diffract-core 0.2.2__tar.gz → 0.3.1__tar.gz

{diffract_core-0.2.2 → diffract_core-0.3.1}/.gitignore

@@ -2,6 +2,9 @@
 model_checkpoints
 .diffract
 
+# Benchmark reports (machine-specific; regenerated by scripts/bench_pipeline.py)
+bench_pipeline_results*.json
+
 # Byte-compiled / optimized
 __pycache__/
 *.py[cod]
@@ -75,6 +78,7 @@ instance/
 # Sphinx documentation
 docs/_build/
 docs/reference/_generated/
+docs/reference/metrics/_generated_table.md
 
 # PyBuilder
 target/

{diffract_core-0.2.2 → diffract_core-0.3.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: diffract-core
-Version: 0.2.2
+Version: 0.3.1
 Summary: Spectral analysis of neural network weights and their evolution over training
 Project-URL: Homepage, https://github.com/Risk-AI-Research/diffract
 Project-URL: Documentation, https://risk-ai-research.github.io/diffract/
@@ -41,6 +41,8 @@ Requires-Dist: polars>=0.20.0; extra == 'all'
 Requires-Dist: pyyaml>=6.0.1; extra == 'all'
 Requires-Dist: taichi>=1.7.3; extra == 'all'
 Requires-Dist: torch>=2.7.0; extra == 'all'
+Provides-Extra: bench
+Requires-Dist: psutil>=5.9.0; extra == 'bench'
 Provides-Extra: common
 Requires-Dist: hydra-core>=1.3.0; extra == 'common'
 Requires-Dist: kaleido>=0.2.1; extra == 'common'
@@ -53,6 +55,7 @@ Provides-Extra: dev
 Requires-Dist: bandit[toml]>=1.7.5; extra == 'dev'
 Requires-Dist: fsspec>=2024.2.0; extra == 'dev'
 Requires-Dist: hydra-core>=1.3.0; extra == 'dev'
+Requires-Dist: hypothesis>=6.0.0; extra == 'dev'
 Requires-Dist: interrogate>=1.7.0; extra == 'dev'
 Requires-Dist: kaleido>=0.2.1; extra == 'dev'
 Requires-Dist: mypy>=1.10.1; extra == 'dev'
@@ -61,6 +64,7 @@ Requires-Dist: pandas>=2.1.0; extra == 'dev'
 Requires-Dist: plotly>=6.0.0; extra == 'dev'
 Requires-Dist: polars>=0.20.0; extra == 'dev'
 Requires-Dist: pre-commit>=3.6.0; extra == 'dev'
+Requires-Dist: psutil>=5.9.0; extra == 'dev'
 Requires-Dist: pytest-cov>=4.0.0; extra == 'dev'
 Requires-Dist: pytest-mock>=3.12.0; extra == 'dev'
 Requires-Dist: pytest-timeout>=2.4.0; extra == 'dev'
@@ -81,6 +85,7 @@ Requires-Dist: sphinx-autodoc-typehints>=1.25.0; extra == 'docs'
 Requires-Dist: sphinx-copybutton>=0.5.0; extra == 'docs'
 Requires-Dist: sphinx-design>=0.6.0; extra == 'docs'
 Requires-Dist: sphinx>=7.0.0; extra == 'docs'
+Requires-Dist: sphinxcontrib-bibtex>=2.6.0; extra == 'docs'
 Requires-Dist: sphinxext-opengraph>=0.9.0; extra == 'docs'
 Provides-Extra: flax
 Requires-Dist: flax>=0.10.0; extra == 'flax'
@@ -128,7 +133,8 @@ Description-Content-Type: text/markdown
 [![Docs](https://img.shields.io/badge/docs-github.io-blue)](https://risk-ai-research.github.io/diffract/)
 [![License: Apache 2.0](https://img.shields.io/badge/License-Apache_2.0-blue.svg)](https://opensource.org/licenses/Apache-2.0)
 
-Official library of ["Diffract: Spectral View of LLM Domain Adaptation"](https://openreview.net/forum?id=XBUHoiAGDE)
+Official library of
+["Diffract: Spectral View of LLM Domain Adaptation"](https://openreview.net/forum?id=XBUHoiAGDE)
 (**ICML 2026 Oral**).
 
 Diffract is a Python package for analyzing deep neural network weights and tracking
@@ -145,7 +151,7 @@ dictionaries of NumPy weight matrices.
 
