From 07bb1234e34acae7c820d5f0985bcb48d4e059f7 Mon Sep 17 00:00:00 2001 From: Dhiman Seal Date: Fri, 7 Aug 2026 19:34:54 +0530 Subject: [PATCH] chore(release): prepare 0.6.0 Promote the accumulated public corpus and Codex adapter changes since v0.5.0 into a backward-compatible minor release. Refresh package metadata, documentation, support policy, sitemap dates, and deterministic comparator authorities. Co-Authored-By: Dhiman's Agentic Suite --- .github/ISSUE_TEMPLATE/bug.yml | 2 +- CHANGELOG.md | 5 ++++- CITATION.cff | 4 ++-- README.md | 18 +++++++++--------- SECURITY.md | 4 ++-- pyproject.toml | 2 +- site/docs/index.html | 18 +++++++++--------- site/index.html | 2 +- site/sitemap.xml | 4 ++-- skivolve/__init__.py | 2 +- skivolve/comparator-profile-authority.json | 8 ++++---- skivolve/comparator_calibration/release.json | 2 +- .../tests/test-release.json | 2 +- .../plain_language_calibration/release.json | 2 +- .../tests/test-release.json | 2 +- 15 files changed, 40 insertions(+), 37 deletions(-) diff --git a/.github/ISSUE_TEMPLATE/bug.yml b/.github/ISSUE_TEMPLATE/bug.yml index 3b7ba53..cfb1fd9 100644 --- a/.github/ISSUE_TEMPLATE/bug.yml +++ b/.github/ISSUE_TEMPLATE/bug.yml @@ -12,7 +12,7 @@ body: attributes: label: Version description: Package version or exact commit. - placeholder: 0.5.0 + placeholder: 0.6.0 validations: required: true - type: dropdown diff --git a/CHANGELOG.md b/CHANGELOG.md index fa2f467..6ce4492 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -4,6 +4,8 @@ All notable changes to Skivolve are documented in this file. The format follows ## [Unreleased] +## [0.6.0] - 2026-08-07 + ### Added - Added four calibrated final-output cases for compatibility decisions, read-only diagnoses, surgical plans, and evidence-gap research, with transient workspace-write evidence and unseen positive paraphrases guarding against oracle overfitting. @@ -129,7 +131,8 @@ All notable changes to Skivolve are documented in this file. The format follows - Repository-local `engineering` and `testing` reference bundles for exercising Git-bound comparison variants. - CI, CodeQL, OpenSSF Scorecard, Dependabot, issue forms, contribution policy, security reporting, governance, support, and release documentation. -[Unreleased]: https://github.com/Dhi13man/skivolve/compare/v0.5.0...HEAD +[Unreleased]: https://github.com/Dhi13man/skivolve/compare/v0.6.0...HEAD +[0.6.0]: https://github.com/Dhi13man/skivolve/compare/v0.5.0...v0.6.0 [0.5.0]: https://github.com/Dhi13man/skivolve/compare/v0.4.0...v0.5.0 [0.4.0]: https://github.com/Dhi13man/skivolve/compare/v0.3.0...v0.4.0 [0.3.0]: https://github.com/Dhi13man/skivolve/compare/v0.2.0...v0.3.0 diff --git a/CITATION.cff b/CITATION.cff index 0db609d..cc70612 100644 --- a/CITATION.cff +++ b/CITATION.cff @@ -2,8 +2,8 @@ cff-version: 1.2.0 message: If you use Skivolve in published work, cite this software release. title: Skivolve type: software -version: 0.5.0 -date-released: 2026-07-29 +version: 0.6.0 +date-released: 2026-08-07 authors: - family-names: Seal given-names: Dhiman diff --git a/README.md b/README.md index 0a97b30..6bf1056 100644 --- a/README.md +++ b/README.md @@ -6,7 +6,7 @@ Skivolve runs reproducible A/B evaluations of agent skills and instruction bundles through isolated harnesses, objective case verifiers, and calibrated blinded comparison. -Version `0.5.0` is an alpha release for expert evaluation work on Linux. The public repository contains train and validation cases, not a private holdout, and ships no live comparator certification. It does not claim that one harness or bundle is superior. The production `software-engineering-v1` comparator profile is calibrated for software changes; the bundled plain-language profile has test authority and author-authored labels, not independent production calibration. +Version `0.6.0` is an alpha release for expert evaluation work on Linux. The public repository contains train and validation cases, not a private holdout, and ships no live comparator certification. It does not claim that one harness or bundle is superior. The production `software-engineering-v1` comparator profile is calibrated for software changes; the bundled plain-language profile has test authority and author-authored labels, not independent production calibration. ## What Skivolve Provides @@ -32,7 +32,7 @@ The runtime package has one exact third-party dependency, `rfc8785==0.1.4`, for Clone the tagged source so the reference suite, cases, and pinned Git baseline are available: ```bash -git clone --branch v0.5.0 https://github.com/Dhi13man/skivolve.git +git clone --branch v0.6.0 https://github.com/Dhi13man/skivolve.git cd skivolve python3 -m venv .venv . .venv/bin/activate @@ -41,16 +41,16 @@ python3 -m venv .venv Download, verify, and install the release wheel: ```bash -mkdir -p /tmp/skivolve-0.5.0 -gh release download v0.5.0 --repo Dhi13man/skivolve \ - --pattern "skivolve-0.5.0*" --pattern SHA256SUMS \ - --dir /tmp/skivolve-0.5.0 -(cd /tmp/skivolve-0.5.0 && sha256sum --check SHA256SUMS) +mkdir -p /tmp/skivolve-0.6.0 +gh release download v0.6.0 --repo Dhi13man/skivolve \ + --pattern "skivolve-0.6.0*" --pattern SHA256SUMS \ + --dir /tmp/skivolve-0.6.0 +(cd /tmp/skivolve-0.6.0 && sha256sum --check SHA256SUMS) gh attestation verify \ - /tmp/skivolve-0.5.0/skivolve-0.5.0-py3-none-any.whl \ + /tmp/skivolve-0.6.0/skivolve-0.6.0-py3-none-any.whl \ --repo Dhi13man/skivolve python -m pip install \ - /tmp/skivolve-0.5.0/skivolve-0.5.0-py3-none-any.whl + /tmp/skivolve-0.6.0/skivolve-0.6.0-py3-none-any.whl ``` ## Run A Comparison diff --git a/SECURITY.md b/SECURITY.md index d4302b6..64165b8 100644 --- a/SECURITY.md +++ b/SECURITY.md @@ -6,8 +6,8 @@ Skivolve executes untrusted generated code and integrates with authenticated cod | Version | Supported | | --------- | --------- | -| `0.4.x` | Yes | -| `<=0.3.x` | No | +| `0.6.x` | Yes | +| `<=0.5.x` | No | Only the latest patch release receives security fixes. A security fix may change a provider protocol lock, release authority, schema, corpus, or result contract when preserving the old behavior would remain unsafe. diff --git a/pyproject.toml b/pyproject.toml index 09cf367..89aad90 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta" [project] name = "skivolve" -version = "0.5.0" +version = "0.6.0" description = "Open-source framework for reproducible A/B evaluation of agent skills and instructions" readme = "README.md" requires-python = ">=3.11" diff --git a/site/docs/index.html b/site/docs/index.html index 852a2c3..822f25d 100644 --- a/site/docs/index.html +++ b/site/docs/index.html @@ -52,7 +52,7 @@
-

