v_ego: float,
+                            laneful: Callable[[float], float] | None = None) -> log.ModelDataV2.Action:
     if 'action' not in model_output:
       plan = model_output['plan'][0]
       desired_accel = get_accel_from_plan(plan[:, Plan.VELOCITY][:, 0], plan[:, Plan.ACCELERATION][:, 0], self.constants.T_IDXS,
@@ -240,6 +243,8 @@ class ModelState(ModelStateBase):
     else:
       desired_accel = model_output['action'][0, 1]
       desired_curvature = model_output['action'][0, 0] / (max(1.0, v_ego))**2
+    if laneful is not None:
+      desired_curvature += laneful(desired_curvature)
 
     stop = v_ego < 0.3 and desired_accel < 0.1
     desired_accel = smooth_value(desired_accel, prev_action.desiredAcceleration, self.LONG_SMOOTH_SECONDS)
@@ -366,6 +371,8 @@ def main(demo=False):
   DH = DesireHelper()
   meta_constants = load_meta_constants()
   RELC = RoadEdgeLaneChangeController()
+  laneful = Laneful()
+  laneful_enabled = False
 
   while True:
     # Keep receiving frames until we are at least 1 frame ahead of previous extra frame
@@ -409,6 +416,7 @@ def main(demo=False):
       model.lat_delay = get_lat_delay(params, sm["lateralDelay"].lateralDelay)
       model.PLANPLUS_CONTROL = params.get("PlanplusControl", return_default=True)
       camera_offset_helper.set_offset(params.get("CameraOffset", return_default=True))
+      laneful_enabled = params.get_bool("Laneful")
     lat_delay = model.lat_delay + model.LAT_SMOOTH_SECONDS
     if sm.updated["extrinsicsCalibration"] and sm.seen['narrowRoadCameraState'] and sm.seen['deviceState']:
       device_from_calib_euler = np.array(sm["extrinsicsCalibration"].rpyCalib, dtype=np.float32)
@@ -482,7 +490,9 @@ def main(demo=False):
 
       if not sm['carControl'].latActive:
         prev_action.desiredCurvature = sm['controlsState'].curvature
-      action = model.get_action_from_model(model_output, prev_action, lat_action_t, long_action_t, v_ego)
+      laneful_active = laneful_enabled and desire == log.Desire.none and DH.lane_change_state == log.LaneChangeState.off
+      action = model.get_action_from_model(model_output, prev_action, lat_action_t, long_action_t, v_ego,
+                                           partial(laneful.update, model_output, v_ego, laneful_active))
       prev_action = action
       fill_model_msg(drivingdata_send, modelv2_send, model_output, action,
                      publish_state, meta_main.frame_id, meta_extra.frame_id, frame_id,
@@ -499,6 +509,10 @@ def main(demo=False):
       modelv2_send.modelV2.meta.laneChangeDirection = DH.lane_change_direction
       mdv2sp_send.valid = modelv2_send.valid
       mdv2sp_send.modelDataV2SP.laneTurnDirection = DH.lane_turn_direction
+      mdv2sp_send.modelDataV2SP.lanefulCurvature = laneful.curvature
+      mdv2sp_send.modelDataV2SP.lanefulTrust = float(laneful.trust)
+      mdv2sp_send.modelDataV2SP.modelCurvature = float(laneful.model_curvature)
+      mdv2sp_send.modelDataV2SP.lanefulGoingAround = bool(laneful.going_around)
       drivingdata_send.drivingModelData.meta.laneChangeState = DH.lane_change_state
       drivingdata_send.drivingModelData.meta.laneChangeDirection = DH.lane_change_direction
 

openpilot/sunnypilot/modeld_v2/plain_artifact_compiler.py

@@ -23,7 +23,7 @@ def record_kernel_linear():
   recorded, hcq_compile, compile_linear = [], realize.hcq_compile, jit.compile_linear
 
   def recording_compile_linear(*args, **kwargs):
-    with mock.patch.object(realize, "hcq_compile", lambda linear, *a, **k: (linear.src and recorded.append(linear), hcq_compile(linear, *a, **k))[1]):
+    with mock.patch.object(realize, "hcq_compile", lambda linear, *a, **k: (recorded.append(linear), hcq_compile(linear, *a, **k))[1]):
       return compile_linear(*args, **kwargs)
 
   with mock.patch.object(jit, "compile_linear", recording_compile_linear):
@@ -38,18 +38,6 @@ def capture_frame(jit, kwargs: dict, output_container: str | None = None):
   return {"inputs": inputs, "outputs": [tensor.numpy().copy() for tensor in outputs], "output_container": output_container}, result
 