 ## 🚀 Quick Start
 
-Diffract requires Python 3.12. The core package installs without any deep
+Diffract requires Python 3.12 or newer. The core package installs without any deep
 learning framework; heavy dependencies are opt-in extras:
 
 ```bash
@@ -156,10 +162,9 @@ pip install "diffract-core[taichi]"      # + accelerated heavy-tailed fits and p
 pip install "diffract-core[all]"         # torch + viz + taichi + pandas/polars exports
 ```
 
-Further extras: `frameworks` (TensorFlow, Flax, ONNX), `pandas` / `polars`
-(DataFrame exports), `zarr` (cloud storage), `redis` (shared cache),
-`notebooks` (tooling for the example notebooks). The quotes around
-`"diffract-core[...]"` matter in zsh.
+Further extras: `frameworks` (TensorFlow, Flax, ONNX), `pandas` / `polars` (DataFrame
+exports), `zarr` (cloud storage), `redis` (shared cache), `notebooks` (tooling for the
+example notebooks). The quotes around `"diffract-core[...]"` matter in zsh.
 
 ### Development Install
 
@@ -167,7 +172,7 @@ Further extras: `frameworks` (TensorFlow, Flax, ONNX), `pandas` / `polars`
 # Install uv if you haven't already
 curl -LsSf https://astral.sh/uv/install.sh | sh
 
-# Clone and install (uv provisions Python 3.12 automatically)
+# Clone and install (uv provisions the right Python automatically)
 git clone https://github.com/Risk-AI-Research/diffract.git
 cd diffract
 uv sync --extra dev --extra torch
@@ -220,7 +225,7 @@ internal structure:
 
 <br>
 
-## 🔑 Key Features
+## Key Features
 
 - **Session-based API**: Simple `models.add`, `compute.apply`, and
   `results.export_metrics` workflow.
@@ -233,9 +238,12 @@ internal structure:
   HDF5, SQLite, Zarr, and hybrid backends.
 
 - **Kernel Apply Levels**: Kernels can work at multiple levels:
+
   - **PARAMETER** - Operate on individual weight matrices.
   - **IN_MODEL** - Aggregate within a single model.
-  - **CROSS_MODEL** - Compare or aggregate across models.
+  - **CROSS_MODEL** - Compare or aggregate across models. Pairwise comparisons
+    (the alignment/overlap family) compare exactly two models—scope to a pair with
+    `filter(model_ids=[a, b])`.
 
 - **Built-in Visualization**: Publication-ready Plotly plots with theming support.
 
@@ -258,7 +266,9 @@ session = Session()
 
 with session:
     session.models.add(torch_model)  # torch.nn.Module
-    session.models.add(torch_state_dict, model_id="checkpoint")  # Dict[str, torch.Tensor]
+    session.models.add(
+        torch_state_dict, model_id="checkpoint"
+    )  # Dict[str, torch.Tensor]
     session.models.add(numpy_weights, model_id="raw-weights")  # Dict[str, np.ndarray]
     session.models.add(onnx_model, model_id="onnx-model")  # onnx.ModelProto
     session.models.add(flax_model, model_id="flax-model")  # flax.linen.Module
@@ -274,6 +284,10 @@ session.compute.apply("frob_norm", "stable_rank")
 session.compute.apply("pl_ks")  # has many dependencies—all resolved automatically
 ```
 
+Every built-in metric—its formula, apply level, required inputs, and configuration—is
+catalogued in the
+[metrics reference](https://risk-ai-research.github.io/diffract/reference/metrics/).
+
 ### Filtering Parameters
 
 Filter computations by model, parameter type, or name:
@@ -309,16 +323,21 @@ with attn:
 Export results in various formats (`pandas`, `polars`, `dict`, `json`, or `list`):
 