Documentation · Version 0.5.0

+

Documentation · Version 0.6.0

Run your first evidence-bound evaluation.

Start with an offline dry run. It validates the suite, tools, exact sources, cases, provider locks, and selection before a model is invoked or result artifact is written.

@@ -77,20 +77,20 @@

Requirements

Skivolve runs generated code. Read the security model before using proprietary fixtures, private holdouts, or valuable provider credentials.

Install the verified release

- 
git clone --branch v0.5.0 https://github.com/Dhi13man/skivolve.git
+          
git clone --branch v0.6.0 https://github.com/Dhi13man/skivolve.git
 cd skivolve
 python3 -m venv .venv
 . .venv/bin/activate
-mkdir -p /tmp/skivolve-0.5.0
-gh release download v0.5.0 --repo Dhi13man/skivolve \
-  --pattern "skivolve-0.5.0*" --pattern SHA256SUMS \
-  --dir /tmp/skivolve-0.5.0
-(cd /tmp/skivolve-0.5.0 && sha256sum --check SHA256SUMS)
+mkdir -p /tmp/skivolve-0.6.0
+gh release download v0.6.0 --repo Dhi13man/skivolve \
+  --pattern "skivolve-0.6.0*" --pattern SHA256SUMS \
+  --dir /tmp/skivolve-0.6.0
+(cd /tmp/skivolve-0.6.0 && sha256sum --check SHA256SUMS)
 gh attestation verify \
-  /tmp/skivolve-0.5.0/skivolve-0.5.0-py3-none-any.whl \
+  /tmp/skivolve-0.6.0/skivolve-0.6.0-py3-none-any.whl \
   --repo Dhi13man/skivolve
 python -m pip install \
-  /tmp/skivolve-0.5.0/skivolve-0.5.0-py3-none-any.whl

+  /tmp/skivolve-0.6.0/skivolve-0.6.0-py3-none-any.whl

This leaves the tagged reference suite beside a provenance-verified installation. The runtime has one exact third-party dependency for RFC 8785 JSON canonicalization.

