heretek-claude-harness

Heretek-AI/heretek-claude-harness

Fork 0

mirror of https://github.com/Heretek-AI/heretek-claude-harness.git synced 2026-10-12 02:03:47 +00:00

Commit Graph

Select branches

Hide Pull Requests

auto/157-yaml-load-without-loader-in-scripts-refresh-pins-p

auto/158-yaml-load-without-loader-in-scripts-catalog-update

auto/159-heretek-default-branch-env-var-unvalidated-in-scri

auto/160-heretek-session-state-dir-env-var-unvalidated-in-s

auto/161-plugins-hooks-scripts-quality-gate-py-scope-path-c

auto/162-plugins-hooks-scripts-fast-gate-py-file-path-valid

auto/163-heretek-telemetry-root-env-var-unvalidated-in-plug

auto/164-http-body-size-limits-on-github-api-calls

auto/166-document-git-clone-url-allowlist-contract-in-scrip

auto/167-scripts-plan-pre-flight-py-path-resolution-consist

auto/168-scripts-generate-marketplace-py-atomic-write

chore/housekeeping-batch-2026-08-08

chore/python-code-smells

chore/sonar-remaining

ci/github-actions-hardening

dependabot/github_actions/github-actions-0309950c1e

dependabot/go_modules/plugins/re-ai/tools/RE-BREAKER/vendored/ssh-mcp/go_modules-efa95dd7b3