 ```python
-scalars_df = session.results.export_metrics("stable_rank", export_format="pandas")
-aggregates_df = session.results.export_aggregates(
-    "stable_rank", export_format="pandas"
-)
-
-# Other formats work the same way
-results = session.results.export_metrics("stable_rank", export_format="polars")
-results = session.results.export_metrics("stable_rank", export_format="dict")
-results = session.results.export_metrics("stable_rank", export_format="json")
-results = session.results.export_metrics("stable_rank", export_format="list")
+with session:
+    session.compute.apply("stable_rank", "log_norm")
+
+    # PARAMETER-level fields come from export_metrics
+    scalars_df = session.results.export_metrics("stable_rank", export_format="pandas")
+    # IN_MODEL / CROSS_MODEL fields come from export_aggregates
+    aggregates_df = session.results.export_aggregates(
+        "log_norm", export_format="pandas"
+    )
+
+    # Other formats work the same way
+    results = session.results.export_metrics("stable_rank", export_format="polars")
+    results = session.results.export_metrics("stable_rank", export_format="dict")
+    results = session.results.export_metrics("stable_rank", export_format="json")
+    results = session.results.export_metrics("stable_rank", export_format="list")
 ```
 
 ### Visualization
@@ -352,9 +371,22 @@ List and configure kernels at runtime:
 ```python
 session.compute.list_available_kernels(verbose=True)
 session.compute.list_available_metrics(verbose=True)
-session.compute.configure_kernel("hard_rank", threshold=1e-6)
+session.compute.configure_kernel("hard_rank", rtol=1e-6)
 ```
 
+Configuration takes effect when a kernel executes. Fields already stored are reused
+as-is — `apply` skips them by field presence, without comparing stored values to the
+current configuration. To recompute under a new configuration, erase the stored fields
+first:
+
+```python
+session.results.erase("hard_rank")
+session.compute.apply("hard_rank")  # computes with rtol=1e-6
+```
+
+See [kernel configuration](https://risk-ai-research.github.io/diffract/guide/recipes/kernels_and_compute.html)
+for the erase-then-apply pattern with multi-output kernels and dependent fields.
+
 ### Session Management
 
 Parameters and results stay available whenever the session is reopened. `Session()`
@@ -403,8 +435,11 @@ You can also override the registered name and output fields:
 
 ```python
 with session:
+
     @session.compute.kernel(name="scaled_metric", produce_fields=["scaled_result"])
-    def custom_analysis(frob_norm: float, stable_rank: float, *, weight: float = 0.5) -> float:
+    def custom_analysis(
+        frob_norm: float, stable_rank: float, *, weight: float = 0.5
+    ) -> float:
         """Custom analysis combining multiple metrics."""
         return weight * frob_norm + (1 - weight) * stable_rank
 ```
@@ -449,9 +484,9 @@ Diffract offers built-in **profiles** for common setups:
 from diffract import Session
 
 # Use a profile (recommended for most users)
-session = Session(profile="ram")      # fast, temporary
-session = Session(profile="local")    # persistent, simple
-session = Session(profile="hybrid")   # persistent, optimized for large arrays
+session = Session(profile="ram")  # fast, temporary
+session = Session(profile="local")  # persistent, simple
+session = Session(profile="hybrid")  # persistent, optimized for large arrays
 
 # Or use a custom config file for full control
 session = Session(config_path="my_config.ini")
@@ -497,12 +532,14 @@ max_workers = 4
 
 ## 📚 Documentation
 
-The documentation site is sourced from `docs/` and built with Sphinx + MyST. Install the
-tooling via `uv sync --extra docs` and run `make docs` to render the HTML locally.
+The documentation is hosted at
+[risk-ai-research.github.io/diffract](https://risk-ai-research.github.io/diffract/). It
+is sourced from `docs/` and built with Sphinx + MyST; `uv sync --extra docs` and
+`make docs` render the HTML locally.
 
 <br>
 
-## 📝 Citation
+## Citation
 
 If you use Diffract or build on the paper, please cite:
 
@@ -518,14 +555,14 @@ If you use Diffract or build on the paper, please cite:
 
 <br>
 
-## ❤️ Contributions
+## Contributions
 
-Contributions are welcome! Fork the repo, create a feature branch, and submit a PR. Use
-`make lint` and `make test` to validate your changes.
+Contributions are welcome — see [CONTRIBUTING.md](CONTRIBUTING.md) for the development
+setup, the checks CI runs, and the design principles.
 
 <br>
 
-## 📄 License
+## License
 
 Licensed under the Apache License 2.0 — see [LICENSE](LICENSE). Copyright 2026 Risk AI
 Research.

{diffract_core-0.2.2 → diffract_core-0.3.1}/README.md

@@ -6,7 +6,8 @@
 [![Docs](https://img.shields.io/badge/docs-github.io-blue)](https://risk-ai-research.github.io/diffract/)
 [![License: Apache 2.0](https://img.shields.io/badge/License-Apache_2.0-blue.svg)](https://opensource.org/licenses/Apache-2.0)
 
-Official library of ["Diffract: Spectral View of LLM Domain Adaptation"](https://openreview.net/forum?id=XBUHoiAGDE)
+Official library of
+["Diffract: Spectral View of LLM Domain Adaptation"](https://openreview.net/forum?id=XBUHoiAGDE)
 (**ICML 2026 Oral**).
 
 Diffract is a Python package for analyzing deep neural network weights and tracking
@@ -23,7 +24,7 @@ dictionaries of NumPy weight matrices.
 
 ## 🚀 Quick Start
 
-Diffract requires Python 3.12. The core package installs without any deep
+Diffract requires Python 3.12 or newer. The core package installs without any deep
 learning framework; heavy dependencies are opt-in extras:
 
