pytest-gpu-proof 0.3.0__tar.gz → 0.4.1__tar.gz

pytest_gpu_proof-0.4.1/.github/workflows/ci.yml

@@ -0,0 +1,68 @@
+name: CI
+
+on:
+  push:
+    branches: [main]
+  pull_request:
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    strategy:
+      fail-fast: false
+      matrix:
+        python-version: ["3.11", "3.12", "3.13"]
+
+    steps:
+      - uses: actions/checkout@v4
+
+      - uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+
+      - name: Install package with dev extras
+        run: pip install -e ".[dev]"
+
+      - name: Run test suite (CPU-only)
+        run: python -m pytest tests/ -q
+
+  coverage:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
+        with:
+          python-version: "3.12"
+      - name: Install package with dev extras
+        run: pip install -e ".[dev]"
+      - name: Enforce 100% line and branch coverage
+        run: |
+          coverage run -m pytest tests/ -q
+          coverage report --fail-under=100
+          coverage xml
+      - uses: actions/upload-artifact@v4
+        with:
+          name: coverage-xml
+          path: coverage.xml
+
+  docs-and-package:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
+        with:
+          python-version: "3.12"
+      - name: Install package with dev extras
+        run: pip install -e ".[dev]"
+      - name: Build documentation strictly
+        run: mkdocs build --strict
+      - name: Build and inspect distributions
+        run: |
+          python -m build
+          python -m twine check --strict dist/*
+      - name: Smoke-test the wheel
+        run: |
+          python -m venv /tmp/wheeltest
+          /tmp/wheeltest/bin/pip install -q dist/*.whl
+          /tmp/wheeltest/bin/gpu-proof --help
+          /tmp/wheeltest/bin/python -m pytest -p pytest_gpu_proof --version

pytest_gpu_proof-0.4.1/.github/workflows/docs.yml

@@ -0,0 +1,69 @@
+name: Docs
+
+on:
+  push:
+    branches: [main]
+  pull_request:
+    paths:
+      - 'docs/**'
+      - 'website/**'
+      - 'mkdocs.yml'
+      - '.github/workflows/docs.yml'
+
+permissions:
+  contents: read
+
+concurrency:
+  group: docs-${{ github.ref }}
+  cancel-in-progress: false
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+
+      - uses: actions/setup-python@v5
+        with:
+          python-version: "3.12"
+
+      - name: Install website dependencies
+        run: pip install -r website/requirements.txt
+
+      - name: Build and check the complete website
+        run: python website/build_site.py
+
+      - name: Test website checks
+        run: python -m unittest discover -s website -p 'test_*.py'
+
+      - uses: actions/upload-artifact@v4
+        with:
+          name: website-preview
+          path: build/website
+          include-hidden-files: true
+
+  deploy:
+    if: github.event_name == 'push' && github.ref == 'refs/heads/main'
+    needs: build
+    runs-on: ubuntu-latest
+    permissions:
+      contents: write
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+      - uses: actions/setup-python@v5
+        with:
+          python-version: "3.12"
+      - run: pip install -r website/requirements.txt
+      - uses: actions/download-artifact@v4
+        with:
+          name: website-preview
+          path: build/website
+      - name: Configure git author
+        run: |
+          git config user.name "github-actions[bot]"
+          git config user.email "github-actions[bot]@users.noreply.github.com"
+
+      - name: Deploy to gh-pages
+        run: ghp-import --no-jekyll --push --branch gh-pages build/website

