runproof-engine 0.1.0__tar.gz

runproof-engine-0.1.0/LICENSE

@@ -0,0 +1,151 @@
+Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+1. Definitions.
+
+"License" shall mean the terms and conditions for use, reproduction, and
+distribution as defined by Sections 1 through 9 of this document.
+
+"Licensor" shall mean the copyright owner or entity authorized by
+the copyright owner that is granting the License.
+
+"Legal Entity" shall mean the union of the acting entity and all
+other entities that control, are controlled by, or are under common control
+with that entity. For the purposes of this definition, "control" means
+(i) the power, direct or indirect, to cause the direction or management of
+such entity, whether by contract or otherwise, or (ii) ownership of fifty
+percent (50%) or more of the outstanding shares, or (iii) beneficial ownership
+of such entity.
+
+"You" (or "Your") shall mean an individual or Legal Entity exercising
+permissions granted by this License.
+
+"Source" form shall mean the preferred form for making modifications,
+including but not limited to software source code, documentation source,
+and configuration files.
+
+"Object" form shall mean any form resulting from mechanical transformation
+or translation of a Source form, including but not limited to compiled
+object code, generated documentation, and conversions to other media types.
+
+"Work" shall mean the work of authorship, whether in Source or Object form,
+made available under the License, as indicated by a copyright notice that is
+included in or attached to the work (an example is provided in the Appendix
+below).
+
+"Derivative Works" shall mean any work, whether in Source or Object form,
+that is based on (or derived from) the Work and for which the editorial
+revisions, annotations, elaborations, or other modifications represent, as a
+whole, an original work of authorship. For the purposes of this License,
+Derivative Works shall not include works that remain separable from, or
+merely link (or bind by name) to the interfaces of, the Work and Derivative
+Works thereof.
+
+"Contribution" shall mean any work of authorship, including the original
+version of the Work and any modifications or additions to that Work or
+Derivative Works thereof, that is intentionally submitted to Licensor for
+inclusion in the Work by the copyright owner or by an individual or Legal
+Entity authorized to submit on behalf of the copyright owner. For the purposes
+of this definition, "submitted" means any form of electronic, verbal, or
+written communication sent to the Licensor or its representatives, including
+but not limited to communication on electronic mailing lists, source code
+control systems, and issue tracking systems that are managed by, or on behalf
+of, the Licensor for the purpose of discussing and improving the Work, but
+excluding communication that is conspicuously marked or otherwise designated
+in writing by the copyright owner as "Not a Contribution."
+
+"Contributor" shall mean Licensor and any individual or Legal Entity on
+behalf of whom a Contribution has been received by Licensor and subsequently
+incorporated within the Work.
+
+2. Grant of Copyright License. Subject to the terms and conditions of this
+License, each Contributor hereby grants to You a perpetual, worldwide,
+non-exclusive, no-charge, royalty-free, irrevocable copyright license to
+reproduce, prepare Derivative Works of, publicly display, publicly perform,
+sublicense, and distribute the Work and such Derivative Works in Source or
+Object form.
+
+3. Grant of Patent License. Subject to the terms and conditions of this
+License, each Contributor hereby grants to You a perpetual, worldwide,
+non-exclusive, no-charge, royalty-free, irrevocable (except as stated in
+this section) patent license to make, have made, use, offer to sell, sell,
+import, and otherwise transfer the Work, where such license applies only to
+those patent claims licensable by such Contributor that are necessarily
+infringed by their Contribution(s) alone or by combination of their
+Contribution(s) with the Work to which such Contribution(s) was submitted.
+
+4. Redistribution. You may reproduce and distribute copies of the Work or
+Derivative Works thereof in any medium, with or without modifications, and in
+Source or Object form, provided that You meet the following conditions:
+
+(a) You must give any other recipients of the Work or Derivative Works a copy
+of this License; and
+
+(b) You must cause any modified files to carry prominent notices stating
+that You changed the files; and
+
+(c) You must retain, in the Source form of any Derivative Works that You
+distribute, all copyright, patent, trademark, and attribution notices from
+the Source form of the Work, excluding those notices that do not pertain to
+any part of the Derivative Works; and
+
+(d) If the Work includes a "NOTICE" text file as part of its distribution,
+then any Derivative Works that You distribute must include a readable copy
+of the attribution notices contained within such NOTICE file, excluding
+those notices that do not pertain to any part of the Derivative Works, in at
+least one of the following places: within a NOTICE text file distributed as
+part of the Derivative Works; within the Source form or documentation, if
+provided along with the Derivative Works; or, within a display generated by
+the Derivative Works, if and wherever such third-party notices normally
+appear. The contents of the NOTICE file are for informational purposes only
+and do not modify the License. You may add Your own attribution notices
+within Derivative Works that You distribute, alongside or as an addendum to
+the NOTICE text from the Work, provided that such additional attribution
+notices cannot be construed as modifying the License.
+
+5. Submission of Contributions. Unless You explicitly state otherwise, any
+Contribution intentionally submitted for inclusion in the Work by You to the
+Licensor shall be under the terms and conditions of this License, without any
+additional terms or conditions. Notwithstanding the above, nothing herein
+shall supersede or modify the terms of any separate license agreement you may
+have executed with Licensor regarding such Contributions.
+
+6. Trademarks. This License does not grant permission to use the trade names,
+trademarks, service marks, or product names of the Licensor, except as required
+for reasonable and customary use in describing the origin of the Work and
+reproducing the content of the NOTICE file.
+
+7. Disclaimer of Warranty. Unless required by applicable law or agreed to in
+writing, Licensor provides the Work (and each Contributor provides its
+Contributions) on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+KIND, either express or implied, including, without limitation, any warranties
+or conditions of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+PARTICULAR PURPOSE. You are solely responsible for determining the
+appropriateness of using or redistributing the Work and assume any risks
+associated with Your exercise of permissions under this License.
+
+8. Limitation of Liability. In no event and under no legal theory, whether in
+tort (including negligence), contract, or otherwise, unless required by
+applicable law (such as deliberate and grossly negligent acts) or agreed to in
+writing, shall any Contributor be liable to You for damages, including any
+direct, indirect, special, incidental, or consequential damages of any
+character arising as a result of this License or out of the use or inability
+to use the Work (including but not limited to damages for loss of goodwill,
+work stoppage, computer failure or malfunction, or any and all other
+commercial damages or losses), even if such Contributor has been advised of
+the possibility of such damages.
+
+9. Accepting Warranty or Additional Liability. While redistributing the Work
+or Derivative Works thereof, You may choose to offer, and charge a fee for,
+acceptance of support, warranty, indemnity, or other liability obligations
+and/or rights consistent with this License. However, in accepting such
+obligations, You may act only on Your own behalf and on Your sole
+responsibility, not on behalf of any other Contributor, and only if You agree
+to indemnify, defend, and hold each Contributor harmless for any liability
+incurred by, or claims asserted against, such Contributor by reason of your
+accepting any such warranty or additional liability.
+
+END OF TERMS AND CONDITIONS