 ```bash
@@ -34,10 +35,9 @@ pip install "diffract-core[taichi]"      # + accelerated heavy-tailed fits and p
 pip install "diffract-core[all]"         # torch + viz + taichi + pandas/polars exports
 ```
 
-Further extras: `frameworks` (TensorFlow, Flax, ONNX), `pandas` / `polars`
-(DataFrame exports), `zarr` (cloud storage), `redis` (shared cache),
-`notebooks` (tooling for the example notebooks). The quotes around
-`"diffract-core[...]"` matter in zsh.
+Further extras: `frameworks` (TensorFlow, Flax, ONNX), `pandas` / `polars` (DataFrame
+exports), `zarr` (cloud storage), `redis` (shared cache), `notebooks` (tooling for the
+example notebooks). The quotes around `"diffract-core[...]"` matter in zsh.
 
 ### Development Install
 
@@ -45,7 +45,7 @@ Further extras: `frameworks` (TensorFlow, Flax, ONNX), `pandas` / `polars`
 # Install uv if you haven't already
 curl -LsSf https://astral.sh/uv/install.sh | sh
 
-# Clone and install (uv provisions Python 3.12 automatically)
+# Clone and install (uv provisions the right Python automatically)
 git clone https://github.com/Risk-AI-Research/diffract.git
 cd diffract
 uv sync --extra dev --extra torch
@@ -98,7 +98,7 @@ internal structure:
 
 <br>
 
-## 🔑 Key Features
+## Key Features
 
 - **Session-based API**: Simple `models.add`, `compute.apply`, and
   `results.export_metrics` workflow.
@@ -111,9 +111,12 @@ internal structure:
   HDF5, SQLite, Zarr, and hybrid backends.
 
 - **Kernel Apply Levels**: Kernels can work at multiple levels:
+
   - **PARAMETER** - Operate on individual weight matrices.
   - **IN_MODEL** - Aggregate within a single model.
-  - **CROSS_MODEL** - Compare or aggregate across models.
+  - **CROSS_MODEL** - Compare or aggregate across models. Pairwise comparisons
+    (the alignment/overlap family) compare exactly two models—scope to a pair with
+    `filter(model_ids=[a, b])`.
 
 - **Built-in Visualization**: Publication-ready Plotly plots with theming support.
 
@@ -136,7 +139,9 @@ session = Session()
 
 with session:
     session.models.add(torch_model)  # torch.nn.Module
-    session.models.add(torch_state_dict, model_id="checkpoint")  # Dict[str, torch.Tensor]
+    session.models.add(
+        torch_state_dict, model_id="checkpoint"
+    )  # Dict[str, torch.Tensor]
     session.models.add(numpy_weights, model_id="raw-weights")  # Dict[str, np.ndarray]
     session.models.add(onnx_model, model_id="onnx-model")  # onnx.ModelProto
     session.models.add(flax_model, model_id="flax-model")  # flax.linen.Module
@@ -152,6 +157,10 @@ session.compute.apply("frob_norm", "stable_rank")
 session.compute.apply("pl_ks")  # has many dependencies—all resolved automatically
 ```
 
+Every built-in metric—its formula, apply level, required inputs, and configuration—is
+catalogued in the
+[metrics reference](https://risk-ai-research.github.io/diffract/reference/metrics/).
+
 ### Filtering Parameters
 
