hflow 0.2.2__tar.gz → 0.2.3__tar.gz

{hflow-0.2.2 → hflow-0.2.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: hflow
-Version: 0.2.2
+Version: 0.2.3
 Summary: Open source SDK for building Physical AI data pipelines
 Keywords: airflow,data-pipeline,data-quality,dataset-curation,mcap,physical-ai,robotics
 Author: Hebbian Robotics, Kingston Kuan, Brandon Ong
@@ -14,10 +14,10 @@ Requires-Dist: mcap-ros2-support>=0.5.7
 Requires-Dist: numpy>=2.4.6
 Requires-Dist: zstandard>=0.25.0
 Requires-Dist: pyarrow>=25.0.1 ; extra == 'arrow'
-Requires-Dist: obstore>=0.10.0 ; extra == 'bucket'
-Requires-Dist: mediapipe>=1.0.0 ; extra == 'mediapipe'
-Requires-Dist: opencv-python-headless>=4.10 ; extra == 'motion'
-Requires-Dist: openai>=3.0.0 ; extra == 'openai'
+Requires-Dist: obstore>=0.11.1 ; extra == 'bucket'
+Requires-Dist: mediapipe>=1.0.1 ; extra == 'mediapipe'
+Requires-Dist: opencv-python-headless>=5.0.0.93 ; extra == 'motion'
+Requires-Dist: openai>=3.3.1 ; extra == 'openai'
 Requires-Python: >=3.11
 Project-URL: Repository, https://github.com/Hebbian-Robotics/hflow
 Project-URL: Documentation, https://github.com/Hebbian-Robotics/hflow/tree/main/docs
@@ -87,7 +87,7 @@ episode.
 
 | | HFlow's boundary |
 | --- | --- |
-| **Input** | One multimodal episode per standard MCAP file (`hflow doctor` says whether yours qualifies) |
+| **Input** | One multimodal episode per supported standard MCAP file (`hflow doctor` reports canonical gaps) |
 | **Processing** | Your Python transforms, checks, labels, and enrichments |
 | **Execution** | In-process for development; generated Airflow 3 DAGs for scheduled runs |
 | **Durable output** | Canonical MCAP episodes, provenance, artifacts, and a Parquet catalog |
@@ -135,10 +135,9 @@ the trust model, and the current limits.
 
 ## Community and hosted interest
 
-<!-- Add the Google Form link to the entry below once it is live. -->
-
-- **Hosted version interest:** Google Form coming soon.
+- **Hosted platform waitlist:** [tell us about your workflow](https://forms.gle/EZpQpGGF3eJomx498).
 - **Community Discord:** [join us](https://discord.gg/vacepQvjmg) for questions, feedback, and contribution discussion.
+- **Code of conduct:** review our [community standards](./CODE_OF_CONDUCT.md) and report concerns privately.
 
 For reproducible bugs and scoped feature requests, use
 [GitHub issues](https://github.com/Hebbian-Robotics/hflow/issues).

{hflow-0.2.2 → hflow-0.2.3}/README.md

@@ -56,7 +56,7 @@ episode.
 
 | | HFlow's boundary |
 | --- | --- |
-| **Input** | One multimodal episode per standard MCAP file (`hflow doctor` says whether yours qualifies) |
+| **Input** | One multimodal episode per supported standard MCAP file (`hflow doctor` reports canonical gaps) |
 | **Processing** | Your Python transforms, checks, labels, and enrichments |
 | **Execution** | In-process for development; generated Airflow 3 DAGs for scheduled runs |
 | **Durable output** | Canonical MCAP episodes, provenance, artifacts, and a Parquet catalog |
@@ -104,10 +104,9 @@ the trust model, and the current limits.
 
 ## Community and hosted interest
 
-<!-- Add the Google Form link to the entry below once it is live. -->
-
-- **Hosted version interest:** Google Form coming soon.
+- **Hosted platform waitlist:** [tell us about your workflow](https://forms.gle/EZpQpGGF3eJomx498).
 - **Community Discord:** [join us](https://discord.gg/vacepQvjmg) for questions, feedback, and contribution discussion.
+- **Code of conduct:** review our [community standards](./CODE_OF_CONDUCT.md) and report concerns privately.
 
 For reproducible bugs and scoped feature requests, use
 [GitHub issues](https://github.com/Hebbian-Robotics/hflow/issues).

