Skip to content

chore: release main#1768

Merged
mldangelo-oai merged 5 commits into
mainfrom
release-please--branches--main
Jul 22, 2026
Merged

chore: release main#1768
mldangelo-oai merged 5 commits into
mainfrom
release-please--branches--main

Conversation

@github-actions

@github-actions github-actions Bot commented Jul 21, 2026

Copy link
Copy Markdown
Contributor

🤖 I have created a release beep boop

0.2.52

0.2.52 (2026-07-22)

Bug Fixes

modelaudit-picklescan: 0.1.10

0.1.10 (2026-07-22)

Bug Fixes

  • picklescan: recognize uv bytes-encoded package overlays (#1777) (e9910fa)

This PR was generated with Release Please. See documentation.

@chatgpt-codex-connector chatgpt-codex-connector Bot left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: ff897ed5a1

ℹ️ About Codex in GitHub

Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you

  • Open a pull request for review
  • Mark a draft as ready
  • Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".

Comment thread pyproject.toml
@github-actions
github-actions Bot force-pushed the release-please--branches--main branch 4 times, most recently from 2bbed40 to 044dff2 Compare July 21, 2026 22:02
@github-actions

github-actions Bot commented Jul 22, 2026

Copy link
Copy Markdown
Contributor Author

Workflow run and artifacts

Performance Benchmarks

Compared 13 shared benchmarks with a regression threshold of 15%.
Status: 0 regressions, 0 improved, 13 stable, 0 new, 0 missing.
Aggregate shared-benchmark median: 4.310s -> 4.362s (+1.2%).

Workload Benchmark Target Size Files Baseline Current Change Status
suspicious-pickle-intake tests/benchmarks/test_scan_benchmarks.py::test_scan_suspicious_pickle_intake suspicious-intake 183.8 KiB 4 146.00ms 149.91ms +2.7% stable
warm-cache-rescan tests/benchmarks/test_scan_benchmarks.py::test_scan_warm_cached_repository_rescan release-candidate 547.3 KiB 32 150.12ms 153.60ms +2.3% stable
duplicate-heavy-registry tests/benchmarks/test_scan_benchmarks.py::test_scan_duplicate_registry_snapshot registry-snapshot 915.2 KiB 13 564.22ms 575.29ms +2.0% stable
rejected-basic-auth-candidates tests/benchmarks/test_scan_benchmarks.py::test_rejected_basic_auth_candidates_scan_linearly - 371.1 KiB 1 2.481s 2.523s +1.7% stable
chunked-upload-stream tests/benchmarks/test_picklescan_benchmarks.py::test_picklescan_chunked_upload_stream chunked_stream 278.2 KiB 1 113.81ms 111.89ms -1.7% stable
nested-payload-review tests/benchmarks/test_picklescan_benchmarks.py::test_picklescan_nested_payload_review[nested_hex] nested_hex 130 B 1 300.9us 305.5us +1.5% stable
single-checkpoint-preflight tests/benchmarks/test_scan_benchmarks.py::test_scan_single_checkpoint_before_load single_checkpoint.pkl 183.0 KiB 1 103.70ms 105.03ms +1.3% stable
mixed-model-repository tests/benchmarks/test_scan_benchmarks.py::test_scan_release_candidate_repository release-candidate 547.3 KiB 32 639.66ms 632.19ms -1.2% stable
clean-training-checkpoint tests/benchmarks/test_picklescan_benchmarks.py::test_picklescan_clean_training_checkpoint safe_large 278.2 KiB 1 110.33ms 109.37ms -0.9% stable
padded-multi-stream-upload tests/benchmarks/test_picklescan_benchmarks.py::test_picklescan_padded_multi_stream_upload multi_stream_padded 4.1 KiB 1 330.3us 332.9us +0.8% stable
direct-malicious-upload tests/benchmarks/test_picklescan_benchmarks.py::test_picklescan_direct_malicious_upload malicious_reduce 52 B 1 218.8us 219.6us +0.4% stable
nested-payload-review tests/benchmarks/test_picklescan_benchmarks.py::test_picklescan_nested_payload_review[nested_raw] nested_raw 78 B 1 270.9us 271.5us +0.2% stable
nested-payload-review tests/benchmarks/test_picklescan_benchmarks.py::test_picklescan_nested_payload_review[nested_base64] nested_base64 98 B 1 292.5us 293.0us +0.2% stable

@github-actions
github-actions Bot force-pushed the release-please--branches--main branch 2 times, most recently from eff3955 to 8edf9b8 Compare July 22, 2026 05:36

@chatgpt-codex-connector chatgpt-codex-connector Bot left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: 05fcb12250

ℹ️ About Codex in GitHub

Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you

  • Open a pull request for review
  • Mark a draft as ready
  • Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".