runproof-engine-0.1.0/PKG-INFO

@@ -0,0 +1,94 @@
+Metadata-Version: 2.1
+Name: runproof-engine
+Version: 0.1.0
+Summary: Evidence, replay, and explainable diffs for real Python runs
+Author: RunProof Contributors
+License: Apache-2.0
+Keywords: reproducibility,provenance,data-lineage,observability,python,replay,explainable-diff
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Science/Research
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3 :: Only
+Classifier: Topic :: Software Development :: Testing
+Classifier: Topic :: Scientific/Engineering :: Information Analysis
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+Provides-Extra: data
+Provides-Extra: dev
+License-File: LICENSE
+
+# RunProof
+
+RunProof is a Python library for recording, validating, replaying, and comparing real computational runs. It turns a Python execution into an inspectable artifact containing inputs, outputs, code references, environment metadata, checks, and an execution trace.
+
+The distinctive feature is **Explainable Diff**: when two runs differ, RunProof compares input fingerprints, schemas, output summaries, step status, code fingerprints, and environment metadata, then reports evidence-backed causes instead of only saying that the runs are different.
+
+## What it is
+
+RunProof is a local-first execution record and reproducibility layer for Python workflows. It is useful for data analysis, reports, ML experiments, research software, API workflows, and any process where the result must be explained later.
+
+RunProof is not a reverse-engineering tool, a code generator, a replacement for Git, or a guarantee that a scientific conclusion is correct. It records and validates the execution that was declared to it.
+
+## Quick start
+
+```python
+from runproof_engine import verified
+
+
+def clean_rows(rows):
+    return [row for row in rows if row["amount"] >= 0]
+
+
+def total(rows):
+    return sum(row["amount"] for row in rows)
+
+with verified("sales_total", root="runs") as run:
+    rows = run.input("sales.json", name="sales")
+    cleaned = run.step("clean_rows", clean_rows, rows)
+    result = run.step("total", total, cleaned)
+    run.assert_true(result >= 0, "total must be non-negative")
+    run.output("total.json", {"total": result})
+
+print(run.result.status)
+print(run.result.artifact_dir)
+```
+
+This creates a run directory with a manifest, input metadata, output metadata, trace events, checks, and an environment snapshot. The input is not silently replaced by generated data. File contents are fingerprinted, while copying full inputs is explicit and configurable.
+
+## Replay and comparison
+
+```python
+from runproof_engine import load_run
+
+previous = load_run("runs/sales_total/20260823-101500-abc123")
+replayed = previous.replay(mode="strict")
+print(replayed.status)
+
+comparison = previous.diff(replayed)
+print(comparison.to_dict())
+print(comparison.render())
+```
+
+`strict` replay uses the captured input when it is available and checks whether the new execution remains comparable. A fresh run can use current inputs and can be compared with a previous run to identify changes.
+
+## Statuses
+
+- `verified`: execution completed and all declared checks passed.
+- `verified_with_warnings`: execution completed but comparability or external-source evidence is limited.
+- `failed`: execution or a required check failed.
+- `blocked`: a declared policy prevented a sensitive action.
+- `non_reproducible`: replay was attempted but did not match the captured run.
+
+## Privacy and real data
+
+RunProof records metadata and hashes by default. Full input copying is opt-in. Secrets are redacted from environment snapshots and trace values. External adapters must provide privacy-safe request metadata instead of storing credentials or raw authorization headers.
+
+## Project status
+
+The current repository implements the local core: run lifecycle, file fingerprints, JSON-safe artifacts, step tracing, assertions, replay, and explainable diffs. Optional integrations are intentionally separated from the core so the library remains useful without a cloud account or a specific AI provider.
+
+## License
+
+Apache-2.0. See `LICENSE`.