 Filter computations by model, parameter type, or name:
@@ -187,16 +196,21 @@ with attn:
 Export results in various formats (`pandas`, `polars`, `dict`, `json`, or `list`):
 
 ```python
-scalars_df = session.results.export_metrics("stable_rank", export_format="pandas")
-aggregates_df = session.results.export_aggregates(
-    "stable_rank", export_format="pandas"
-)
-
-# Other formats work the same way
-results = session.results.export_metrics("stable_rank", export_format="polars")
-results = session.results.export_metrics("stable_rank", export_format="dict")
-results = session.results.export_metrics("stable_rank", export_format="json")
-results = session.results.export_metrics("stable_rank", export_format="list")
+with session:
+    session.compute.apply("stable_rank", "log_norm")
+
+    # PARAMETER-level fields come from export_metrics
+    scalars_df = session.results.export_metrics("stable_rank", export_format="pandas")
+    # IN_MODEL / CROSS_MODEL fields come from export_aggregates
+    aggregates_df = session.results.export_aggregates(
+        "log_norm", export_format="pandas"
+    )
+
+    # Other formats work the same way
+    results = session.results.export_metrics("stable_rank", export_format="polars")
+    results = session.results.export_metrics("stable_rank", export_format="dict")
+    results = session.results.export_metrics("stable_rank", export_format="json")
+    results = session.results.export_metrics("stable_rank", export_format="list")
 ```
 
 ### Visualization
@@ -230,9 +244,22 @@ List and configure kernels at runtime:
 ```python
 session.compute.list_available_kernels(verbose=True)
 session.compute.list_available_metrics(verbose=True)
-session.compute.configure_kernel("hard_rank", threshold=1e-6)
+session.compute.configure_kernel("hard_rank", rtol=1e-6)
 ```
 
+Configuration takes effect when a kernel executes. Fields already stored are reused
+as-is — `apply` skips them by field presence, without comparing stored values to the
+current configuration. To recompute under a new configuration, erase the stored fields
+first:
+
+```python
+session.results.erase("hard_rank")
+session.compute.apply("hard_rank")  # computes with rtol=1e-6
+```
+
+See [kernel configuration](https://risk-ai-research.github.io/diffract/guide/recipes/kernels_and_compute.html)
+for the erase-then-apply pattern with multi-output kernels and dependent fields.
+
 ### Session Management
 
 Parameters and results stay available whenever the session is reopened. `Session()`
@@ -281,8 +308,11 @@ You can also override the registered name and output fields:
 
 ```python
 with session:
+
     @session.compute.kernel(name="scaled_metric", produce_fields=["scaled_result"])
-    def custom_analysis(frob_norm: float, stable_rank: float, *, weight: float = 0.5) -> float:
+    def custom_analysis(
+        frob_norm: float, stable_rank: float, *, weight: float = 0.5
+    ) -> float:
         """Custom analysis combining multiple metrics."""
         return weight * frob_norm + (1 - weight) * stable_rank
 ```
@@ -327,9 +357,9 @@ Diffract offers built-in **profiles** for common setups:
 from diffract import Session
 
 # Use a profile (recommended for most users)
-session = Session(profile="ram")      # fast, temporary
-session = Session(profile="local")    # persistent, simple
-session = Session(profile="hybrid")   # persistent, optimized for large arrays
+session = Session(profile="ram")  # fast, temporary
+session = Session(profile="local")  # persistent, simple
+session = Session(profile="hybrid")  # persistent, optimized for large arrays
 
 # Or use a custom config file for full control
 session = Session(config_path="my_config.ini")
@@ -375,12 +405,14 @@ max_workers = 4
 
 ## 📚 Documentation
 
-The documentation site is sourced from `docs/` and built with Sphinx + MyST. Install the
-tooling via `uv sync --extra docs` and run `make docs` to render the HTML locally.
+The documentation is hosted at
+[risk-ai-research.github.io/diffract](https://risk-ai-research.github.io/diffract/). It
+is sourced from `docs/` and built with Sphinx + MyST; `uv sync --extra docs` and
+`make docs` render the HTML locally.
 
 <br>
 
-## 📝 Citation
+## Citation
 
 If you use Diffract or build on the paper, please cite:
 
@@ -396,14 +428,14 @@ If you use Diffract or build on the paper, please cite:
 
 <br>
 
-## ❤️ Contributions
+## Contributions
 
-Contributions are welcome! Fork the repo, create a feature branch, and submit a PR. Use
-`make lint` and `make test` to validate your changes.
+Contributions are welcome — see [CONTRIBUTING.md](CONTRIBUTING.md) for the development
+setup, the checks CI runs, and the design principles.
 