dependabot/pip/charset-normalizer-3.5.0

dependabot/pip/pip-26.2.1

dependabot/pip/ruff-0.16.3

feat/autopilot-issue-loop

fix/10-first-party-adrs

fix/11-refresh-pins-update-shas

fix/12-security-mailbox

fix/14-marketplace-version-design

fix/15-rust-clippy-skill

fix/16-dependabot-cves

fix/20-hook-orchestrator-adr

fix/53-ci-gate

fix/60-smoke-test

fix/60-smoke-test-cleanup

fix/9-plugin-json-dependencies

fix/dependabot-pr-25

fix/dependabot-pr-29

fix/nosonar-same-line

fix/python-security-rules

fix/requests-dep-missing

fix/security-scan-pr-detector-handles-adds

fix/shell-script-issues

fix/sonar-blocker

harbor-terminal-bench-ab-impl

heretek-maintenance-skills

main

refactor/cognitive-complexity

trim/plan

trim/r1-r6-r7-r11-hooks-and-gates

trim/r2-r3-inline-utils

trim/r4-audit-decide

trim/r5-spike-purge

trim/r8-r10-s1-s4-compaction-and-collapse

trim/spec

worktree-fix-pr22-ci

#101

#102

#103

#104

#105

#106

#107

#108

#125

#129

#130

#131

#133

#135

#136

#137

#138

#139

#140

#142

#143

#144

#145

#146

#147

#148

#149

#151

#152

#153

#154

#155

#156

#175

#180

#181

#182

#183

#184

#185

#186

#187

#188

#189

#192

#194

#195

#196

#197

#198

#199

#200

#201

#202

#203

#204

#205

#209

#217

#219

#22

#220

#221

#222

#223

#224

#225

#227

#228

#229

#23

#230

#234

#235

#24

#244

#245

#246

#246

#25

#251

#251

#252

#252

#253

#253

#254

#254

#26

#27

#28

#29

#35

#36

#37

#38

#40

#41

#42

#43

#44

#45

#98

v1.0.0

9aef55be23 docs: add deprecation notice redirecting to @heretek-ai/agent-proof main Claude 2026-08-20 15:18:07 -04:00
df52439880 build(deps): bump the github-actions group with 5 updates dependabot/github_actions/github-actions-0309950c1e dependabot[bot] 2026-08-17 09:30:48 +00:00
3f932c781b build(deps): bump charset-normalizer from 3.4.9 to 3.5.0 dependabot/pip/charset-normalizer-3.5.0 dependabot[bot] 2026-08-17 09:30:44 +00:00
c1c5c8ea70 build(deps-dev): bump ruff from 0.16.1 to 0.16.3 dependabot/pip/ruff-0.16.3 dependabot[bot] 2026-08-17 09:30:31 +00:00
a9bd0a9dcd build(deps-dev): bump pip from 26.1.2 to 26.2.1 dependabot/pip/pip-26.2.1 dependabot[bot] 2026-08-17 09:30:22 +00:00
d76894c659 build(deps): bump the go_modules group across 2 directories with 4 updates dependabot/go_modules/plugins/re-ai/tools/RE-BREAKER/vendored/ssh-mcp/go_modules-efa95dd7b3 dependabot[bot] 2026-08-13 17:00:24 +00:00
27ef095290 fix: line endings Claude 2026-08-13 12:53:31 -04:00
2250c79062 feat: consolidate RE-AI and heretek-skills into unified Claude Code Plugin Marketplace Claude 2026-08-13 12:53:27 -04:00
ae57d581c6 refactor: remove heretek-swarm from heretek-claude-harness to keep it standalone Claude 2026-08-13 12:23:41 -04:00
73e2b3fd98 feat: consolidate agent harness components (#244) BillyOutlastandClaude 2026-08-13 12:16:42 -04:00
056b7d4693 fix(script): sync terminal_bench_ab.sh Claude 2026-08-13 01:08:47 -04:00
a7d1db07b1 ci: replace custom script steps with published Heretek-AI/harness-audit@v1 action Claude 2026-08-12 23:55:03 -04:00
dce3debf35 feat: add 4-pillar readiness scorecard calculation & badge generator Claude 2026-08-12 23:44:40 -04:00
94decd04f0 feat: integrate Harbor TerminalBench 2.0 A/B evaluation suite, heretek eval subcommand, and GitHub Action Claude 2026-08-12 23:35:11 -04:00
822608d262 ci: add publish-npm.yml workflow for automatic npm releases Claude 2026-08-12 23:27:26 -04:00
e112bca133 feat: publish @heretek-ai/[email protected] to npm registry Claude 2026-08-12 23:25:38 -04:00
d6951fdbc9 docs: total documentation pass across CLAUDE.md, AGENTS.md, README.md, scripts, and hooks Claude 2026-08-12 23:21:06 -04:00
73ca057a75 feat: add ruby, elixir, csharp language packs and heretek init auto-detector rules Claude 2026-08-12 23:07:39 -04:00
00b62d6106 feat: add heretek status scorecard TUI and heretek metrics latency benchmark Claude 2026-08-12 23:05:53 -04:00
8542686746 feat: add npm package launcher and GitHub Pages marketplace publishing workflow Claude 2026-08-12 23:04:11 -04:00
111de22e9d feat: add heretek init auto-detector and python, rust, typescript language packs Claude 2026-08-12 23:02:13 -04:00
117d9df89c feat: add frontend-design, web-design-guidelines, grilling skills and config-protection hook Claude 2026-08-12 22:31:55 -04:00
e853047f59 feat: add fallow plugin and agentic-readiness audit skill Claude 2026-08-12 20:05:11 -04:00
fce6261ee0 docs: update README.md with 9-pack marketplace architecture Claude 2026-08-12 19:58:21 -04:00