runproof-engine-0.1.0/README.md

@@ -0,0 +1,73 @@
+# RunProof
+
+RunProof is a Python library for recording, validating, replaying, and comparing real computational runs. It turns a Python execution into an inspectable artifact containing inputs, outputs, code references, environment metadata, checks, and an execution trace.
+
+The distinctive feature is **Explainable Diff**: when two runs differ, RunProof compares input fingerprints, schemas, output summaries, step status, code fingerprints, and environment metadata, then reports evidence-backed causes instead of only saying that the runs are different.
+
+## What it is
+
+RunProof is a local-first execution record and reproducibility layer for Python workflows. It is useful for data analysis, reports, ML experiments, research software, API workflows, and any process where the result must be explained later.
+
+RunProof is not a reverse-engineering tool, a code generator, a replacement for Git, or a guarantee that a scientific conclusion is correct. It records and validates the execution that was declared to it.
+
+## Quick start
+
+```python
+from runproof_engine import verified
+
+
+def clean_rows(rows):
+    return [row for row in rows if row["amount"] >= 0]
+
+
+def total(rows):
+    return sum(row["amount"] for row in rows)
+
+with verified("sales_total", root="runs") as run:
+    rows = run.input("sales.json", name="sales")
+    cleaned = run.step("clean_rows", clean_rows, rows)
+    result = run.step("total", total, cleaned)
+    run.assert_true(result >= 0, "total must be non-negative")
+    run.output("total.json", {"total": result})
+
+print(run.result.status)
+print(run.result.artifact_dir)
+```
+
+This creates a run directory with a manifest, input metadata, output metadata, trace events, checks, and an environment snapshot. The input is not silently replaced by generated data. File contents are fingerprinted, while copying full inputs is explicit and configurable.
+
+## Replay and comparison
+
+```python
+from runproof_engine import load_run
+
+previous = load_run("runs/sales_total/20260823-101500-abc123")
+replayed = previous.replay(mode="strict")
+print(replayed.status)
+
+comparison = previous.diff(replayed)
+print(comparison.to_dict())
+print(comparison.render())
+```
+
+`strict` replay uses the captured input when it is available and checks whether the new execution remains comparable. A fresh run can use current inputs and can be compared with a previous run to identify changes.
+
+## Statuses
+
+- `verified`: execution completed and all declared checks passed.
+- `verified_with_warnings`: execution completed but comparability or external-source evidence is limited.
+- `failed`: execution or a required check failed.
+- `blocked`: a declared policy prevented a sensitive action.
+- `non_reproducible`: replay was attempted but did not match the captured run.
+
+## Privacy and real data
+
+RunProof records metadata and hashes by default. Full input copying is opt-in. Secrets are redacted from environment snapshots and trace values. External adapters must provide privacy-safe request metadata instead of storing credentials or raw authorization headers.
+
+## Project status
+
+The current repository implements the local core: run lifecycle, file fingerprints, JSON-safe artifacts, step tracing, assertions, replay, and explainable diffs. Optional integrations are intentionally separated from the core so the library remains useful without a cloud account or a specific AI provider.
+
+## License
+
+Apache-2.0. See `LICENSE`.