 
-def kernel_signature(ast, elf) -> list:
-  from tinygrad.dtype import AddrSpace
-  if hasattr(ast, "kernel_params"):
-    if any(p.arg.addrspace is AddrSpace.ALU for p in ast.kernel_params):
-      raise ValueError(f"{elf.name} takes a variable, which plain artifacts don't support")
-    compact = {slot: i for i, slot in enumerate(ast.arg.globals)}
-    return [[p.arg.name, compact[p.arg.slot], repr(p.dtype), [int(x) for x in p._shape]] for p in ast.kernel_params]
-  if not all(isinstance(slot, int) for _, slot, _, _ in elf.signature):
-    raise ValueError("TinyELF.signature lost its slots and this tinygrad has no UOp.kernel_params: update kernel_signature")
-  return [[name, slot, repr(dtype), [int(x) for x in shape]] for name, slot, dtype, shape in elf.signature]
-
-
 def serialize_jit(jit, kernel_linear, check: dict | None = None) -> tuple[dict, memoryview]:
   from tinygrad.uop.ops import Ops
   sink = tempfile.TemporaryFile(dir=".")
@@ -63,12 +51,6 @@ def serialize_jit(jit, kernel_linear, check: dict | None = None) -> tuple[dict,
     if uop.op is Ops.PARAM:
       input_specs.setdefault(uop.arg.slot, {"dtype": repr(uop.dtype), "numel": int(uop.max_numel()), "device": uop.device})
       return {"input": uop.arg.slot}
-    root, offset = uop, 0
-    while root.op in (Ops.AFTER, Ops.BITCAST, Ops.SHRINK):
-      offset, root = offset + (root.src[1].arg * root.src[0].dtype.itemsize if root.op is Ops.SHRINK else 0), root.src[0]
-    if root.op is Ops.ALLOC:
-      base = bases.setdefault(id(root), (len(bases), root, root.dtype))
-      return {"buffer": base[0], "offset": offset, "nbytes": int(uop.max_numel()) * uop.dtype.itemsize, "dtype": repr(uop.dtype)}
     buffer = uop.buffer
     root = buffer._base if buffer._base is not None else buffer
     base = bases.setdefault(id(root), (len(bases), root, uop.base.dtype if buffer._base is None else uop.dtype))
@@ -81,7 +63,7 @@ def serialize_jit(jit, kernel_linear, check: dict | None = None) -> tuple[dict,
       elf, info = ast.to_elf(), ast.arg
       global_size, local_size = info.launch_dims({})
       calls.append({"kind": "program", "name": elf.name, "lib": blob.add(bytes(elf.lib)), "target": dataclasses.asdict(elf.target),
-                    "signature": kernel_signature(ast, elf),
+                    "signature": [[name, slot, repr(dtype), [int(x) for x in shape]] for name, slot, dtype, shape in elf.signature],
                     "global_size": [int(x) for x in global_size], "local_size": [int(x) for x in local_size],
                     "globals": list(info.globals), "outs": list(info.outs), "ins": list(info.ins), "args": arguments})
       outs, ins = info.outs, info.ins
@@ -95,9 +77,7 @@ def serialize_jit(jit, kernel_linear, check: dict | None = None) -> tuple[dict,
 
   ret = jit.captured.ret
   returns = {"kind": type(ret).__name__, "tensors": [describe(t.uop.base) | {"shape": [int(x) for x in t.shape]} for t in flatten(ret)]}
-  from tinygrad.device import Buffer
-  assert not [base for index, base, _ in bases.values() if index in needs_init and not isinstance(base, Buffer)], "a kernel reads a scratch before writing it"
-  buffers = [{"nbytes": base.nbytes if isinstance(base, Buffer) else int(base.max_numel()) * dtype.itemsize, "device": base.device, "dtype": repr(dtype)}
+  buffers = [{"nbytes": base.nbytes, "device": base.device, "dtype": repr(dtype)}
              | ({"init": blob.add(base.as_memoryview())} if index in needs_init else {}) for index, base, dtype in bases.values()]
   names = list(jit.captured.expected_names)
   if check is not None:

openpilot/sunnypilot/modeld_v2/tests/test_convert_upstream_pkl.py

@@ -1,121 +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.
-"""
-import os
-import re
-import sys
-import tempfile
-import unittest
-from unittest import mock
-import numpy as np
-
-os.environ.setdefault("CHECK_OOB", "0")
-os.environ.setdefault("GMMU", "0")
-if sys.platform == "darwin" and os.environ.get("DEV", "").startswith("MOCKUSB"):  # the mock's VRAM is a memfd, which macOS lacks: an unlinked file is the same
-  from tinygrad.runtime.autogen import libc
-
-  def _memfd_create(name, flags):
-    fd, path = tempfile.mkstemp()
-    os.unlink(path)
-    return fd
-  libc.memfd_create = _memfd_create
-
-from openpilot.common.test import OpenpilotTestCase
-from openpilot.sunnypilot.modeld_v2 import convert_upstream_pkl
-from openpilot.sunnypilot.modeld_v2.convert_upstream_pkl import convert
-from openpilot.sunnypilot.modeld_v2.helpers import PlainJit, load_model
-from openpilot.sunnypilot.modeld_v2.plain_artifact_compiler import capture_frame
-
-IMG, DESIRE, STATE, OUT = (6, 8, 8), (8,), (4, 16), (1, 32)
-
-
-class TestConvertUpstreamPkl(OpenpilotTestCase):
-  @classmethod
-  def setUpClass(cls):
-    super().setUpClass()
-    if not os.environ.get("TINYGRAD_TESTS"):
-      raise unittest.SkipTest("TINYGRAD_TESTS not set. skipping converter test")
-    from tinygrad import Device, Tensor
-    assert Device.DEFAULT == "AMD" and getattr(Device["AMD"], "is_usb", False), f"{Device.DEFAULT} is not an AMD device behind the USB bridge"
-    assert (Tensor([1, 2, 3]) * 2).tolist() == [2, 4, 6]
-    cls.tmp = tempfile.TemporaryDirectory()
-    cls.rng = np.random.default_rng(0)
-    cls.weights = Tensor(cls.rng.standard_normal((16, 32)).astype(np.float32)).realize()
-    cls.bias = Tensor(cls.rng.standard_normal((1, 32)).astype(np.float32)).realize()
-    cls.input_specs = {"input_imgs": (IMG, "uint8", Device.DEFAULT), "desire": (DESIRE, "float32", Device.DEFAULT),
-                       "features": (STATE, "float32", Device.DEFAULT)}
-    cls.output_specs = {"outputs": (OUT, "float32", Device.DEFAULT), "next_features": (STATE, "float32", Device.DEFAULT)}
-
-  @classmethod
-  def tearDownClass(cls):
-    cls.tmp.cleanup()
-    super().tearDownClass()
-
-  def model(self, input_imgs, desire, features, output_buffers):
-    from tinygrad import Tensor
-    feat = features.mean(axis=0).reshape(1, 16) + input_imgs.float().mean() + desire.sum()
-    Tensor.realize(output_buffers["outputs"].assign((feat @ self.weights + self.bias).relu()),
-                   output_buffers["next_features"].assign(features[1:].cat(feat * 2)))
-
-  def inputs(self, seed: int) -> dict:
-    from examples.openpilot.helpers import allocate_inputs
-    rng = np.random.default_rng(seed)
-
-    def initialize(arrays: dict):
-      for value in arrays.values():
-        value[...] = rng.standard_normal(value.shape) if value.dtype.kind == "f" else rng.integers(0, 256, value.shape)
-    return allocate_inputs(self.input_specs, initialize) | {"output_buffers": allocate_inputs(self.output_specs)}
-
-  def jit(self):
-    from tinygrad import TinyJit
-    run = TinyJit(self.model, prune=True)
-    kwargs = self.inputs(1)
-    run(**kwargs)
-    run(**kwargs)
-    return run
-
-  def assert_matches_eager(self, plain, seed: int):
-    fresh, expected = self.inputs(seed), self.inputs(seed)
-    plain(**fresh)
-    self.model(**expected)
-    for name in self.output_specs:
-      assert np.array_equal(fresh["output_buffers"][name].numpy(), expected["output_buffers"][name].numpy()), name
-
-  def convert(self, jit) -> tuple[dict, memoryview]:
-    from tinygrad import Device
-    kwargs = self.inputs(2)
-    frame, _ = capture_frame(jit, kwargs, "output_buffers")
-    header, blob = convert(jit, kwargs, frame, Device[Device.DEFAULT].renderer.target)
-    kernels = jit.captured._linear.src[0].without_after.arg.aux.kernels
-    assert [call["name"] for call in header["calls"]] == [re.sub(r"\x1b\[[0-9;]*m", "", kernel[1]) for kernel in kernels]
-    assert all(re.fullmatch(r"\w+", call["name"]) for call in header["calls"]), "kernel names: failure point 1"
-    assert [(tuple(call["outs"]), tuple(call["ins"])) for call in header["calls"]] == [tuple(kernel[6]) for kernel in kernels], "outs/ins: failure point 1"
-    bound = {argument["input"] for call in header["calls"] for argument in call["args"] if "input" in argument}
-    assert bound == {spec["slot"] for spec in header["inputs"]}, f"input slots bound by pokes {sorted(bound)}: failure point 4"
-    assert [spec["name"] for spec in header["inputs"]][:len(self.input_specs)] == sorted(self.input_specs)
-    return header, blob
-
-  def test_converted_jit_matches_eager(self):  # the submit decoded into plain calls, replayed against its own frame
-    jit = self.jit()
-    plain = PlainJit(*self.convert(jit))
-    self.assert_matches_eager(plain, 3)
-    self.assert_matches_eager(plain, 4)
-
-  def test_pickle_round_trip_through_main(self):
-    from examples.openpilot.helpers import dump_pickle, load_pickle
-    from tinygrad.engine.realize import lower_and_compile
-    pkl, out = os.path.join(self.tmp.name, "tiny_tinygrad.pkl"), os.path.join(self.tmp.name, "tiny_plain.pkl")
-    dump_pickle({"run": self.jit(), "input_specs": self.input_specs, "output_specs": self.output_specs, "metadata": {"name": "tiny"}}, pkl)
-
-    artifact = load_pickle(pkl, out_of_band=True)
-    artifact["run"].captured._linear = lower_and_compile(artifact["run"].captured._linear)
-    self.assert_matches_eager(PlainJit(*self.convert(artifact["run"])), 5)
-
-    with mock.patch.object(sys, "argv", ["convert_upstream_pkl", pkl, out]):
-      convert_upstream_pkl.main()
-    bundle = load_model(out, cache=False, verify=True)
-    assert bundle["metadata"] == {"name": "tiny"} and bundle["input_specs"] == self.input_specs and bundle["output_specs"] == self.output_specs
-    self.assert_matches_eager(bundle["run"], 6)