 <br>
 
-## 📄 License
+## License
 
 Licensed under the Apache License 2.0 — see [LICENSE](LICENSE). Copyright 2026 Risk AI
 Research.

{diffract_core-0.2.2 → diffract_core-0.3.1}/pyproject.toml

@@ -85,6 +85,7 @@ notebooks = [
     "einops >=0.7.0",
 ]
 taichi = ["taichi >=1.7.3"]
+bench = ["psutil >=5.9.0"]
 all = [
     "torch >=2.7.0",
     "plotly >=6.0.0",
@@ -105,14 +106,17 @@ docs = [
     "sphinx-design >=0.6.0",
     "furo >=2024.8.0",
     "sphinxext-opengraph >=0.9.0",
+    "sphinxcontrib-bibtex >=2.6.0",
 ]
 dev = [
     "bandit[toml] >=1.7.5",
+    "hypothesis >=6.0.0",
     "interrogate >=1.7.0",
     "mypy >=1.10.1",
     "pandas >=2.1.0",
     "polars >=0.20.0",
     "pre-commit >=3.6.0",
+    "psutil >=5.9.0",
     "pytest >=7.4.0",
     "pytest-cov >=4.0.0",
     "pytest-mock >=3.12.0",
@@ -170,8 +174,10 @@ filterwarnings = [
     "ignore::DeprecationWarning",
     "ignore::UserWarning",
     "ignore::PendingDeprecationWarning",
-    # taichi 1.7.x ships a docstring with an invalid escape sequence
-    "ignore::SyntaxWarning:taichi.tools.image",
+    # taichi 1.7.x ships a docstring with an invalid escape sequence; the
+    # compile-time warning is attributed to the importing frame rather than
+    # the module that carries it, so it is matched by message.
+    "ignore:invalid escape sequence:SyntaxWarning",
 ]
 log_cli = true
 log_cli_level = "INFO"
@@ -201,7 +207,6 @@ omit = [
     "*/.venv/*",
     "*/venv/*",
     "*/.tox/*",
-    "src/diffract/core/compute/kernels/*",
 ]
 branch = true
 parallel = true
@@ -225,7 +230,7 @@ exclude_lines = [
 ]
 show_missing = true
 precision = 2
-fail_under = 65
+fail_under = 67
 skip_covered = false
 skip_empty = false
 
@@ -294,11 +299,3 @@ check-hidden = true
 name = "pypi"
 url = "https://pypi.org/simple"
 explicit = false
-
-[tool.commitizen]
-name = "cz_conventional_commits"
-tag_format = "v$version"
-version_scheme = "pep440"
-version_provider = "uv"
-update_changelog_on_bump = true
-major_version_zero = true

{diffract_core-0.2.2 → diffract_core-0.3.1}/ruff.toml

@@ -187,8 +187,16 @@ dummy-variable-rgx = "^(_+|(_+[a-zA-Z0-9_]*[a-zA-Z0-9]+?))$"
     "PLR0913", # Too many arguments
     "PLR0915", # Too many statements
     "ARG001", # Unused function argument
+    "ARG002", # Unused method argument (fixtures, mock signatures)
+    "ARG005", # Unused lambda argument (stub implementations)
     "FBT001", # Boolean positional argument
     "PT011",  # pytest.raises() is too broad
+    "PLR2004", # Literal expectations are the substance of an assertion
+    "SLF001", # Tests exercise private members deliberately
+    "INP001", # Test directories are namespace packages by design
+    "PLC0415", # Imports inside tests control DI wiring order
+    "S108",   # /tmp only appears as literal data in config-parsing asserts
+    "S110",   # try/except/pass in teardown paths
 ]
 "notebooks/*" = [
     "D",      # Docstring requirements

{diffract_core-0.2.2 → diffract_core-0.3.1}/src/diffract/__init__.py

@@ -22,9 +22,10 @@ from __future__ import annotations
 import importlib
 from typing import TYPE_CHECKING, Any
 
-__version__ = "0.2.2"
+__version__ = "0.3.1"
 
 from .containers import list_profiles
+from .core.data.metadata import upgrade_metadata_index
 from .core.data.nn.params.schema import ParameterType
 from .session import ParameterOverrides, Session
 
