Skip to content

Releases: kabirnarang39/skillci

v0.4.1

Choose a tag to compare

@github-actions github-actions released this 25 Jul 22:07

Changelog

  • 52e927f Add golangci-lint config, fix real findings, zero the rest
  • 46921e1 Add judge and fuzz_llm examples to example-skill
  • c7a85e0 CI: add -race, an OS matrix, and a golangci-lint step
  • 8ec4cec Drop external Google Fonts import from dashboard pages
  • a2ca3d7 Fix CI: golangci-lint-action needs v9, not v6, for golangci-lint v2
  • 64aa2de README: call out the fail_on:regression first-run surprise
  • aa7a63a Release prep: CHANGELOG v0.4.1, bump version refs, fix stale action default
  • d8158c7 Test: bisect's zero-history error path guides the user to --good
  • c4e006b Test: prove RunMatrix attributes per-model results correctly
  • 4a2c7b2 scoop bucket update for skillci version v0.4.0

v0.4.0

Choose a tag to compare

@github-actions github-actions released this 25 Jul 20:47

Changelog

  • cb45686 Add design doc: redteam adversarial assertions
  • 5c25ca3 Add implementation plan for redteam adversarial assertions
  • b5b1c8a Add internal/redteam: plugin registry, 2 deterministic attack plugins
  • cedf126 Add redteam example, untrack internal planning docs
  • 711ad75 Release v0.4.0
  • faab16d cmd: report redteam findings in eval/regress output
  • f41311c evalspec: add redteam:/redteam_strict: assertion fields
  • 2e0157d gofmt: fix redteam.go formatting (blank comment line before paragraph break)
  • 5cd1d44 lint: add redteam-strict-without-redteam rule
  • 5008ab8 regress: prove a first-time-failing redteam case self-grows with zero changes
  • ae0ecfa runner/regress/redteam: fix 3 whole-branch review findings
  • 7536c70 runner: execute redteam plugins in RunCase
  • de8a175 scoop bucket update for skillci version v0.3.3

v0.3.3

Choose a tag to compare

@github-actions github-actions released this 25 Jul 18:47

Changelog

  • 0401551 Add flake_always_sample: close the got-lucky-on-attempt-1 blind spot
  • 827a53a Release v0.3.3
  • 33107bd Remove Go Report Card badge, service is retired
  • 9975409 scoop bucket update for skillci version v0.3.2

v0.3.2

Choose a tag to compare

@github-actions github-actions released this 25 Jul 15:29

Changelog

  • ffbc3b7 Add Windows install path: Scoop bucket + windows builds
  • 872dd7d Release v0.3.2
  • 5f0cca0 vscode: add extension icon for marketplace listing

v0.3.1

Choose a tag to compare

@github-actions github-actions released this 25 Jul 15:19

Changelog

  • 7e456dd Add community/discovery assets: CoC, badges, social preview
  • 1eeaec0 Fix contact email in SECURITY.md and README example
  • 2ce2718 Release v0.3.1
  • 4a56756 Remove star-history badge, endpoint returns 500/timeout