runproof-engine-0.1.0/pyproject.toml

@@ -0,0 +1,46 @@
+[build-system]
+requires = ["setuptools>=68"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "runproof-engine"
+version = "0.1.0"
+description = "Evidence, replay, and explainable diffs for real Python runs"
+readme = "README.md"
+requires-python = ">=3.10"
+license = { text = "Apache-2.0" }
+authors = [
+  { name = "RunProof Contributors" }
+]
+keywords = ["reproducibility", "provenance", "data-lineage", "observability", "python", "replay", "explainable-diff"]
+classifiers = [
+  "Development Status :: 3 - Alpha",
+  "Intended Audience :: Developers",
+  "Intended Audience :: Science/Research",
+  "License :: OSI Approved :: Apache Software License",
+  "Programming Language :: Python :: 3",
+  "Programming Language :: Python :: 3 :: Only",
+  "Topic :: Software Development :: Testing",
+  "Topic :: Scientific/Engineering :: Information Analysis",
+]
+dependencies = []
+
+[project.optional-dependencies]
+data = ["pandas>=2.0"]
+dev = ["pytest>=8", "ruff>=0.6"]
+
+[project.scripts]
+runproof = "runproof_engine.cli:main"
+
+[tool.setuptools]
+package-dir = {"" = "src"}
+
+[tool.setuptools.packages.find]
+where = ["src"]
+
+[tool.setuptools.package-data]
+runproof_engine = ["py.typed"]
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]
+addopts = "-q"

runproof-engine-0.1.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

runproof-engine-0.1.0/src/runproof_engine/__init__.py

@@ -0,0 +1,33 @@
+from .core import (
+    CheckRecord,
+    ReplayUnavailable,
+    RunContext,
+    RunProofError,
+    RunResult,
+    StepRecord,
+    verified,
+)
+from .diff import Difference, RunDiff, compare_manifests
+from .policy import Policy, PolicyDenied, safe_default_policy
+from .replay import LoadedRun, ReplayReport, load_run
+
+__all__ = [
+    "CheckRecord",
+    "Difference",
+    "LoadedRun",
+    "Policy",
+    "PolicyDenied",
+    "ReplayReport",
+    "ReplayUnavailable",
+    "RunContext",
+    "RunDiff",
+    "RunProofError",
+    "RunResult",
+    "StepRecord",
+    "compare_manifests",
+    "load_run",
+    "safe_default_policy",
+    "verified",
+]
+
+__version__ = "0.1.0"

runproof-engine-0.1.0/src/runproof_engine/cli.py

@@ -0,0 +1,69 @@
+from __future__ import annotations
+
+import argparse
+import json
+import sys
+from pathlib import Path
+
+from .replay import LoadedRun, load_run
+
+
+def build_parser() -> argparse.ArgumentParser:
+    parser = argparse.ArgumentParser(prog="runproof", description="Inspect and compare RunProof artifacts")
+    subparsers = parser.add_subparsers(dest="command", required=True)
+
+    inspect_parser = subparsers.add_parser("inspect", help="inspect a run artifact")
+    inspect_parser.add_argument("path", type=Path)
+    inspect_parser.add_argument("--json", action="store_true", dest="as_json")
+
+    verify_parser = subparsers.add_parser("verify", help="verify input and output integrity")
+    verify_parser.add_argument("path", type=Path)
+    verify_parser.add_argument("--json", action="store_true", dest="as_json")
+
+    diff_parser = subparsers.add_parser("diff", help="compare two run artifacts")
+    diff_parser.add_argument("left", type=Path)
+    diff_parser.add_argument("right", type=Path)
+    diff_parser.add_argument("--json", action="store_true", dest="as_json")
+    return parser
+
+
+def main(argv: list[str] | None = None) -> int:
+    parser = build_parser()
+    args = parser.parse_args(argv)
+    try:
+        if args.command == "inspect":
+            run = load_run(args.path)
+            payload = run.manifest
+            text = json.dumps(payload, indent=2, ensure_ascii=False) if args.as_json else _inspect_text(run)
+        elif args.command == "verify":
+            run = load_run(args.path)
+            report = run.verify_integrity()
+            payload = report.to_dict()
+            text = json.dumps(payload, indent=2, ensure_ascii=False) if args.as_json else str(report)
+            print(text)
+            return 0 if report.status == "verified" else 2
+        else:
+            left = load_run(args.left)
+            right = load_run(args.right)
+            comparison = left.diff(right)
+            payload = comparison.to_dict()
+            text = json.dumps(payload, indent=2, ensure_ascii=False) if args.as_json else comparison.render()
+        print(text)
+        return 0
+    except (OSError, ValueError, KeyError) as error:
+        print(f"runproof: {error}", file=sys.stderr)
+        return 2
+
+
+def _inspect_text(run: LoadedRun) -> str:
+    manifest = run.manifest
+    run_info = manifest.get("run", {})
+    return "\n".join([
+        f"name: {run_info.get('name')}",
+        f"run_id: {run_info.get('run_id')}",
+        f"status: {run_info.get('status')}",
+        f"inputs: {len(manifest.get('inputs', []))}",
+        f"steps: {len(manifest.get('steps', []))}",
+        f"outputs: {len(manifest.get('outputs', []))}",
+        f"checks: {len(manifest.get('checks', []))}",
+    ])