{hflow-0.2.2 → hflow-0.2.3}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "hflow"
-version = "0.2.2"
+version = "0.2.3"
 description = "Open source SDK for building Physical AI data pipelines"
 readme = "README.md"
 license = "Apache-2.0"
@@ -36,10 +36,10 @@ name = "Brandon Ong"
 
 [project.optional-dependencies]
 arrow = ["pyarrow>=25.0.1"]
-bucket = ["obstore>=0.10.0"]
-mediapipe = ["mediapipe>=1.0.0"]
-motion = ["opencv-python-headless>=4.10"]
-openai = ["openai>=3.0.0"]
+bucket = ["obstore>=0.11.1"]
+mediapipe = ["mediapipe>=1.0.1"]
+motion = ["opencv-python-headless>=5.0.0.93"]
+openai = ["openai>=3.3.1"]
 
 [project.urls]
 Repository = "https://github.com/Hebbian-Robotics/hflow"
@@ -52,25 +52,28 @@ hflow = "hflow.cli:main"
 [dependency-groups]
 dev = [
     "hflow-server",
-    "httpx2>=2.10",
-    "obstore>=0.10.0",
-    "opencv-python-headless>=4.10",
+    "httpx2>=2.12.0",
+    "obstore>=0.11.1",
+    "opencv-python-headless>=5.0.0.93",
     "pyarrow>=25.0.1",
     "pytest>=9.1.1",
     "pyyaml>=6.0.3",
-    "ruff>=0.16.2",
-    "ty>=0.0.71",
+    "ruff>=0.16.4",
+    "ty>=0.0.74",
 ]
 
 [build-system]
-requires = ["uv_build>=0.11.33,<0.12"]
+requires = ["uv_build>=0.12.5,<0.13"]
 build-backend = "uv_build"
 
 [tool.uv]
 exclude-newer = "5 days"
 
 [tool.uv.workspace]
-members = ["packages/*"]
+members = [
+    "packages/*",
+    "examples/build_ai_evaluation",
+]
 
 [tool.uv.sources.hflow-server]
 workspace = true
@@ -120,4 +123,7 @@ unused-ignore-comment = "error"
 possibly-unresolved-reference = "error"
 
 [tool.ty.src]
-exclude = ["examples/openai_vision/"]
+exclude = [
+    "examples/build_ai_evaluation/",
+    "examples/openai_vision/",
+]

{hflow-0.2.2 → hflow-0.2.3}/pyproject.toml.orig

@@ -1,6 +1,6 @@
 [project]
 name = "hflow"
-version = "0.2.2"
+version = "0.2.3"
 description = "Open source SDK for building Physical AI data pipelines"
 readme = "README.md"
 license = "Apache-2.0"
@@ -35,21 +35,21 @@ arrow = ["pyarrow>=25.0.1"]
 # Native object-store data roots (gs://, s3://, az://): obstore is the Rust
 # object_store crate as a single dependency-free wheel; local-path roots
 # never import it.
-bucket = ["obstore>=0.10.0"]
+bucket = ["obstore>=0.11.1"]
 # Hand detection with MediaPipe's Hand Landmarker (hflow.mediapipe_hands).
 # A MODEL, not a signal statistic, so it is opt-in twice over: outside the core
 # install, and outside the dev group as well (unlike motion and bucket, which
 # are mirrored into dev so the suite exercises them). It adds ~430 MB and its
 # own OpenCV; a dev environment opts in with `--extra mediapipe`, exactly as
 # the openai example does.
-mediapipe = ["mediapipe>=1.0.0"]
+mediapipe = ["mediapipe>=1.0.1"]
 # Camera-shake measurement: pyramidal Lucas-Kanade optical flow and a RANSAC
 # similarity fit. No numpy-only equivalent preserves the instrument, and
 # reimplementing them would make it a different, unvalidated one -- so the
 # dependency is real, and confined to the one check that needs it. Headless
 # because a data pipeline runs where there is no display.
-motion = ["opencv-python-headless>=4.10"]
-openai = ["openai>=3.0.0"]
+motion = ["opencv-python-headless>=5.0.0.93"]
+openai = ["openai>=3.3.1"]
 
 [project.urls]
 Repository = "https://github.com/Hebbian-Robotics/hflow"
@@ -64,20 +64,20 @@ dev = [
     "hflow-server", # the workspace API package, present in dev so the suite tests it
     # Starlette's TestClient transport for the hflow-server suite. httpx2, not
     # httpx: starlette 1.6 deprecates the httpx transport in its favour.
-    "httpx2>=2.10",
-    "obstore>=0.10.0", # the bucket extra, present in dev so the suite tests it
+    "httpx2>=2.12.0",
+    "obstore>=0.11.1", # the bucket extra, present in dev so the suite tests it
     # the motion extra, present in dev so the suite tests it rather than
     # skipping the one check that cannot be verified any other way
-    "opencv-python-headless>=4.10",
+    "opencv-python-headless>=5.0.0.93",
     "pyarrow>=25.0.1", # the arrow extra, present in dev so the suite tests it
     "pytest>=9.1.1",
     "pyyaml>=6.0.3",
-    "ruff>=0.16.2",
-    "ty>=0.0.71",
+    "ruff>=0.16.4",
+    "ty>=0.0.74",
 ]
 