{pytest_gpu_proof-0.3.0 → pytest_gpu_proof-0.4.1}/.gitignore

@@ -299,4 +299,6 @@ Testing/
 *.fatbin
 
 # Specifics
-gpu-proof.json
+gpu-proof.json
+# Local working notes (never committed)
+docs/open-tasks/

pytest_gpu_proof-0.4.1/AGENTS.md

@@ -0,0 +1,29 @@
+# Agent guide
+
+This repository is a security-sensitive pytest plugin. Preserve fail-closed
+behavior and treat receipt, fingerprint, signature, Git, merge, and policy code
+as trust boundaries.
+
+Before changing behavior, read:
+
+- `README.md`
+- `docs/architecture.md`
+- `docs/security_model.md`
+- `docs/policy.md`
+- `CONTRIBUTING.md`
+
+Implementation rules:
+
+- New receipts are schema 3; keep explicit legacy verification isolated.
+- Signer metadata belongs inside the signed payload.
+- Default fingerprint scope is the full tracked repository; generated inputs
+  require explicit extra paths.
+- Never turn receipt-emission failures into success unless the caller selected
+  `best_effort`.
+- Never accept unknown policy fields or malformed receipt structure.
+- Keep tests hermetic: mock GitHub key lookup and local identity.
+- Maintain 100% line and branch coverage. Add adversarial cases for new trust
+  branches.
+- Do not edit generated `site/` or release artifacts in `dist/`.
+
+Run the complete check list from `CONTRIBUTING.md` before proposing a PR.