@@ -37,6 +38,7 @@ __all__ = [
     "Session",
     "__version__",
     "list_profiles",
+    "upgrade_metadata_index",
     "viz",
 ]
 

{diffract_core-0.2.2 → diffract_core-0.3.1}/src/diffract/configs/hybrid.ini

@@ -71,4 +71,5 @@ max_workers = 8
 skip_not_implemented_types = true
 
 [export]
-default_export_format = "pandas"
+# Formats beyond "dict"/"json"/"list" need their optional extra installed.
+default_export_format = "dict"

{diffract_core-0.2.2 → diffract_core-0.3.1}/src/diffract/configs/sqlite.ini

@@ -59,4 +59,5 @@ max_workers = 8
 skip_not_implemented_types = true
 
 [export]
-default_export_format = "pandas"
+# Formats beyond "dict"/"json"/"list" need their optional extra installed.
+default_export_format = "dict"

{diffract_core-0.2.2 → diffract_core-0.3.1}/src/diffract/containers.py

@@ -25,6 +25,7 @@ from .core.compute.containers import (
     ComputeSingletonContainerWiringConfig,
 )
 from .core.data.metadata.containers import MetadataContainer
+from .core.data.metadata.sqlite_index import IN_MEMORY_DATABASE
 from .core.data.nn.containers import ModelParametersContainer
 from .core.export.containers import ExportContainer
 from .core.parallel import ParallelSingletonContainer
@@ -42,6 +43,10 @@ PROFILES: dict[str, str] = {
     "hybrid": "configs/hybrid.ini",
 }
 
+# Backend sentinels that occupy a "path" key without naming a file. They are
+# carried verbatim so a backend can recognize them by equality.
+_NON_FILESYSTEM_PATH_VALUES: frozenset[str] = frozenset({IN_MEMORY_DATABASE})
+
 
 def list_profiles() -> list[str]:
     """Return available profile names."""
@@ -176,8 +181,10 @@ class MainContainer(containers.DeclarativeContainer):
     # Configuration
     config = providers.Configuration()
 
-    # Logging configuration
-    logging_config = providers.Resource(
+    # Callable, not Resource: logging is configured once at build and must stay
+    # out of the init_resources()/shutdown_resources() lifecycle, which would
+    # otherwise re-run dictConfig on every context entry and reset user handlers.
+    logging_config = providers.Callable(
         "logging.config.dictConfig",
         config=config.logging,
     )
@@ -371,6 +378,8 @@ def create_main_container(
                 if k != key or not isinstance(v, str):
                     continue
                 value = v.strip().strip('"')
+                if value in _NON_FILESYSTEM_PATH_VALUES:
+                    continue
                 if value.startswith(("ext://", "/", "~")):
                     continue
                 cur[k] = str(base_path / value)

{diffract_core-0.2.2 → diffract_core-0.3.1}/src/diffract/core/__init__.py

@@ -1,23 +1,17 @@
 """Core module for diffract."""
 
 from diffract.core.constants import (
-    CONTEXT_SEPARATOR,
     HDF5_INDEX_DATASET,
     HDF5_INDEX_GROUP,
     HDF5_INDEX_TOMBSTONE,
-    MODELS_CONTEXT_PREFIX,
-    PARAMS_CONTEXT_PREFIX,
     REGEX_PREFIX,
     WEIGHTS_FIELD,
 )
 
 __all__ = [
-    "CONTEXT_SEPARATOR",
     "HDF5_INDEX_DATASET",
     "HDF5_INDEX_GROUP",
     "HDF5_INDEX_TOMBSTONE",
-    "MODELS_CONTEXT_PREFIX",
-    "PARAMS_CONTEXT_PREFIX",
     "REGEX_PREFIX",
     "WEIGHTS_FIELD",
 ]

{diffract_core-0.2.2 → diffract_core-0.3.1}/src/diffract/core/cache/interface.py

@@ -70,9 +70,11 @@ class ICacheManager(Protocol):
         Args:
             obj_uid: Unique identifier for the cached object.
             field_name: Name of the field to store.
-            value: Value to cache (must be pickle-serializable).
+            value: Value to cache. Must be a numpy array, a JSON-serializable
+                value, or bytes.
 
         Raises:
+            ValueError: If the value is not a supported kind.
             Exception: If storage operation fails.
         """
         ...