be5d141655 feat: overhaul marketplace into 9 logical quality packs (best-practices, quality-audit, ci-cd, pre-commit, go, cpp, java, expanded agents & hooks) Claude 2026-08-12 19:57:04 -04:00
46930761c8 docs: overhaul README.md to reflect marketplace CLI and plugin architecture Claude 2026-08-12 18:18:45 -04:00
d821cad39c docs: overhaul CLAUDE.md & AGENTS.md, purge obsolete agent chuff Claude 2026-08-12 18:16:39 -04:00
d61e0dd586 feat: clean-slate rebuild of plugin marketplace & distribution CLI Claude 2026-08-12 17:57:19 -04:00
9a86dbf3e0 feat: complete clean-slate rebuild of heretek-claude-harness Claude 2026-08-12 17:47:33 -04:00
62aeea4dfc fix(scripts): pass --mounts to Harbor so plugins bind-mount into Docker container for Agent A Claude 2026-08-12 17:33:00 -04:00
e031d80f90 feat(workflow): wire n_tasks through to harbor; full tier via manual trigger Claude 2026-08-12 17:16:16 -04:00
7c5f4ea7df fix(workflow): also self-heal 'automated' label Claude 2026-08-12 14:07:50 -04:00
87c5b7133e fix(workflow): self-heal missing terminal-bench-ab label Claude 2026-08-12 14:05:09 -04:00
021dfa6b7b feat(scripts): add --debug to harbor runs for visibility Claude 2026-08-12 11:55:16 -04:00
5b352b2911 fix(workflow): bump python-version to 3.12 for harbor 0.21.0 compatibility Claude 2026-08-12 09:52:00 -04:00
d61686d9c1 docs(scripts): correct stale harbor layout comment in terminal_bench_ab.sh Claude 2026-08-12 02:07:31 -04:00
2dffa8904a docs(scripts): correct harbor 0.21.0 schema + remove stale Follow-up Claude 2026-08-12 01:59:25 -04:00
4c182685f0 feat(scripts): aggregate_results invocations after each harbor run Claude 2026-08-12 01:55:40 -04:00
8259d5e16f test: extract write_trial factory + round-trip through Summary Claude 2026-08-12 01:51:19 -04:00
c5172ad13f feat(scripts): aggregate_results.py per-trial walker Claude 2026-08-12 01:46:02 -04:00
3f9655f32e docs(plan): aggregate-results implementation plan Claude 2026-08-12 01:40:48 -04:00
b4ef9ade07 docs(spec): aggregate-results design (close #236) Claude 2026-08-12 01:36:40 -04:00
8c5803e638 Merge pull request #235 from Heretek-AI/harbor-terminal-bench-ab-impl BillyOutlast 2026-08-12 01:11:38 -04:00
0c9236b84a fix(workflow): use --no-build on uv tool install harbor harbor-terminal-bench-ab-impl Claude 2026-08-11 23:52:54 -04:00
78c59e7ac2 fix(workflow): suppress S2648 on uv tool install with rationale Claude 2026-08-11 23:43:01 -04:00
7eb8f2ba8d test: extract shared factories into tests/_factories.py Claude 2026-08-11 23:20:40 -04:00
c852341f14 fix(workflow): pin uv + harbor versions; add --only-binary :all: Claude 2026-08-11 21:44:17 -04:00
5ee8c38617 test: wrap exception test in lambda to isolate the throwing call Claude 2026-08-11 21:41:31 -04:00
4ec99cfbe0 refactor(scripts): reduce render_markdown cognitive complexity from 36 to <15 Claude 2026-08-11 21:40:22 -04:00
730aa67214 fix(scripts): use [[ ]] for tests in terminal_bench_ab.sh Claude 2026-08-11 21:36:38 -04:00
a47f0d0050 docs(scripts): record Phase 5 smoke run findings Claude 2026-08-11 20:06:33 -04:00
65074e6160 ci: actionlint the Terminal-Bench A/B workflow Claude 2026-08-11 20:02:35 -04:00
2a9426547f feat(workflow): terminal-bench-ab.yml + schema tests Claude 2026-08-11 20:00:15 -04:00
71670760c1 feat(scripts): secret leak scan + render guard Claude 2026-08-11 19:55:18 -04:00
249f4b8073 test: edge case fixtures (all-fail, identical, missing) Claude 2026-08-11 19:52:30 -04:00
37d311038f test: golden fixture case-quick-8-pass-5 + regression test Claude 2026-08-11 19:48:53 -04:00
70b8486e2f feat(scripts): render Markdown comparison report Claude 2026-08-11 19:46:00 -04:00
ed390cf263 feat(scripts): compute_diff for agent comparison Claude 2026-08-11 19:43:48 -04:00
321c56706a feat(scripts): comparison_report.py arg parser + summary loader Claude 2026-08-11 19:39:05 -04:00
ed2365f49a feat(scripts): terminal_bench_ab.sh runs two harbor agents Claude 2026-08-11 19:31:07 -04:00
62f6b87497 docs(plan): Harbor + Terminal-Bench A/B implementation plan Claude 2026-08-11 19:14:46 -04:00
dca9c27110 docs(spec): Harbor + Terminal-Bench A/B eval design Claude 2026-08-11 17:23:51 -04:00
eeac7febe3 docs(CLAUDE.md): add subagent-stall rule + GIT_* env safety Claude 2026-08-11 12:12:13 -04:00
1fdd8467d2 docs: branch cleanup design + plan (autonomous execution) Claude 2026-08-11 12:04:25 -04:00
a6088f1d59 sprint: v3.5 observability (drains #115-#124, closes #126) (#234)
BillyOutlast Claude t
2026-08-11 11:54:53 -04:00