pytest_gpu_proof-0.4.1/CHANGELOG.md

@@ -0,0 +1,180 @@
+# Changelog
+
+All notable changes to pytest-gpu-proof are documented here. The format is
+based on [Keep a Changelog](https://keepachangelog.com/); versions follow
+[SemVer](https://semver.org/) (pre-1.0: minor bumps may break).
+
+## [0.4.1] — 2026-10-12
+
+### Fixed
+
+- Shard entries record `dirty` (the recording tree's state); merge ORs shard
+  flags into the merged `repo.dirty`, carry-forward refuses a dirty shard, and
+  verification refuses any dirty shard unless `allow_dirty` is set.
+- `gpu-proof merge --carry-from` refuses a source receipt recorded with a dirty
+  working tree. The merged `repo.dirty` is OR-ed over the fresh inputs only, so a
+  carried shard from a dirty recording was laundered into a clean-looking merged
+  receipt (found by GRiD's split driver, 2026-10-10). Carried shards now record
+  `carried.original_dirty`, and verification refuses a carried shard recorded
+  dirty unless `allow_dirty` is set.
+
+- The expected-skips mismatch names the delta (unexpected skips and stale
+  baseline entries) instead of only reporting that the sets differ.
+- The receipt's `environment.gpu_info` falls back to the same torch probe the
+  `gpu_required` marker uses when nvidia-smi is absent or fails (`source`
+  records which probe answered), so a torch-only box no longer records
+  `gpu_info: null` and then fails a `require_gpu` policy.
+
+- Verification refuses a receipt whose session started more than five
+  minutes before its commit existed (committer time): a cheap replay and
+  forgery guard that needs no nonce.
+
+- `mode: ci-gpu` is now bound to the signing key: a ci-gpu receipt verifies
+  only when the policy lists `allowed_key_fingerprints` and the receipt was
+  signed by one of them (previously the mode was an unverified label).
+- Without an explicit `carried_max_age_days`, a carried shard's original run
+  may not be older than the receipt's `max_age_days` (was a fixed 30 days).
+
+### Added
+
+- `gpu-proof merge --verify-inputs`: authenticate every input shard against
+  its signer's current GitHub keys before merging (unsigned or tampered inputs
+  are refused).
+- `gpu-proof status PATH...`: one-line summaries of receipt files or
+  directories (commit, dirty, signed, outcome, counts, shards, carried).
+- `gpu-proof durations RECEIPT... --out map.json`: fold per-test durations
+  into a JSON map for shard bin-packing.
+- Command-line equivalents for the toml-only options:
+  `--gpu-proof-no-gpu-uuid`, `--gpu-proof-require-gpu`,
+  `--gpu-proof-max-age-days N`.
+- `gpu-proof plan --receipt OLD [--repo .] [--json]`: a dry run of the
+  carry-forward conditions against the current tree, reporting per shard
+  whether it could be carried or must be re-run (and why). Drivers that plan
+  partial re-runs no longer reimplement the checks.
+- `record_gpu_uuid` (`[tool.gpu_proof]`, default `true`): set `false` to omit each GPU's
+  nvidia-smi UUID from the receipt environment while keeping name, driver, memory and
+  compute capability. Verification does not read the UUID.
+
+## [0.4.0] — 2026-08-17
+
+### Added
+
+- Schema `"3"`: signer username, key fingerprint, key algorithm, exact test
+  collection, session outcome, pytest arguments, and per-shard environment/time
+  are included in the signed payload.
+- Open contributor and restricted signer policies. Restricted mode supports
+  username and exact SSH-key-fingerprint allowlists.
+- Policy pinning for mode, global tracked/extra fingerprint scope, exact test
+  manifest, shard names, and per-shard tracked/extra scope.
+- Explicit fingerprint paths for ignored/generated inputs and manifest support
+  for symlinks and submodule gitlinks.
+- Explicit receipt-artifact exclusions avoid self-referential whole-tree
+  fingerprints and can be pinned by verification policy.
+- `--gpu-proof-best-effort` as an explicit development escape hatch.
+- `min_schema` policy field to refuse legacy schema-1/2 receipts.
+- Python 3.13 CI, strict docs/package jobs, and enforced 100% line and branch
+  coverage.
+
+### Changed
+
+- The default fingerprint scope is the entire Git-tracked repository instead
+  of `src,tests`.
+- Receipt creation now fails pytest on Git, fingerprint, key, serialization, or
+  write errors; it also removes stale output at session start.
+- Schema-3 verification rejects dirty recording and verification trees by
+  default and accepts receipt commits only at the current commit or an ancestor.
+- Setup/teardown failures, missing terminal reports, comparison exceptions,
+  skipped tests, and overall session failure are represented and verified.
+- GPU metadata records all devices reported by `nvidia-smi`.
+- Array comparison is shape-safe, uses tolerance only for float/complex data,
+  and uses exact equality for other dtypes.
+- Receipt writes are atomic and strict JSON forbids NaN/non-JSON values.
+- Receipt generation rejects xdist workers; use separate shard processes.
+- Legacy schema-1/2 verification derives the policy-checked key fingerprint
+  from the key that actually verified the signature; an asserted
+  `signature.key_fingerprint` that disagrees is rejected.
+- `signer_mode: restricted` policies reject unsigned receipts even with
+  `--allow-unsigned`, and `--github-user` must match the signed schema-3
+  identity.
+- The receipt under verification is excluded from the verification-tree dirty
+  check, so an untracked just-generated receipt verifies without gitignoring.
+- Passphrase-protected SSH keys prompt correctly on current cryptography
+  releases (`ValueError` as well as `TypeError`) and fail closed with an
+  actionable message when no terminal is available.
+- Uninitialized submodule checkouts fingerprint their index gitlink commit
+  instead of accidentally recording the parent repository's HEAD.
+- Receipt/shard age limits are enforced to the exact day boundary.
+- GitHub usernames are validated before key fetches and key responses are
+  size-capped.
+- A stale receipt that cannot be cleared at session start raises a pytest
+  usage error (an exit-status write that early would be silently overwritten).
+- Merging receipts without session timestamps is refused with a clear error.
+
+### Fixed
+
+- Carry-forward now recomputes the stored fingerprint algorithm and preserves
+  explicit generated/ignored shard inputs.
+- Signed identity and algorithm substitution are rejected.
+- Empty source scope, unmerged index entries, malformed policies, incomplete
+  collections, and stale success artifacts fail closed.
+
+## [0.3.0] — 2026-08-08
+
+### Added
+- Schema `"2"` sharded receipts: `--gpu-proof-shard NAME` +
+  `--gpu-proof-shard-fingerprint-paths` emit a per-shard narrow fingerprint;
+  `gpu-proof merge` unions schema-2 shards (unique names enforced).
+- Verifiable carry-forward: `gpu-proof merge --carry-from OLD` grafts shards
+  absent from the fresh inputs iff the old commit is an ancestor AND the
+  shard's narrow fingerprint recomputes clean; grafted shards are marked
+  `carried` and the verifier rejects them unless the policy sets
+  `allow_carried: true` (bounded by `carried_max_age_days`, default 30).
+- Verifier: schema-2 checks (per-shard fingerprint recompute, membership
+  partition of `tests[]`, carried-shard policy gate). Schema-1 receipts are
+  unchanged and a schema-1 receipt carrying a `shards` block is rejected.
+
+## [0.2.0] — 2026-08-07
+
+### Added
+- `gpu-proof merge`: union N shard receipts from one commit into a single
+  re-signed receipt (per-module crash isolation / machine sharding). Refuses
+  shards that disagree on schema, commit SHA, fingerprint, mode, or
+  environment; duplicate node IDs across shards are a hard error. Records
+  per-shard provenance under `session.shards` (additive — the verifier is
+  unchanged). `repo.dirty` is OR-ed; `gpu_info` survives CPU-only shards.
+  Docs: `docs/sharding.md`.
+
+### Fixed
+- Explicit CLI values equal to their built-in defaults are no longer silently
+  ignored in favor of `[tool.gpu_proof]` (value-taking options now register a
+  `None` sentinel; `--gpu-proof-fail-on-skip` ORs with the toml value since a
+  store_true flag can only turn it on).
+
+## [0.1.0] — 2026-07-07
+
+First public release.
+
+### Added
+- pytest plugin (`-p` auto-loaded via the `pytest11` entry point): captures
+  per-test outcomes and skips, git SHA, a SHA-256 source fingerprint over
+  configured paths, and self-reported GPU info; emits a signed JSON receipt at
+  session end (`--gpu-proof-enable`).
+- Ed25519 SSH-key signing; signature covers the canonical (compact,
+  sorted-key) JSON without the signature block. `none` backend for unsigned
+  receipts.
+- CPU-only verifier `gpu-proof verify`: signature against the signer's public
+  `github.com/<user>.keys`, fingerprint match, commit SHA, outcome + skip
+  policy, `--require-gpu`, freshness (`--max-age-days`, `0` = today only),
+  dirty policy.
+- Skip policies: `--allow-skipped` (any) or `--expected-skips FILE` (exact-set
+  baseline — unexpected AND stale entries both fail); mutually exclusive.
+  Also `[tool.gpu_proof] expected_skips`.
+- Signer resolution: explicit flag/config → `gh` CLI login (keyholder) →
+  origin-remote owner with a printed warning (org remotes have no SSH keys).
+- `is_dirty` ignores untracked content inside submodules (pin moves and
+  tracked edits still count).
+- Receipt diffing (`compare.py`), `[tool.gpu_proof]` pyproject configuration,
+  docs site (mkdocs), honest trust-model statement in
+  `docs/security_model.md`.
+
+[0.1.0]: https://github.com/A2R-Lab/pytest-gpu-proof/releases/tag/v0.1.0