openpilot/sunnypilot/modeld_v2/tests/test_plain_artifact.py

@@ -1,162 +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.
-"""
-import dataclasses
-import functools
-import inspect
-import os
-import sys
-import tempfile
-from unittest import mock
-import numpy as np
-import unittest
-
-import openpilot.sunnypilot.modeld_v2.helpers as helpers
-from openpilot.common.test import OpenpilotTestCase
-from openpilot.sunnypilot.modeld_v2 import compile_warp
-from openpilot.sunnypilot.modeld_v2.frame_fusion import frame_part, pack_layout
-from openpilot.sunnypilot.modeld_v2.helpers import PlainJit, cache_is_fresh, load_model, read_parts, write_bundle
-from openpilot.sunnypilot.modeld_v2.plain_artifact_compiler import capture_frame, record_kernel_linear, serialize_jit
-
-CAM_W, CAM_H, MODEL_W, MODEL_H = 32, 16, 16, 8
-FRAME = f"{CAM_W},{CAM_H},{CAM_W},{CAM_H},{CAM_H // 2},{CAM_W * CAM_H * 3 // 2}"
-FRAME_SIZE = CAM_W * CAM_H * 3 // 2
-HOST = {"desire": (8,), "traffic_convention": (2,)}
-STATE, OUT = (4, 16), (1, 32)
-
-
-def compile_jit(fn, inputs: dict, output_container: str | None = None) -> tuple[dict, memoryview]:
-  from tinygrad import TinyJit
-  run = TinyJit(fn, prune=True)
-  with record_kernel_linear() as recorded:
-    run(**inputs)
-    run(**inputs)
-    check, _ = capture_frame(run, inputs, output_container)
-  assert len(recorded) == 1, f"expected one captured kernel list, got {len(recorded)}"
-  return serialize_jit(run, recorded[0], check)
-
-
-class TestPlainArtifact(OpenpilotTestCase):
-  @classmethod
-  def setUpClass(cls):
-    super().setUpClass()
-    if not os.environ.get("TINYGRAD_TESTS"):
-      raise unittest.SkipTest("TINYGRAD_TESTS env var not set, skipping artifact test.")
-    from tinygrad import Tensor
-    cls.tmp = tempfile.TemporaryDirectory()
-    cls.rng = np.random.default_rng(0)
-    cls.weights = Tensor(cls.rng.standard_normal((16, 32)).astype(np.float32)).realize()
-    cls.bias = Tensor(cls.rng.standard_normal((1, 32)).astype(np.float32)).realize()
-
-  @classmethod
-  def tearDownClass(cls):
-    cls.tmp.cleanup()
-    super().tearDownClass()
-
-  def model(self, x, h):  # a two input, one weight model: the shape of a policy without the size
-    return ((x @ self.weights + self.bias).relu() + h.mean()).contiguous()
-
-  def tensors(self, seed: int):
-    from tinygrad import Tensor
-    rng = np.random.default_rng(seed)
-    return {"x": Tensor(rng.standard_normal((1, 16)).astype(np.float32)).realize(), "h": Tensor(rng.standard_normal((4, 16)).astype(np.float32)).realize()}
-
-  def artifact(self, name: str = "model") -> str:
-    path = os.path.join(self.tmp.name, f"{name}_tinygrad.pkl")
-    if not os.path.exists(path):
-      write_bundle(path, {"run": compile_jit(self.model, self.tensors(1))}, {"metadata": {"name": name}})
-    return path
-
-  def test_round_trip_matches_jit(self):  # compiler -> bundle -> PlainJit, replay verified, then fresh inputs bit exact with eager tinygrad
-    bundle = load_model(self.artifact(), cache=False, verify=True)
-    assert bundle["metadata"] == {"name": "model"} and isinstance(bundle["run"], PlainJit)
-    fresh = self.tensors(2)
-    assert np.array_equal(bundle["run"](**fresh).numpy(), self.model(**fresh).numpy())
-
-  def test_replay_check_catches_a_changed_kernel(self):
-    parts, extras = read_parts(self.artifact())
-    header, blob = parts["run"]
-    poisoned = dict(header, check=dict(header["check"], outputs=[header["check"]["inputs"][0][1]]))
-    with self.assertRaises(helpers.ArtifactMismatch):
-      PlainJit(poisoned, blob)
-
-  def test_cache_round_trip_holds_no_weights_and_is_rebuilt_when_stale(self):
-    path = self.artifact("cached")
-    expected = load_model(path, cache=False, verify=False)["run"](**self.tensors(3)).numpy()
-    load_model(path)
-    assert cache_is_fresh(path)
-    with open(f"{path}.cache", "rb") as file:
-      cache = file.read()
-    assert self.weights.numpy().tobytes() not in cache and len(cache) < os.path.getsize(path)
-    with mock.patch.object(helpers, "PlainJit", side_effect=AssertionError("a fresh cache must not rebuild")):
-      cached = load_model(path)
-    assert np.array_equal(cached["run"](**self.tensors(3)).numpy(), expected)
-    with mock.patch.object(helpers, "tinygrad_identity", return_value="another tinygrad"):
-      assert not cache_is_fresh(path)
-      assert isinstance(load_model(path)["run"], PlainJit)
-      assert cache_is_fresh(path)
-    assert not cache_is_fresh(path)  # keyed on the tinygrad that wrote it, so the next boot after a bump rebuilds once
-    os.utime(path)
-    with mock.patch.object(helpers, "tinygrad_identity", return_value="another tinygrad"):
-      assert not cache_is_fresh(path)
-