08899bce4b docs(plan): v3.5 observability sprint implementation plan tandClaude 2026-08-11 06:22:32 -04:00
68e168f342 docs(spec): clarify ADR placement + autopilot flag caveat tandClaude 2026-08-11 06:14:55 -04:00
89e0e05123 fix(issue-loop): strip GIT_* env from subprocess calls in branch.py + 3 test fixtures tandClaude 2026-08-11 06:13:43 -04:00
f11e0e2d6c docs: compact CLAUDE.md (76->14 lines) + skills + sonar bodies (#225)
BillyOutlast John Smith Claude
2026-08-11 00:37:09 -04:00
b7cd41cb61 docs: compact CLAUDE.md (76->14 lines) + skills + sonar bodies trim/r8-r10-s1-s4-compaction-and-collapse John SmithandClaude 2026-08-11 00:34:17 -04:00
0d90415e2d feat(trim): R1+R6+R7+R11 hooks locality + dispatcher + secrets + ci.sh (#224)
BillyOutlast John Smith Claude
2026-08-11 00:29:23 -04:00
37da068a85 feat(trim): R1+R6+R7+R11 hooks locality + dispatcher + secrets + ci.sh trim/r1-r6-r7-r11-hooks-and-gates John SmithandClaude 2026-08-11 00:25:54 -04:00
b2addfdde4 feat(trim): R2 inline require_session_id into drift_detector.py (#223) BillyOutlast 2026-08-11 00:04:20 -04:00
f4f46f12b4 feat(trim): R2 inline require_session_id into drift_detector.py trim/r2-r3-inline-utils John SmithandClaude 2026-08-11 00:02:17 -04:00
6aff48207d feat(trim): R4 delete scripts/audit/ (no consumer found) (#222) BillyOutlast 2026-08-10 23:59:22 -04:00
76132d0020 feat(trim): R4 delete scripts/audit/ (no consumer found) trim/r4-audit-decide John SmithandClaude 2026-08-10 23:56:58 -04:00
7a90754921 feat(trim): R5 spike purges + build artifact cleanup (#221) BillyOutlast 2026-08-10 23:55:47 -04:00
7255d44d11 feat(trim): R5 spike purges + build artifact cleanup trim/r5-spike-purge John SmithandClaude 2026-08-10 23:53:28 -04:00
af3cb8275c docs(plan): add heretek-harness-trim implementation plan (#220) BillyOutlast 2026-08-10 23:49:29 -04:00
7788fbc2b2 docs(plan): add heretek-harness-trim implementation plan trim/plan John SmithandClaude 2026-08-10 23:47:18 -04:00
fb4e20a757 docs(spec): add heretek-harness-trim design (#219) BillyOutlast 2026-08-10 23:43:42 -04:00
314fe782a8 docs(spec): add heretek-harness-trim design (closes audit-to-spec brainstorm) trim/spec John SmithandClaude 2026-08-10 23:41:17 -04:00
2fe0288439 feat(hooks): A0 pre-commit core rollout (closes #206/#207/#208) (#217)
BillyOutlast Claude John Smith
2026-08-10 23:02:30 -04:00
d08aa0e23b feat: autopilot issue-loop with 5-path routing (fix|investigate|spec|break-down|skip) (#209)
BillyOutlast Claude John Smith
2026-08-10 21:03:37 -04:00
521ac992ec fix(security): validate input path before resolve() to address SonarCloud S8707 feat/autopilot-issue-loop John SmithandClaude 2026-08-10 20:09:49 -04:00
6638fd2a73 fix(security): inline path-traversal validation at filesystem access sites John SmithandClaude 2026-08-10 20:05:58 -04:00
8aad2cbf97 fix(security): inline path-traversal validation at filesystem access sites John SmithandClaude 2026-08-10 20:05:06 -04:00
affc7dfb36 fix(tests): remove redundant rc = 1 initialization in _capture_main John SmithandClaude 2026-08-10 19:57:51 -04:00
ca6db975f0 fix(autopilot): address SonarCloud review findings on PR #209 John SmithandClaude 2026-08-10 19:39:31 -04:00
d4d3f88c17 Merge remote-tracking branch 'origin/main' into feat/autopilot-issue-loop John Smith 2026-08-10 19:32:15 -04:00
301a2ba12e docs(spec): autopilot issue-loop design + plan + refactor ADR John SmithandClaude 2026-08-10 19:31:59 -04:00
e3625977eb fix(autopilot): add mark-investigated CLI wrapper + 3 minor cleanups (final-review fixes) John Smith 2026-08-10 19:21:36 -04:00
c28a74ac7b feat(telemetry): add harness_test.py fixture runner (sub-spec 2 §2.3) (#205)
BillyOutlast John Smith Claude
2026-08-10 19:13:57 -04:00
2689f4a3e3 feat(drain): autopilot integration smoke test (5 fixtures, all paths) John Smith 2026-08-10 19:10:51 -04:00
bd07d55c80 feat(skill): rewrite issue-loop SKILL.md for autopilot flow John Smith 2026-08-10 19:07:57 -04:00
0df8ec4d74 feat(config): autopilot paths + periodic summary + new subagent models John Smith 2026-08-10 19:06:01 -04:00
3301795188 feat(prompts): extend critic for spec review + trivial-vs-substantive feedback John Smith 2026-08-10 19:04:12 -04:00
4c06aafb45 feat(prompts): add breakdowner subagent prompt John Smith 2026-08-10 19:02:40 -04:00
611e570408 feat(prompts): add spec-writer subagent prompt John Smith 2026-08-10 19:01:03 -04:00
aee5aa9277 feat(prompts): add investigator subagent prompt John Smith 2026-08-10 18:59:06 -04:00

1 2 3 4 5 ...