Skip to content

Releases: oleg494/coding-kit

v4.4.0 — Memory Organization, Dynamic Project Taxonomy & Warmup Lifecycle

Choose a tag to compare

@oleg494 oleg494 released this 08 Sep 08:20

Release v4.4.0 — Memory organization, dynamic project taxonomy, qualitative importance levels, atomic batch classification, and memory warmup verification status badges & unsure feed importance precedence.


Transparent Release Correction Notice

  • Initial Tag & CI Failure: The initial release publication (8f23c5b) contained un-restamped skill metadata (version: "4.3.1" instead of "4.4.0"), which triggered CI test failure in StampedCorpusTest.test_all_36_skills_stamped across both Ubuntu and Windows runners (Run ID 34203911713).
  • Tag Movement & Scope of Fix: The v4.4.0 tag was subsequently moved to commit 9a5d9acfe078ddc46961cd7b4caa916a9abe53dd (chore(release): restamp 36 skills to 4.4.0), updating metadata.version across all 36 skills and their canonical mirrors, along with checksum updates in integrity-manifest.json (73 files changed, +108 -108).
  • Asset Replacement: The release tarball asset was rebuilt and replaced under the moved tag:
    • File: coding-kit-4.4.0.tar.gz
    • SHA-256: cad5b8c4a89c3c42a7349b3657ba9cbc45600f39fe324e505316ee85978bd8f6
    • Size: 753,173 bytes (515 members rooted under coding-kit-4.4.0/)
    • Action for Early Downloaders: If your archive has previous SHA-256 43d1b8a121b0190c5ef1d960ea901c117b8fc16e737f994dc944c388d7d79c09, please re-download the corrected asset.
  • Verification Proof:
    • Remote CI Matrix: GREEN on both Windows and Ubuntu runners (Run ID 34204343975).
    • Local Test Suite: 738 passed, 2 skipped, 87 subtests passed in 82.96s on Windows Python 3.11.16.

v4.2.0 — instruction precedence, verification calibration & deploy CLI safety

Choose a tag to compare

@oleg494 oleg494 released this 06 Sep 06:50

What's Changed in v4.2.0

Instruction Precedence & Authorization Gate

  • Clarified instruction hierarchy in AGENTS.md and OPS.md (Host system/developer instructions > User instructions > Kit skills). When skill guidance conflicts with user directions, agents follow the user and state the departed skill.
  • Replaced the brainstorming unconditional HARD-GATE with an AUTHORIZATION-GATE: agents proceed directly on authorized reversible local work without halting for redundant re-approval. Pauses remain reserved for irreversible, external, destructive, money/auth/privacy actions, or outcome-changing ambiguity.

Verification Scope Calibration

  • Calibrated verification discipline across superpowers, SKILL_RUNTIME, test-driven-development, dispatching-parallel-agents, verification-before-completion, and testing-discipline.
  • Scoped checks appropriate to the touched components by default; full-suite re-runs on untouched components are no longer required for bounded changes, and unrun suites are never claimed.

Deploy CLI Safety Boundary

  • Added argparse CLI handling to scripts/tools/deploy.py (--canonical, --dry-run, --help).
  • Commands like python scripts/tools/deploy.py --help now safely display usage without triggering unintentional host deployments or router modifications.
  • Added comprehensive regression coverage in tests/test_deploy_cli.py.

Tooling & Runner Resilience

  • Stdlib fallback: Restored full regex-based YAML frontmatter fallback parsing in memory/db-tools/lint_wiki.py and scripts/doctor.py so CI runners and fresh installs without PyYAML pass all hygiene and specification tests cleanly.
  • Cross-drive testing: Handled Windows cross-drive working directory changes (cd /d) in tests/test_findings_lifecycle.py.
  • Backup reliability: scripts/tools/backup_memory.py now exits with status 1 when any database snapshot is skipped.
  • Integrity manifest: Updated byte-level hashing to preserve invalid UTF-8 byte distinctions while maintaining newline equivalence.

Evals & Traps Expansion

  • Expanded trap-suite from 24 to 26 scenarios with authorized-work-proceeds and calibrated-testing.

Licensing & Attribution

  • Preserved license: Proprietary on skills/windows-encoding-fixes with explicit, honest disclosure in README.md (no false claims of a 100% MIT bundle).

Full Commit Diff: v4.0.3...v4.2.0

v4.0.3 — dead-harness cutover

Choose a tag to compare

@oleg494 oleg494 released this 02 Sep 07:44
Release v4.0.3: dead-harness cutover

v4.0.2 — audit remediation

Choose a tag to compare

@oleg494 oleg494 released this 02 Sep 04:03
Release v4.0.2: audit remediation

v4.0.0 — interchange

Choose a tag to compare

@oleg494 oleg494 released this 02 Sep 04:03
Release v4.0.0: interchange

v3.9.0 — devflow gates

Choose a tag to compare

@oleg494 oleg494 released this 02 Sep 04:03
Release v3.9.0: devflow gates

v3.8.0 — context hygiene

Choose a tag to compare

@oleg494 oleg494 released this 02 Sep 04:03
Release v3.8.0: context hygiene

v3.7.0 — standards conformance

Choose a tag to compare

@oleg494 oleg494 released this 02 Sep 04:03
Release v3.7.0: standards conformance

v3.6.0 — honest oracle

Choose a tag to compare

@oleg494 oleg494 released this 02 Sep 04:03
Release v3.6.0: honest oracle (including test-isolation fixes)

v3.5.0 — trust surface

Choose a tag to compare

@oleg494 oleg494 released this 02 Sep 04:03
Release v3.5.0: trust surface