v0.3.0

Choose a tag to compare

@github-actions github-actions released this 25 Jul 11:43

Changelog

  • bb5d4d0 Add SECURITY.md and CHANGELOG.md
  • c35158f Add a VS Code extension for live SKILL.md linting
  • 22d1048 Add a real end-to-end integration test for the VS Code extension
  • 948ca3e Add boundary-value tests for budget assertions and flake_retries: 1
  • a7337c4 Add chain-of-thought reasoning to judge verdicts
  • b06d081 Add design spec: LLM-as-judge hardening (CoT, caching, self-consistency)
  • 07916d7 Add direct unit test coverage for parseTriggerMarker
  • b31b579 Add fuzz_llm: generate-once-cache-forever LLM paraphrase testing
  • bb73129 Add issue templates and a PR template
  • 25e6103 Add judge-cache.json caching and judge_samples self-consistency voting
  • 54b5b4b Add judge_mode: batched/isolated judge call grouping
  • e12c52a Add judgecache package for caching LLM-as-judge verdicts
  • f33c89c Add native Go fuzz tests for the parsers and pure algorithms
  • ec61a79 Add opt-in pinned-source hash verification (--verify-pinned-sources)
  • 16cced6 Add pr-comment: post regress results directly on the PR
  • 7946abe Add real concurrent-request test for dashboard ingest
  • 1a6ea85 Add runner-level test for corrupt judge-cache.json degrading to live calls
  • 5a9ee8c Add skillci check --format json for machine-parseable lint output
  • d9b478b Clear stale pending snapshots when a case reverts to golden
  • 2a1afdc Close coverage gaps found via true whole-program coverage analysis
  • 11544ff Close error-path and open-pr branch coverage gaps
  • 3dfc82c Close testing gap: CRLF line endings fail cleanly, not silently
  • fd6ce14 Close testing gap: dedicated line-number test per body-relative scanner
  • 4a8ad3c Close testing gap: extension's referenced-file diagnostic path
  • deb6b75 Compare dashboard ingest tokens in constant time
  • ecfe9fb Document the brew trust step Homebrew requires for third-party taps
  • 1e6010c Exclude .bin/, test-fixtures/, and test build output from the packaged .vsix
  • 6cb9bb5 Fix SKILL.md issue line numbers to point at the real file, not the body
  • 4e0b8c4 Fix SSRF in check --verify-pinned-sources
  • aed32b5 Fix lint-on-type: it never actually reflected unsaved keystrokes
  • beb1c65 Fuzz synonym-swap: generate one mutation per eligible word
  • af0a682 Lock in yaml.v3's alias-bomb protection through skillci's own entry points
  • 3f4cd00 Make main() thin and testable in both binaries; close readSkillMeta gaps
  • f065744 Omit unset Assertions fields when marshaling generated eval cases
  • 8c818d5 Prune orphaned bisect worktrees left by a killed run
  • ea6713c Reject duplicate or missing eval case names at load time
  • a767ab6 Reject empty tokens in SKILLCI_INGEST_TOKENS entries
  • e822da2 Reject unrecognized fail_on values at config load time
  • 6adbda4 Release v0.3.0: LLM-judge hardening, README overhaul
  • bfe6ec6 Remove committed superpowers design spec
  • 3bd9a1b Remove unused hadHistory capture in RunMatrix
  • 37e2bf2 Retry transient Anthropic API failures with backoff
  • 49abe16 Return a copy from judgecache.Cache.Samples
  • 4a97628 Scope prbranch.Push's commit to its own paths
  • 74c20db Silence Cobra's usage dump on the other commands' errors
  • 854f707 Split dashboard trend sparkline per model, add a regression badge
  • a9cbaaa Stop double-printing every command's error message
  • 606f6e1 Test judge reasoning parser's malformed-line guard
  • f02f4cb Validate per-case assert.judge_mode, matching global judge_mode
  • 638102f Warn on unaddressed generated eval cases older than 14 days

v0.2.0

Choose a tag to compare

@github-actions github-actions released this 24 Jul 22:15

Changelog

  • 26d7c7c Add --auto-bisect to run bisect automatically on new regressions
  • 9d4cd0a Add --open-pr to commit generated eval cases and open a pull request
  • 0b9e377 Add AST02 (unpinned dependency) lint rule
  • 4db3af5 Add AST05 (untrusted external instructions) lint rule
  • 2934b61 Add GoReleaser packaging + release workflow + Homebrew tap config
  • e1871c2 Cache verified bisect endpoints across separate CLI invocations
  • c98c25b Capture full failure context in self-growing eval loop's generated cases
  • d154c57 feat: extend eval-lint's _strict pairing checks to all four other pairs
  • ba4ca04 feat: pin the GitHub Action to a real release version
  • 8ecd62f fix: cap .skillci/history.json to the 200 most recent runs
  • 3d340da fix: cap dashboard ingest body size, scope tokens per owner/repo
  • 7a0b70c fix: handle merge commits and multiple candidate culprits in bisect