 [build-system]
-requires = ["uv_build>=0.11.33,<0.12"]
+requires = ["uv_build>=0.12.5,<0.13"]
 build-backend = "uv_build"
 
 [tool.uv]
@@ -87,7 +87,7 @@ build-backend = "uv_build"
 exclude-newer = "5 days"
 
 [tool.uv.workspace]
-members = ["packages/*"]
+members = ["packages/*", "examples/build_ai_evaluation"]
 
 [tool.uv.sources]
 hflow-server = { workspace = true }
@@ -128,7 +128,7 @@ unused-ignore-comment = "error"
 possibly-unresolved-reference = "error"
 
 [tool.ty.src]
-# examples/openai_vision imports the user's own `openai` client: bundling a
-# VLM client is a non-goal (examples ARE the docs), so the package is
-# deliberately not a dependency and the example is excluded from typechecking.
-exclude = ["examples/openai_vision/"]
+# Workspace examples typecheck themselves with their own dependencies.
+# openai_vision imports the user's optional client, so the root project does
+# not typecheck it either.
+exclude = ["examples/build_ai_evaluation/", "examples/openai_vision/"]

hflow-0.2.3/src/hflow/__main__.py

@@ -0,0 +1,3 @@
+from hflow.cli import main
+
+raise SystemExit(main())

{hflow-0.2.2 → hflow-0.2.3}/src/hflow/_grouped_mcap_writer/_writer.py

@@ -236,6 +236,7 @@ class GroupedMcapWriter:
         self._flush()
 
     def register_schema(self, name: str, encoding: str, data: bytes) -> SchemaId:
+        """Register a schema and return its id for :meth:`register_channel`."""
         self._raise_if_not_active("register a schema")
         schema_id = SchemaId(len(self._schemas_by_id) + 1)
         schema = Schema(id=schema_id, data=data, encoding=encoding, name=name)
@@ -255,6 +256,11 @@ class GroupedMcapWriter:
         group: str,
         metadata: dict[str, str] | None = None,
     ) -> ChannelId:
+        """Register a topic on a named group and return its id for :meth:`write_message`.
+
+        ``schema_id`` must be a prior :meth:`register_schema` return value, or
+        ``NO_SCHEMA_ID`` for schemaless channels.
+        """
         self._raise_if_not_active("register a channel")
         # schema_id 0 is the MCAP spec's "no schema" sentinel.
         if schema_id != NO_SCHEMA_ID and schema_id not in self._schemas_by_id:
@@ -288,6 +294,11 @@ class GroupedMcapWriter:
         publish_time: int | None = None,
         sequence: int = 0,
     ) -> None:
+        """Write one message on a registered channel.
+
+        ``log_time`` and ``publish_time`` are nanoseconds since epoch; when
+        ``publish_time`` is omitted it defaults to ``log_time``.
+        """
         self._raise_if_not_active("write a message")
         group_name = self._group_name_by_channel_id.get(channel_id)
         if group_name is None:
@@ -318,6 +329,7 @@ class GroupedMcapWriter:
             self._finalize_group_chunk(group_name)
 
     def add_metadata(self, name: str, data: dict[str, str]) -> None:
+        """Append an MCAP Metadata record (e.g. episode or provenance stamps)."""
         self._raise_if_not_active("add metadata")
         self._flush()
         offset = self._stream.tell()
@@ -337,6 +349,7 @@ class GroupedMcapWriter:
         log_time: int = 0,
         create_time: int = 0,
     ) -> None:
+        """Append an MCAP Attachment record; times are nanoseconds since epoch."""
         self._raise_if_not_active("add an attachment")
         self._flush()
         offset = self._stream.tell()
@@ -363,6 +376,9 @@ class GroupedMcapWriter:
         self._flush()
 
     def finish(self) -> None:
+        """Finalize the MCAP file. Must be the last mutating call; safe to call
+        again (idempotent). Further writes raise :class:`RuntimeError`.
+        """
         if self._state is _WriterState.FINISHED:
             return
         self._raise_if_not_active("finish")

{hflow-0.2.2 → hflow-0.2.3}/src/hflow/_video_measurements/_camera_motion.py

@@ -7,6 +7,7 @@ from types import ModuleType
 
 import numpy as np
 
+from ._field_guards import require_float
 from ._raw_frames import LUMA_FRAME_FILTER_GRAPH, luma_frames
 from ._toolchain import VideoMeasurementToolchain
 
@@ -51,6 +52,8 @@ class CameraMotionSettings:
     horizontal_field_of_view_degrees: float = DEFAULT_HORIZONTAL_FIELD_OF_VIEW_DEGREES
 
     def __post_init__(self) -> None:
+        require_float(self.frames_per_second, "frames_per_second")
+        require_float(self.horizontal_field_of_view_degrees, "horizontal_field_of_view_degrees")
         if not math.isfinite(self.frames_per_second) or self.frames_per_second <= 0:
             raise ValueError(
                 f"frames_per_second must be finite and positive, got {self.frames_per_second}"

hflow-0.2.3/src/hflow/_video_measurements/_field_guards.py

@@ -0,0 +1,30 @@
+"""Shared numeric-field validation for the video-measurement settings dataclasses.
+
+Range checks alone (``0 <= x <= 100``) do not reject the wrong *type*: ``bool``
+subclasses ``int``, so ``True``/``False`` satisfy every numeric comparison and
+range test the settings below already run, and a ``str``/``None`` would raise
+a bare ``TypeError`` from the comparison itself instead of a clear message
+naming the field. This closes that hole the same way ``catalog.py`` already
+does for interval bounds and measurement values.
+
+These settings are caller-constructed configuration, not measurement-pipeline
+output, so unlike ``catalog.py``'s NumPy-scalar coercion, no NumPy handling is
+added here: a caller building a ``np.float64`` threshold can call ``.item()``
+itself, the same way any other non-native-Python value would need to.
+"""
+
+
+def require_int(value: object, name: str) -> None:
+    """Refuse anything but a plain ``int``, ``bool`` included."""
+    if isinstance(value, bool) or not isinstance(value, int):
+        raise ValueError(f"{name} must be an int, got {type(value).__name__}")
+
+
+def require_float(value: object, name: str) -> None:
+    """Refuse anything but a plain ``int`` or ``float``, ``bool`` included.
+
+    An ``int`` is accepted for a float-declared field: it is a perfectly good
+    float value (``0`` is a real, falsy value that must still pass).
+    """
+    if isinstance(value, bool) or not isinstance(value, int | float):
+        raise ValueError(f"{name} must be an int or float, got {type(value).__name__}")

{hflow-0.2.2 → hflow-0.2.3}/src/hflow/_video_measurements/_frame_statistics.py

@@ -14,6 +14,7 @@ from io import StringIO
 from pathlib import Path
 from typing import Protocol
 
+from ._field_guards import require_float, require_int
 from ._toolchain import VideoMeasurementToolchain
 
 FRAME_STATISTICS_DEFINITION_VERSION = "video-frame-statistics/v1"
@@ -54,6 +55,8 @@ class VideoTimeInterval:
     end_seconds: float
 
     def __post_init__(self) -> None:
+        require_float(self.start_seconds, "start_seconds")
+        require_float(self.end_seconds, "end_seconds")
         if not math.isfinite(self.start_seconds) or self.start_seconds < 0:
             raise ValueError(f"start_seconds must be finite and nonnegative: {self.start_seconds}")
         if not math.isfinite(self.end_seconds) or self.end_seconds < self.start_seconds:
@@ -74,6 +77,14 @@ class FrameStatisticsSettings:
     overexposed_average_luma_threshold: float = 235.0
 
     def __post_init__(self) -> None:
+        require_int(
+            self.black_frame_minimum_pixel_share_percent,
+            "black_frame_minimum_pixel_share_percent",
+        )
+        require_int(self.black_pixel_luma_threshold, "black_pixel_luma_threshold")
+        require_float(self.freeze_noise_tolerance_decibels, "freeze_noise_tolerance_decibels")
+        require_float(self.freeze_minimum_duration_seconds, "freeze_minimum_duration_seconds")
+        require_float(self.overexposed_average_luma_threshold, "overexposed_average_luma_threshold")
         if not 0 <= self.black_frame_minimum_pixel_share_percent <= 100:
             raise ValueError("black_frame_minimum_pixel_share_percent must be between 0 and 100")
         if not 0 <= self.black_pixel_luma_threshold <= 255:
@@ -371,7 +382,11 @@ class _FrameStatisticsAccumulator:
             overexposed_frame_percent=100.0 * self.overexposed_frame_count / frame_count,
             freeze_intervals=tuple(self.freeze_intervals),
             freeze_total_seconds=sum(
-                interval.end_seconds - interval.start_seconds for interval in self.freeze_intervals
+                (
+                    interval.end_seconds - interval.start_seconds
+                    for interval in self.freeze_intervals
+                ),
+                0.0,
             ),
             average_luma_mean=self.average_luma.mean(),
             average_luma_minimum=self.average_luma.minimum(),