-  def test_fused_with_warp_matches_warp_then_model(self):
-    from tinygrad import Tensor
-    warp_path = os.path.join(self.tmp.name, "warp_tinygrad.pkl")
-    with mock.patch.object(sys, "argv", ["compile_warp", "--frame", FRAME, "--warp-to", f"{MODEL_W}x{MODEL_H}", "--output", warp_path]):
-      compile_warp.main()
-    warp = load_model(warp_path, cache=False)["run"]
-
-    def native(new_img, desire, traffic_convention, state_feat_q, output_buffers):
-      feat = state_feat_q.mean(axis=0).reshape(1, 16) + new_img.float().mean() + desire.sum() + traffic_convention[0]
-      Tensor.realize(output_buffers["outputs"].assign((feat @ self.weights + self.bias).relu()),
-                     output_buffers["next_state_feat_q"].assign(state_feat_q[1:].cat(feat * 2)))
-
-    def model_inputs(new_img):
-      return {"new_img": new_img} | {name: Tensor(np.ones(shape, np.float32) * 0.5).realize() for name, shape in HOST.items()} | \
-             {"state_feat_q": Tensor(self.rng.standard_normal(STATE).astype(np.float32)).realize(),
-              "output_buffers": {"outputs": Tensor.zeros(OUT).contiguous().realize(), "next_state_feat_q": Tensor.zeros(STATE).contiguous().realize()}}
-    frames = Tensor(self.rng.integers(0, 256, (2, FRAME_SIZE), dtype=np.uint8)).realize()
-    tfm = Tensor(np.tile(np.eye(3, dtype=np.float32), (2, 1, 1))).realize()
-    path = os.path.join(self.tmp.name, "native_tinygrad.pkl")
-    part = compile_jit(native, model_inputs(warp(input_frame=frames, M_inv=tfm).realize()), "output_buffers")
-    extras = {"input_specs": {"new_img": ((2, 6, MODEL_H // 2, MODEL_W // 2), "|u1", "CPU"), "state_feat_q": (STATE, "<f4", "CPU")}
-              | {name: (shape, "<f4", "CPU") for name, shape in HOST.items()},
-              "output_specs": {"outputs": (OUT, "<f4", "CPU"), "next_state_feat_q": (STATE, "<f4", "CPU")},
-              "metadata": {"output_shapes": {"outputs": OUT, "next_state_feat_q": STATE}}}
-    write_bundle(path, {"run": part}, extras)
-
-    fused = load_model(path, cache=False, extend=functools.partial(frame_part, warp_path))
-    assert fused["run"].input_names == ["host", "state_feat_q"]
-    offsets, packed = pack_layout(HOST, FRAME_SIZE)
-    host = np.zeros(packed, np.uint8)
-    inputs = model_inputs(None)
-    for name, shape in ({"tfm": (2, 3, 3)} | HOST).items():
-      np.ndarray(shape, np.float32, host, offsets[name])[...] = tfm.numpy() if name == "tfm" else inputs[name].numpy()
-    host[offsets["frames"]:] = frames.numpy().ravel()
-    fused["run"](host=Tensor(host, device="NPY"), state_feat_q=inputs["state_feat_q"], output_buffers=inputs["output_buffers"])
-
-    expected = model_inputs(warp(input_frame=frames, M_inv=tfm).realize()) | {k: inputs[k] for k in ("state_feat_q",)}
-    native(**expected)
-    for name in ("outputs", "next_state_feat_q"):
-      assert np.array_equal(inputs["output_buffers"][name].numpy(), expected["output_buffers"][name].numpy()), name
-
-  def test_tinygrad_api_the_loader_reads(self):
-    import tinygrad.engine.jit as jit
-    from tinygrad.device import Buffer, TinyELF
-    from tinygrad.helpers import Target
-    from tinygrad.uop.ops import ParamArg, ProgramInfo, UOp
-    fields = {cls: {f.name for f in dataclasses.fields(cls)} for cls in (ProgramInfo, ParamArg, Target)}
-    assert fields[ProgramInfo] >= {"global_size", "local_size", "globals", "outs", "ins", "target"}, "ProgramInfo changed: update helpers._program_uop"
-    assert fields[ParamArg] >= {"slot", "dtype", "name", "image"}, "ParamArg changed: update helpers._program_uop"
-    assert fields[Target] >= {"device", "renderer", "arch"}, "Target changed: update the 'target' key in plain_artifact_compiler.serialize_jit"
-    assert "signature" in getattr(TinyELF, "__annotations__", {}) or hasattr(UOp, "kernel_params"), \
-      "kernel signatures moved: update plain_artifact_compiler.serialize_jit"
-    assert callable(getattr(UOp, "param", None)) and callable(getattr(UOp, "from_buffer", None)), "UOp.param/from_buffer: update helpers.PlainJit"
-    assert callable(getattr(UOp, "store_call", None)) and callable(getattr(UOp, "call", None)), "UOp.call/store_call: update helpers.PlainJit"
-    assert callable(getattr(Buffer, "view", None)) and callable(getattr(Buffer, "ensure_allocated", None)), "Buffer.view: update helpers._upload"
-    assert callable(getattr(jit, "compile_linear", None)) and callable(getattr(jit, "_prepare_jit_inputs", None)), "engine.jit: update helpers._Jit"
-    assert "expected_names" in inspect.signature(jit.CapturedJit).parameters, "CapturedJit: update helpers.PlainJit and plain_artifact_compiler.serialize_jit"

openpilot/sunnypilot/models/manager.py

@@ -7,10 +7,7 @@ See the LICENSE.md file in the root directory for more details.
 
 import asyncio
 import os
-import re
-import threading
 import time
-from concurrent.futures import ThreadPoolExecutor
 
 import requests
 from openpilot.common.params import Params
@@ -25,99 +22,12 @@ from openpilot.sunnypilot.models.helpers import (ACTIVE_BUNDLE_KEYS, get_active_
 
 # (connect, read) seconds. read is per-request inactivity, not a total cap
 DOWNLOAD_TIMEOUT = (30, 30)
-# HuggingFace throttles each connection to ~1-2 MB/s but not the connection count; 12 saturates the device link
-MAX_CONCURRENT_PIECES = 12
-PIECE_SIZE = 8 * 1024 * 1024
-PIECE_ATTEMPTS = 3
-PIECE_BACKOFF = 1.0  # seconds, growing linearly: waits 1 s then 2 s between a piece's three attempts
-TRANSIENT_HTTP_STATUS = frozenset({408, 429, 500, 502, 503, 504})
-REPORT_INTERVAL = 0.5  # seconds between progress publications
-# byte ranges count encoded bytes but iter_content yields decoded ones, so ask for an unencoded body
-NO_COMPRESSION = {"Accept-Encoding": "identity"}
 
 
 class DownloadCancelled(Exception):
   pass
 
 
-def _is_transient(e: BaseException) -> bool:
-  if isinstance(e, requests.HTTPError):
-    return e.response is not None and e.response.status_code in TRANSIENT_HTTP_STATUS
-  return isinstance(e, (requests.ConnectionError, requests.Timeout, requests.exceptions.ChunkedEncodingError))
-
-
-class _Progress:
-  def __init__(self):
-    self._bytes = 0
-    self._lock = threading.Lock()
-
-  def add_bytes(self, n: int) -> None:
-    with self._lock:
-      self._bytes += n
-
-  def snapshot(self) -> int:
-    with self._lock:
-      return self._bytes
-
-
-def _piece_ranges(total: int, piece_size: int) -> list[tuple[int, int]]:
-  return [(start, min(start + piece_size, total)) for start in range(0, total, piece_size)]
-
-
-def _prepare_target(path: str, total: int) -> None:
-  with open(path, "wb") as f:
-    f.truncate(total)
-
-
-def _content_range_total(response: requests.Response) -> int | None:
-  if response.status_code != 206:
-    return None
-  match = re.fullmatch(r"bytes \d+-\d+/(\d+)", response.headers.get("Content-Range", ""))
-  return int(match.group(1)) if match else None
-
-
-def _probe_size(url: str) -> tuple[int, bool]:
-  with requests.get(url, headers={**NO_COMPRESSION, "Range": "bytes=0-0"}, stream=True, timeout=DOWNLOAD_TIMEOUT) as response:
-    response.raise_for_status()
-    total = _content_range_total(response)
-    if total is not None:
-      return total, True
-    return int(response.headers.get("Content-Length", 0)), False
-
-
-def _fetch_piece(url: str, path: str, index: int, start: int, end: int | None, progress: _Progress,
-                 cancel: threading.Event, block_size: int) -> None:
-  headers = {**NO_COMPRESSION, "Range": f"bytes={start}-{end - 1}"} if end is not None else NO_COMPRESSION
-  label = f"{os.path.basename(path)} piece {index}"
-  for attempt in range(PIECE_ATTEMPTS):
-    written = 0
-    try:
-      with requests.get(url, headers=headers, stream=True, timeout=DOWNLOAD_TIMEOUT) as response:
-        response.raise_for_status()
-        if end is not None and response.status_code != 206:
-          raise ValueError(f"server ignored byte range for {label}")
-        with open(path, "r+b") as f:
-          f.seek(start)
-          for block in response.iter_content(chunk_size=block_size):
-            if cancel.is_set():
-              raise DownloadCancelled("Download cancelled")
-            f.write(block)
-            written += len(block)
-            progress.add_bytes(len(block))
-          if end is None:
-            f.truncate()  # unknown length: the body defines the file size
-          if end is not None and written != end - start:
-            raise requests.exceptions.ConnectionError(f"short read: {written} of {end - start} bytes")
-      return
-    except requests.RequestException as e:
-      progress.add_bytes(-written)  # the piece restarts from scratch
-      if not _is_transient(e) or attempt == PIECE_ATTEMPTS - 1:
-        raise
-      cloudlog.warning(f"retrying {label} after {type(e).__name__}: {e}")
-      if cancel.wait(PIECE_BACKOFF * (1 + attempt)):
-        raise DownloadCancelled("Download cancelled") from None
-
-
 class ModelManagerSP:
   """Manages model downloads and status reporting"""
 
@@ -131,7 +41,7 @@ class ModelManagerSP:
     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, chestnut=self.chestnut_present)
-    self._block_size = 128 * 1000  # 128 KB network read blocks
+    self._chunk_size = 128 * 1000  # 128 KB chunks
     self._download_start_times: dict[str, float] = {}  # Track start time per model
     self._download_ref: bytes | str | None = None
 
@@ -146,6 +56,7 @@ class ModelManagerSP:
     self._download_ref = None
 
   def _sync_artifact_progress(self, source_artifact) -> None:
+    """Mirror download progress to all artifacts sharing the same filename in the selected bundle."""
     if not self.selected_bundle:
       return
     for model in self.selected_bundle.models:
@@ -156,6 +67,7 @@ class ModelManagerSP:
         artifact.downloadProgress.eta = source_artifact.downloadProgress.eta
 
   def _calculate_eta(self, filename: str, progress: float) -> int:
+    """Calculate ETA based on elapsed time and current progress"""
     if filename not in self._download_start_times or progress <= 0:
       return 60  # Default ETA for new downloads
 
@@ -163,58 +75,39 @@ class ModelManagerSP:
     if elapsed_time <= 0:
       return 60
 
+    # If we're at X% after Y seconds, we can estimate total time as (Y / X) * 100
     total_estimated_time = (elapsed_time / progress) * 100
     eta = total_estimated_time - elapsed_time
+
     return max(1, int(eta))  # Return at least 1 second if download is ongoing
 
-  def _set_progress(self, artifact, status, progress: float, eta: int = 0) -> None:
-    artifact.downloadProgress.status = status
-    artifact.downloadProgress.progress = progress
-    artifact.downloadProgress.eta = eta
-    self._sync_artifact_progress(artifact)
-    self._report_status()
+  async def _download_file(self, url: str, path: str, model) -> None:
+    """Downloads a file with progress tracking"""
+    self._download_start_times[model.fileName] = time.monotonic()
 
-  def _publish_progress(self, artifact, done_bytes: int, total: int) -> None:
-    # held at 99 until the file passes its hash check
-    progress = min(99.0, done_bytes / total * 100) if total > 0 else 0.0
-    eta = self._calculate_eta(artifact.fileName, progress)
-    self._set_progress(artifact, custom.ModelManagerSP.DownloadStatus.downloading, progress, eta)
+    with requests.get(url, stream=True, timeout=DOWNLOAD_TIMEOUT) as response:  # noqa: ASYNC210
+      response.raise_for_status()
+      total_size = int(response.headers.get("content-length", 0))
+      bytes_downloaded = 0
 
-  async def _report_until_done(self, tasks: list[asyncio.Future], artifact, progress: _Progress, total: int) -> None:
-    pending = set(tasks)
-    while pending:
-      done, pending = await asyncio.wait(pending, timeout=REPORT_INTERVAL)
-      for task in done:
-        task.result()  # re-raises a worker failure
-      if self._download_interrupted():
-        raise DownloadCancelled("Download cancelled")
-      self._publish_progress(artifact, progress.snapshot(), total)
+      with open(path, 'wb') as f:  # noqa: ASYNC230
+        for chunk in response.iter_content(chunk_size=self._chunk_size):  # type: bytes
+          f.write(chunk)
+          bytes_downloaded += len(chunk)
 
-  async def _download_file(self, url: str, path: str, artifact) -> None:
-    self._download_start_times[artifact.fileName] = time.monotonic()
-    loop = asyncio.get_running_loop()
+          if self._download_interrupted():
+            raise DownloadCancelled("Download cancelled")
 
-    total, ranged = await loop.run_in_executor(None, _probe_size, url)
-    pieces: list[tuple[int, int | None]] = list(_piece_ranges(total, PIECE_SIZE)) if ranged else [(0, None)]
-    await loop.run_in_executor(None, _prepare_target, path, total)
-    progress = _Progress()
-    cancel = threading.Event()
+          if total_size > 0:
+            progress = (bytes_downloaded / total_size) * 100
+            model.downloadProgress.status = custom.ModelManagerSP.DownloadStatus.downloading
+            model.downloadProgress.progress = progress
+            model.downloadProgress.eta = self._calculate_eta(model.fileName, progress)
+            self._sync_artifact_progress(model)
+            self._report_status()
 
-    with ThreadPoolExecutor(max_workers=MAX_CONCURRENT_PIECES) as pool:
-      tasks = [loop.run_in_executor(pool, _fetch_piece, url, path, i, start, end, progress, cancel, self._block_size)
-               for i, (start, end) in enumerate(pieces)]
-      try:
-        await self._report_until_done(tasks, artifact, progress, total)
-      except BaseException as e:
-        cancel.set()
-        if isinstance(e, DownloadCancelled):
-          artifact.downloadProgress.canceling = True
-          self._set_progress(artifact, custom.ModelManagerSP.DownloadStatus.downloading, artifact.downloadProgress.progress)
-        for task in tasks:
-          task.cancel()  # drops queued pieces; running ones see the event at their next block
-        await asyncio.gather(*tasks, return_exceptions=True)
-        raise
-    del self._download_start_times[artifact.fileName]
+    # Clean up start time after download completes
+    del self._download_start_times[model.fileName]
 
   async def _process_artifact(self, artifact, destination_path: str) -> None:
     if not artifact.downloadUri.uri:
@@ -226,30 +119,33 @@ class ModelManagerSP:
     expected_hash = artifact.downloadUri.sha256
     filename = artifact.fileName
     full_path = os.path.join(destination_path, filename)
-    status = custom.ModelManagerSP.DownloadStatus
-    artifact.downloadProgress.canceling = False
 
     try:
-      self._set_progress(artifact, status.verifying, 0)
       if await verify_file(full_path, expected_hash):
-        self._set_progress(artifact, status.cached, 100)
+        artifact.downloadProgress.status = custom.ModelManagerSP.DownloadStatus.cached
+        artifact.downloadProgress.progress = 100
+        artifact.downloadProgress.eta = 0
+        self._sync_artifact_progress(artifact)
+        self._report_status()
         return
 
-      self._set_progress(artifact, status.downloading, 0)
       await self._download_file(url, full_path, artifact)
-      self._set_progress(artifact, status.verifying, 99)
       if not await verify_file(full_path, expected_hash):
         raise ValueError(f"Hash validation failed for {filename}")
 
-      self._set_progress(artifact, status.downloaded, 100)
+      artifact.downloadProgress.status = custom.ModelManagerSP.DownloadStatus.downloaded
+      artifact.downloadProgress.progress = 100
+      artifact.downloadProgress.eta = 0
+      self._sync_artifact_progress(artifact)
+      self._report_status()
 
     except DownloadCancelled:
       self._download_start_times.pop(artifact.fileName, None)
-      artifact.downloadProgress.status = status.failed
+      artifact.downloadProgress.status = custom.ModelManagerSP.DownloadStatus.failed
       artifact.downloadProgress.eta = 0
       self._sync_artifact_progress(artifact)
       if self.selected_bundle:
-        self.selected_bundle.status = status.failed
+        self.selected_bundle.status = custom.ModelManagerSP.DownloadStatus.failed
       self._report_status()
       raise
 
@@ -257,11 +153,11 @@ class ModelManagerSP:
       cloudlog.error(f"Error downloading {filename}: {str(e)}")
       if os.path.isfile(full_path):  # noqa: ASYNC240
         os.remove(full_path)
-      artifact.downloadProgress.status = status.failed
+      artifact.downloadProgress.status = custom.ModelManagerSP.DownloadStatus.failed
       artifact.downloadProgress.eta = 0
       self._sync_artifact_progress(artifact)
       if self.selected_bundle:
-        self.selected_bundle.status = status.failed
+        self.selected_bundle.status = custom.ModelManagerSP.DownloadStatus.failed
       self._report_status()
       self._download_start_times.pop(artifact.fileName, None)
       raise
@@ -376,7 +272,12 @@ class ModelManagerSP:
         rk.keep_time()
 
   def clear_model_cache(self) -> None:
-    """ Clears the model cache directory of all files except those in the active model bundle."""
+    """
+    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)
     active_files = []
     for source in ACTIVE_BUNDLE_KEYS:
       if selected_bundle := get_selected_bundle(self.params, source):
@@ -384,6 +285,7 @@ class ModelManagerSP:
           if model.artifact.fileName:
             active_files.append(model.artifact.fileName)
 
+    # Remove all files except active ones
     model_dir = Paths.model_root()
     try:
       for filename in os.listdir(model_dir):

openpilot/sunnypilot/sunnylink/settings_ui.json

@@ -2021,8 +2021,14 @@
         {
           "id": "model_behavior",
           "title": "Model Behavior",
-          "description": "Lane desire and lead-vehicle awareness tuning",
+          "description": "Lane desire, blended laneful, and lead-vehicle awareness tuning",
           "items": [
+            {
+              "key": "Laneful",
+              "widget": "toggle",
+              "title": "Use Blended Laneful Mode",
+              "description": "Nudges the model's path toward lane center with a smoothly ramped correction that scales with lane-line confidence. It fades out automatically when lines are unclear, mid-lane-change, during turns, or when the model is going around something, so you keep laneless behavior plus extra centering."
+            },
             {
               "key": "LaneTurnDesire",
               "widget": "toggle",

openpilot/sunnypilot/sunnylink/settings_ui_src/pages/models.yaml

@@ -9,8 +9,14 @@ description: Driving model behavior and camera calibration
 sections:
 - id: model_behavior
   title: Model Behavior
-  description: Lane desire and lead-vehicle awareness tuning
+  description: Lane desire, blended laneful, and lead-vehicle awareness tuning
   items:
+  - key: Laneful
+    widget: toggle
+    title: Use Blended Laneful Mode
+    description: Nudges the model's path toward lane center with a smoothly ramped correction that scales with
+      lane-line confidence. It fades out automatically when lines are unclear, mid-lane-change, during turns,
+      or when the model is going around something, so you keep laneless behavior plus extra centering.
   - key: LaneTurnDesire
     widget: toggle
     title: Use Lane Turn Desires

openpilot/system/ui/sunnypilot/widgets/download_status.py

@@ -57,7 +57,7 @@ class DownloadStatusAction(ItemAction):
     self.icon: str | None = None
     self.icon_color: rl.Color | None = None
     self._font = gui_app.font(FontWeight.NORMAL)
-    # raw progress arrives in steps, one per progress report from the manager
+    # raw progress arrives in steps, one per 128KB chunk the manager publishes
     self._progress = FirstOrderFilter(0.0, 0.5, 1 / gui_app.target_fps)
     # integrated per frame; (t * speed) % span jumps whenever the fill width changes
     self._sweep = 0.0