Validate without dispatch

diff --git a/site/index.html b/site/index.html index 2e4d9d7..3fda500 100644 --- a/site/index.html +++ b/site/index.html @@ -46,7 +46,7 @@ "license": "https://opensource.org/license/mit", "programmingLanguage": "Python", "runtimePlatform": "Linux and Python 3.11 or newer", - "version": "0.5.0", + "version": "0.6.0", "isAccessibleForFree": true, "keywords": "agent skill evaluation, instruction evaluation, agent harness evaluation, reproducible A/B evaluation, blinded pairwise comparison" } diff --git a/site/sitemap.xml b/site/sitemap.xml index 6a8ea6e..fa47ac2 100644 --- a/site/sitemap.xml +++ b/site/sitemap.xml @@ -1,7 +1,7 @@ - https://dhi13man.github.io/skivolve/2026-07-17 - https://dhi13man.github.io/skivolve/docs/2026-07-17 + https://dhi13man.github.io/skivolve/2026-08-07 + https://dhi13man.github.io/skivolve/docs/2026-08-07 https://dhi13man.github.io/skivolve/corpus/2026-07-17 https://dhi13man.github.io/skivolve/architecture/2026-07-17 https://dhi13man.github.io/skivolve/security/2026-07-17 diff --git a/skivolve/__init__.py b/skivolve/__init__.py index c1a58b7..6c2d8ac 100644 --- a/skivolve/__init__.py +++ b/skivolve/__init__.py @@ -23,7 +23,7 @@ ) from .runner import EvalRunner, RunSelection, RunnerError -__version__ = "0.5.0" +__version__ = "0.6.0" __all__ = [ "ClaudeCliProvider", diff --git a/skivolve/comparator-profile-authority.json b/skivolve/comparator-profile-authority.json index 100ebd9..9c44739 100644 --- a/skivolve/comparator-profile-authority.json +++ b/skivolve/comparator-profile-authority.json @@ -4,8 +4,8 @@ { "id": "plain-language-revision-v1", "descriptor_sha256": "60806e964d6c415d1ebb007976acedd1286a2ec6dd788442e58f345cbbd26b30", - "production_release_sha256": "da012be22caeb1c76b37b181537a8f4e061419b35c520bde6d4dce484a8c9c40", - "test_release_sha256": "fdf61ed4ff33650a28c4431b98e8553205fb0c3aafc457844efcaad6f4c0958b", + "production_release_sha256": "aece988498ecc3427d1ca22073d7e6507306ffd79229350730055b8b649b6376", + "test_release_sha256": "6323bd82b5be4c1a232fbd892dbe8a6adbe1d5e92287443e313dac35533f3c8f", "certification_contract_sha256": "48acdc90136e871ab9cea000c76f2ec94c517ed4466d6cba5beb57f5b4a9c265", "requires_live_certification": true, "authority_scope": "test" @@ -13,8 +13,8 @@ { "id": "software-engineering-v1", "descriptor_sha256": "6a166ed3a313ee145d00519382c93c9fb56223aaf9b80f29806428f53f505e35", - "production_release_sha256": "177f65fe98ea11ca11e9f5998070ff4c5d9a5233ba362d97e43356422c6f01f0", - "test_release_sha256": "ba789cdad72490699914d2046565e8a2fc4132252e31b2d8c5e4e279ffd2554e", + "production_release_sha256": "42696ed92dcbc7e896a41458e6e229b29bf240de56da66f0fbc6730db24a709f", + "test_release_sha256": "a8809f54dea239c209d51b36dc7a4427e7fe37fbf9470489f0a8f5af72d4bad7", "certification_contract_sha256": "48acdc90136e871ab9cea000c76f2ec94c517ed4466d6cba5beb57f5b4a9c265", "requires_live_certification": true, "authority_scope": "production" diff --git a/skivolve/comparator_calibration/release.json b/skivolve/comparator_calibration/release.json index 6c4fe27..d31f142 100644 --- a/skivolve/comparator_calibration/release.json +++ b/skivolve/comparator_calibration/release.json @@ -184,7 +184,7 @@ "profile_registry_source_sha256": "1582fa2eaebdf3c645f16918e2d5a62a279c176f55c1451d81aa48072b27648a", "provider_capability_registry_source_sha256": "90871a063abcd1061c4d336589667837dd2d07ecfabcb69aa642ed5db283c07e", "harness_manifest_source_sha256": "2d2924e7168a789cfa37ba513a30b4ceef28135d830127e833c7d3e1dc5c0569", - "harness_package_source_sha256": "eb4d6316c4ed472038178dc19ef6f10dc76916ff7d2b3075b3a88100074bbba2", + "harness_package_source_sha256": "df29ab44d3cdd23f3b668a1c3605d7d7ffed8dadd750e41d5062e0f430f3f367", "run_evals_source_sha256": "7f1c9665fa0b5715b0ff82bb7a1449545422533fee8927ae693970bed20802d5", "holdout_plan_source_sha256": "38981b6a9f272d02418ca99e2f2a31666a22988e4ca67606f53e50fae6332b2b", "prepare_holdout_plan_source_sha256": "b26f8592d541a32f250699f6be77a9229b349c7f6bf893e76a1533610d1661a2", diff --git a/skivolve/comparator_calibration/tests/test-release.json b/skivolve/comparator_calibration/tests/test-release.json index 026eb1b..894cde5 100644 --- a/skivolve/comparator_calibration/tests/test-release.json +++ b/skivolve/comparator_calibration/tests/test-release.json @@ -166,7 +166,7 @@ "profile_registry_source_sha256": "1582fa2eaebdf3c645f16918e2d5a62a279c176f55c1451d81aa48072b27648a", "provider_capability_registry_source_sha256": "90871a063abcd1061c4d336589667837dd2d07ecfabcb69aa642ed5db283c07e", "harness_manifest_source_sha256": "2d2924e7168a789cfa37ba513a30b4ceef28135d830127e833c7d3e1dc5c0569", - "harness_package_source_sha256": "eb4d6316c4ed472038178dc19ef6f10dc76916ff7d2b3075b3a88100074bbba2", + "harness_package_source_sha256": "df29ab44d3cdd23f3b668a1c3605d7d7ffed8dadd750e41d5062e0f430f3f367", "run_evals_source_sha256": "7f1c9665fa0b5715b0ff82bb7a1449545422533fee8927ae693970bed20802d5", "holdout_plan_source_sha256": "38981b6a9f272d02418ca99e2f2a31666a22988e4ca67606f53e50fae6332b2b", "prepare_holdout_plan_source_sha256": "b26f8592d541a32f250699f6be77a9229b349c7f6bf893e76a1533610d1661a2", diff --git a/skivolve/plain_language_calibration/release.json b/skivolve/plain_language_calibration/release.json index 451d65f..5f67951 100644 --- a/skivolve/plain_language_calibration/release.json +++ b/skivolve/plain_language_calibration/release.json @@ -166,7 +166,7 @@ "profile_registry_source_sha256": "1582fa2eaebdf3c645f16918e2d5a62a279c176f55c1451d81aa48072b27648a", "provider_capability_registry_source_sha256": "90871a063abcd1061c4d336589667837dd2d07ecfabcb69aa642ed5db283c07e", "harness_manifest_source_sha256": "2d2924e7168a789cfa37ba513a30b4ceef28135d830127e833c7d3e1dc5c0569", - "harness_package_source_sha256": "eb4d6316c4ed472038178dc19ef6f10dc76916ff7d2b3075b3a88100074bbba2", + "harness_package_source_sha256": "df29ab44d3cdd23f3b668a1c3605d7d7ffed8dadd750e41d5062e0f430f3f367", "run_evals_source_sha256": "7f1c9665fa0b5715b0ff82bb7a1449545422533fee8927ae693970bed20802d5", "holdout_plan_source_sha256": "38981b6a9f272d02418ca99e2f2a31666a22988e4ca67606f53e50fae6332b2b", "prepare_holdout_plan_source_sha256": "b26f8592d541a32f250699f6be77a9229b349c7f6bf893e76a1533610d1661a2", diff --git a/skivolve/plain_language_calibration/tests/test-release.json b/skivolve/plain_language_calibration/tests/test-release.json index 1065a10..e4b7b91 100644 --- a/skivolve/plain_language_calibration/tests/test-release.json +++ b/skivolve/plain_language_calibration/tests/test-release.json @@ -148,7 +148,7 @@ "profile_registry_source_sha256": "1582fa2eaebdf3c645f16918e2d5a62a279c176f55c1451d81aa48072b27648a", "provider_capability_registry_source_sha256": "90871a063abcd1061c4d336589667837dd2d07ecfabcb69aa642ed5db283c07e", "harness_manifest_source_sha256": "2d2924e7168a789cfa37ba513a30b4ceef28135d830127e833c7d3e1dc5c0569", - "harness_package_source_sha256": "eb4d6316c4ed472038178dc19ef6f10dc76916ff7d2b3075b3a88100074bbba2", + "harness_package_source_sha256": "df29ab44d3cdd23f3b668a1c3605d7d7ffed8dadd750e41d5062e0f430f3f367", "run_evals_source_sha256": "7f1c9665fa0b5715b0ff82bb7a1449545422533fee8927ae693970bed20802d5", "holdout_plan_source_sha256": "38981b6a9f272d02418ca99e2f2a31666a22988e4ca67606f53e50fae6332b2b", "prepare_holdout_plan_source_sha256": "b26f8592d541a32f250699f6be77a9229b349c7f6bf893e76a1533610d1661a2",