pytest_gpu_proof-0.4.1/CLAUDE.md

@@ -0,0 +1,14 @@
+# Claude orientation
+
+Use [AGENTS.md](AGENTS.md) as the canonical agent guide. In particular:
+
+- a receipt is signer attestation, not proof of GPU execution;
+- receipt, fingerprint, signature, Git, merge, and policy code fail closed;
+- new recordings use schema 3 and bind signer metadata inside the signature;
+- the default manifest covers the full tracked repository;
+- tests are hermetic and maintain 100% line and branch coverage;
+- generated `site/`, `dist/`, coverage output, real keys, and local receipts are
+  not source changes.
+
+Before implementation work, read `docs/architecture.md`,
+`docs/security_model.md`, `docs/policy.md`, and `CONTRIBUTING.md`.

pytest_gpu_proof-0.4.1/CONTRIBUTING.md

@@ -0,0 +1,41 @@
+# Contributing
+
+## Development setup
+
+```bash
+python -m venv .venv
+source .venv/bin/activate
+python -m pip install -e ".[dev]"
+```
+
+## Required checks
+
+```bash
+python -m pytest tests -q
+coverage run -m pytest tests -q
+coverage report --fail-under=100
+mkdocs build --strict
+python -m build
+python -m twine check --strict dist/*
+```
+
+CI runs the test suite on Python 3.11, 3.12, and 3.13, independently enforces
+100% line and branch coverage, builds docs strictly, and smoke-tests the wheel.
+
+## Change expectations
+
+- Add adversarial tests for trust-boundary changes, not only happy paths.
+- Keep receipt generation and verification fail-closed by default.
+- Treat schema and policy changes as compatibility decisions; document them in
+  `CHANGELOG.md` and the relevant guide.
+- Keep Git and network tests hermetic. Never depend on a developer's actual
+  GitHub login, SSH keys, GPU, or global Git configuration.
+- Use separate pytest processes for shards. Receipt generation does not support
+  xdist workers.
+- Do not commit generated `site/`, coverage files, caches, or local receipts.
+
+## Pull requests
+
+Describe the trust claim before and after the change, migration implications,
+and the exact checks run. Small, reviewable commits are preferred. Security
+reports should follow [SECURITY.md](SECURITY.md), not a public issue.