Comment thread pyproject.toml
[project]
name = "modelaudit"
version = "0.2.51"
version = "0.2.52"

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

P2 Badge Require picklescan 0.1.10 for this release

When users upgrade modelaudit to 0.2.52 in an environment that already has modelaudit-picklescan==0.1.9, the unchanged dependency floor at pyproject.toml:55 still satisfies the new root wheel; pip install --help confirms the default upgrade strategy is only-if-needed, so dependencies are upgraded only when they no longer satisfy requirements. That leaves those upgraded root installs without the picklescan fix advertised in this release, so the coordinated root release should raise the floor to modelaudit-picklescan>=0.1.10,<0.2.0.

Useful? React with 👍 / 👎.

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Confirmed: the refreshed release branch bumps picklescan to 0.1.10 but the root requirement remains >=0.1.9,<0.2.0, so only-if-needed upgrades can retain 0.1.9. I am leaving this thread unresolved and will raise the floor/regenerate the root lock on the final refreshed release branch after the pending security/cache merges; updating the current generated branch now would be overwritten by the next release-please refresh.

@github-actions
github-actions Bot force-pushed the release-please--branches--main branch 2 times, most recently from 53db33b to 22db7d5 Compare July 22, 2026 16:39
@github-actions
github-actions Bot force-pushed the release-please--branches--main branch from 2f3710a to 715458e Compare July 22, 2026 16:41

@chatgpt-codex-connector chatgpt-codex-connector Bot left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: 26f38fb3d3

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

  • Open a pull request for review
  • Mark a draft as ready
  • Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".

Comment thread pyproject.toml
"protobuf>=5.29.0",
"msgpack>=1.2.1,<2.0",
"modelaudit-picklescan>=0.1.9,<0.2.0",
"modelaudit-picklescan>=0.1.10,<0.2.0",

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

P1 Badge Update every mirror of the picklescan floor

With this requirement raised to 0.1.10, tests/test_dependency_lock.py:17 still defines REQUIRED_PICKLESCAN_RELEASE as the exact 0.1.9 requirement and line 85 asserts that old string is present, so the mandatory pytest suite deterministically fails. The canonical root and picklescan agent guides and docs/agents/release-process.md:14 also still publish the old floor; update these mirrors with the dependency bump.

AGENTS.md reference: AGENTS.md:L14-L21

Useful? React with 👍 / 👎.

Comment thread CHANGELOG.md
- avoid logging file-derived header-format values while preserving format-mismatch detections, and clean up CodeQL quality findings
- inspect LZ4-compressed Joblib payloads with bounded decompression and preserve fail-closed optional dependency handling; thanks to @PowerliftLog for the report

## [0.2.52](https://github.com/promptfoo/modelaudit/compare/v0.2.51...v0.2.52) (2026-07-22)

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

P3 Badge Clear released fixes from Unreleased

When this section declares 0.2.52 released, the fixes at lines 12–15 remain under ## [Unreleased]; the sibling changelog likewise leaves its 0.1.10 fix under Unreleased at lines 14–18. The root [unreleased] reference at line 2555 also still compares from v0.2.51, so the published changelogs describe already-shipped fixes as pending and link to a range containing this release; clear the promoted entries and advance the comparison reference.

AGENTS.md reference: AGENTS.md:L82-L82

Useful? React with 👍 / 👎.

@mldangelo-oai
mldangelo-oai merged commit 89125b5 into main Jul 22, 2026
44 checks passed
@mldangelo-oai
mldangelo-oai deleted the release-please--branches--main branch July 22, 2026 19:20
@github-actions

Copy link
Copy Markdown
Contributor Author

🤖 Created releases:

🌻

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant