@k2works/claude-code-booster 6.4.0 → 6.5.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/LICENSE +21 -21
- package/README.md +61 -61
- package/bin/claude-code-booster +113 -113
- package/lib/assets/.claude/README.md +287 -287
- package/lib/assets/.claude/agents/xp-architect.md +250 -250
- package/lib/assets/.claude/agents/xp-executive.md +207 -207
- package/lib/assets/.claude/agents/xp-interaction-designer.md +239 -239
- package/lib/assets/.claude/agents/xp-product-manager.md +245 -245
- package/lib/assets/.claude/agents/xp-programmer.md +268 -268
- package/lib/assets/.claude/agents/xp-project-manager.md +229 -229
- package/lib/assets/.claude/agents/xp-technical-writer.md +224 -224
- package/lib/assets/.claude/agents/xp-tester.md +265 -265
- package/lib/assets/.claude/agents/xp-user-representative.md +204 -204
- package/lib/assets/.claude/scripts/generate-inception-deck.mjs +911 -911
- package/lib/assets/.claude/settings.json +11 -11
- package/lib/assets/.claude/skills/ai-agent-guidelines/SKILL.md +111 -111
- package/lib/assets/.claude/skills/analyzing-architecture/SKILL.md +83 -83
- package/lib/assets/.claude/skills/analyzing-business-architecture/SKILL.md +122 -122
- package/lib/assets/.claude/skills/analyzing-business-case/SKILL.md +148 -148
- package/lib/assets/.claude/skills/analyzing-business-strategy/SKILL.md +277 -277
- package/lib/assets/.claude/skills/analyzing-data-model/SKILL.md +77 -77
- package/lib/assets/.claude/skills/analyzing-domain-model/SKILL.md +117 -117
- package/lib/assets/.claude/skills/analyzing-inception-deck/SKILL.md +84 -84
- package/lib/assets/.claude/skills/analyzing-non-functional/SKILL.md +95 -95
- package/lib/assets/.claude/skills/analyzing-operation/SKILL.md +95 -95
- package/lib/assets/.claude/skills/analyzing-requirements/SKILL.md +91 -91
- package/lib/assets/.claude/skills/analyzing-review/SKILL.md +174 -174
- package/lib/assets/.claude/skills/analyzing-tech-stack/SKILL.md +101 -101
- package/lib/assets/.claude/skills/analyzing-test-strategy/SKILL.md +89 -89
- package/lib/assets/.claude/skills/analyzing-ui-design/SKILL.md +80 -80
- package/lib/assets/.claude/skills/analyzing-usecases/SKILL.md +72 -72
- package/lib/assets/.claude/skills/apply-okf-workspace/iteration-1/benchmark.json +20 -0
- package/lib/assets/.claude/skills/apply-okf-workspace/iteration-1/benchmark.md +13 -0
- package/lib/assets/.claude/skills/apply-okf-workspace/iteration-1/eval-1-register-new-adr/eval_metadata.json +14 -0
- package/lib/assets/.claude/skills/apply-okf-workspace/iteration-1/eval-1-register-new-adr/with_skill/grading.json +39 -0
- package/lib/assets/.claude/skills/apply-okf-workspace/iteration-1/eval-1-register-new-adr/with_skill/outputs/docs_after/adr/001-db.md +12 -0
- package/lib/assets/.claude/skills/apply-okf-workspace/iteration-1/eval-1-register-new-adr/with_skill/outputs/docs_after/adr/002-cache-strategy.md +20 -0
- package/lib/assets/.claude/skills/apply-okf-workspace/iteration-1/eval-1-register-new-adr/with_skill/outputs/docs_after/adr/index.md +4 -0
- package/lib/assets/.claude/skills/apply-okf-workspace/iteration-1/eval-1-register-new-adr/with_skill/outputs/docs_after/design/data-model.md +12 -0
- package/lib/assets/.claude/skills/apply-okf-workspace/iteration-1/eval-1-register-new-adr/with_skill/outputs/docs_after/design/index.md +3 -0
- package/lib/assets/.claude/skills/apply-okf-workspace/iteration-1/eval-1-register-new-adr/with_skill/outputs/docs_after/index.md +10 -0
- package/lib/assets/.claude/skills/apply-okf-workspace/iteration-1/eval-1-register-new-adr/with_skill/outputs/docs_after/log.md +7 -0
- package/lib/assets/.claude/skills/apply-okf-workspace/iteration-1/eval-1-register-new-adr/with_skill/outputs/docs_after/operation/deploy-old.md +12 -0
- package/lib/assets/.claude/skills/apply-okf-workspace/iteration-1/eval-1-register-new-adr/with_skill/outputs/docs_after/operation/deploy.md +12 -0
- package/lib/assets/.claude/skills/apply-okf-workspace/iteration-1/eval-1-register-new-adr/with_skill/outputs/docs_after/operation/index.md +4 -0
- package/lib/assets/.claude/skills/apply-okf-workspace/iteration-1/eval-1-register-new-adr/with_skill/outputs/docs_after/reference/OKF/345/260/216/345/205/245/343/202/254/343/202/244/343/203/211_V0.2.md +965 -0
- package/lib/assets/.claude/skills/apply-okf-workspace/iteration-1/eval-1-register-new-adr/with_skill/outputs/report.md +76 -0
- package/lib/assets/.claude/skills/apply-okf-workspace/iteration-1/eval-1-register-new-adr/without_skill/grading.json +39 -0
- package/lib/assets/.claude/skills/apply-okf-workspace/iteration-1/eval-1-register-new-adr/without_skill/outputs/docs_after/adr/001-db.md +12 -0
- package/lib/assets/.claude/skills/apply-okf-workspace/iteration-1/eval-1-register-new-adr/without_skill/outputs/docs_after/adr/002-cache-strategy.md +20 -0
- package/lib/assets/.claude/skills/apply-okf-workspace/iteration-1/eval-1-register-new-adr/without_skill/outputs/docs_after/adr/index.md +4 -0
- package/lib/assets/.claude/skills/apply-okf-workspace/iteration-1/eval-1-register-new-adr/without_skill/outputs/docs_after/design/data-model.md +12 -0
- package/lib/assets/.claude/skills/apply-okf-workspace/iteration-1/eval-1-register-new-adr/without_skill/outputs/docs_after/design/index.md +3 -0
- package/lib/assets/.claude/skills/apply-okf-workspace/iteration-1/eval-1-register-new-adr/without_skill/outputs/docs_after/index.md +10 -0
- package/lib/assets/.claude/skills/apply-okf-workspace/iteration-1/eval-1-register-new-adr/without_skill/outputs/docs_after/log.md +7 -0
- package/lib/assets/.claude/skills/apply-okf-workspace/iteration-1/eval-1-register-new-adr/without_skill/outputs/docs_after/operation/deploy-old.md +12 -0
- package/lib/assets/.claude/skills/apply-okf-workspace/iteration-1/eval-1-register-new-adr/without_skill/outputs/docs_after/operation/deploy.md +12 -0
- package/lib/assets/.claude/skills/apply-okf-workspace/iteration-1/eval-1-register-new-adr/without_skill/outputs/docs_after/operation/index.md +4 -0
- package/lib/assets/.claude/skills/apply-okf-workspace/iteration-1/eval-1-register-new-adr/without_skill/outputs/docs_after/reference/OKF/345/260/216/345/205/245/343/202/254/343/202/244/343/203/211_V0.2.md +965 -0
- package/lib/assets/.claude/skills/apply-okf-workspace/iteration-1/eval-1-register-new-adr/without_skill/outputs/report.md +22 -0
- package/lib/assets/.claude/skills/apply-okf-workspace/iteration-1/eval-2-verify-reviewed-doc/eval_metadata.json +13 -0
- package/lib/assets/.claude/skills/apply-okf-workspace/iteration-1/eval-2-verify-reviewed-doc/with_skill/grading.json +34 -0
- package/lib/assets/.claude/skills/apply-okf-workspace/iteration-1/eval-2-verify-reviewed-doc/with_skill/outputs/docs_after/adr/001-db.md +12 -0
- package/lib/assets/.claude/skills/apply-okf-workspace/iteration-1/eval-2-verify-reviewed-doc/with_skill/outputs/docs_after/adr/002-cache-strategy.md +11 -0
- package/lib/assets/.claude/skills/apply-okf-workspace/iteration-1/eval-2-verify-reviewed-doc/with_skill/outputs/docs_after/adr/index.md +3 -0
- package/lib/assets/.claude/skills/apply-okf-workspace/iteration-1/eval-2-verify-reviewed-doc/with_skill/outputs/docs_after/design/data-model.md +14 -0
- package/lib/assets/.claude/skills/apply-okf-workspace/iteration-1/eval-2-verify-reviewed-doc/with_skill/outputs/docs_after/design/index.md +3 -0
- package/lib/assets/.claude/skills/apply-okf-workspace/iteration-1/eval-2-verify-reviewed-doc/with_skill/outputs/docs_after/index.md +10 -0
- package/lib/assets/.claude/skills/apply-okf-workspace/iteration-1/eval-2-verify-reviewed-doc/with_skill/outputs/docs_after/log.md +7 -0
- package/lib/assets/.claude/skills/apply-okf-workspace/iteration-1/eval-2-verify-reviewed-doc/with_skill/outputs/docs_after/operation/deploy-old.md +12 -0
- package/lib/assets/.claude/skills/apply-okf-workspace/iteration-1/eval-2-verify-reviewed-doc/with_skill/outputs/docs_after/operation/deploy.md +12 -0
- package/lib/assets/.claude/skills/apply-okf-workspace/iteration-1/eval-2-verify-reviewed-doc/with_skill/outputs/docs_after/operation/index.md +4 -0
- package/lib/assets/.claude/skills/apply-okf-workspace/iteration-1/eval-2-verify-reviewed-doc/with_skill/outputs/docs_after/reference/OKF/345/260/216/345/205/245/343/202/254/343/202/244/343/203/211_V0.2.md +965 -0
- package/lib/assets/.claude/skills/apply-okf-workspace/iteration-1/eval-2-verify-reviewed-doc/with_skill/outputs/report.md +61 -0
- package/lib/assets/.claude/skills/apply-okf-workspace/iteration-1/eval-2-verify-reviewed-doc/without_skill/grading.json +34 -0
- package/lib/assets/.claude/skills/apply-okf-workspace/iteration-1/eval-2-verify-reviewed-doc/without_skill/outputs/docs_after/adr/001-db.md +12 -0
- package/lib/assets/.claude/skills/apply-okf-workspace/iteration-1/eval-2-verify-reviewed-doc/without_skill/outputs/docs_after/adr/002-cache-strategy.md +11 -0
- package/lib/assets/.claude/skills/apply-okf-workspace/iteration-1/eval-2-verify-reviewed-doc/without_skill/outputs/docs_after/adr/index.md +3 -0
- package/lib/assets/.claude/skills/apply-okf-workspace/iteration-1/eval-2-verify-reviewed-doc/without_skill/outputs/docs_after/design/data-model.md +13 -0
- package/lib/assets/.claude/skills/apply-okf-workspace/iteration-1/eval-2-verify-reviewed-doc/without_skill/outputs/docs_after/design/index.md +3 -0
- package/lib/assets/.claude/skills/apply-okf-workspace/iteration-1/eval-2-verify-reviewed-doc/without_skill/outputs/docs_after/index.md +10 -0
- package/lib/assets/.claude/skills/apply-okf-workspace/iteration-1/eval-2-verify-reviewed-doc/without_skill/outputs/docs_after/log.md +7 -0
- package/lib/assets/.claude/skills/apply-okf-workspace/iteration-1/eval-2-verify-reviewed-doc/without_skill/outputs/docs_after/operation/deploy-old.md +12 -0
- package/lib/assets/.claude/skills/apply-okf-workspace/iteration-1/eval-2-verify-reviewed-doc/without_skill/outputs/docs_after/operation/deploy.md +12 -0
- package/lib/assets/.claude/skills/apply-okf-workspace/iteration-1/eval-2-verify-reviewed-doc/without_skill/outputs/docs_after/operation/index.md +4 -0
- package/lib/assets/.claude/skills/apply-okf-workspace/iteration-1/eval-2-verify-reviewed-doc/without_skill/outputs/docs_after/reference/OKF/345/260/216/345/205/245/343/202/254/343/202/244/343/203/211_V0.2.md +965 -0
- package/lib/assets/.claude/skills/apply-okf-workspace/iteration-1/eval-2-verify-reviewed-doc/without_skill/outputs/report.md +18 -0
- package/lib/assets/.claude/skills/apply-okf-workspace/iteration-1/eval-3-deprecate-replaced-doc/eval_metadata.json +13 -0
- package/lib/assets/.claude/skills/apply-okf-workspace/iteration-1/eval-3-deprecate-replaced-doc/with_skill/grading.json +34 -0
- package/lib/assets/.claude/skills/apply-okf-workspace/iteration-1/eval-3-deprecate-replaced-doc/with_skill/outputs/docs_after/adr/001-db.md +12 -0
- package/lib/assets/.claude/skills/apply-okf-workspace/iteration-1/eval-3-deprecate-replaced-doc/with_skill/outputs/docs_after/adr/002-cache-strategy.md +11 -0
- package/lib/assets/.claude/skills/apply-okf-workspace/iteration-1/eval-3-deprecate-replaced-doc/with_skill/outputs/docs_after/adr/index.md +3 -0
- package/lib/assets/.claude/skills/apply-okf-workspace/iteration-1/eval-3-deprecate-replaced-doc/with_skill/outputs/docs_after/design/data-model.md +12 -0
- package/lib/assets/.claude/skills/apply-okf-workspace/iteration-1/eval-3-deprecate-replaced-doc/with_skill/outputs/docs_after/design/index.md +3 -0
- package/lib/assets/.claude/skills/apply-okf-workspace/iteration-1/eval-3-deprecate-replaced-doc/with_skill/outputs/docs_after/index.md +10 -0
- package/lib/assets/.claude/skills/apply-okf-workspace/iteration-1/eval-3-deprecate-replaced-doc/with_skill/outputs/docs_after/log.md +7 -0
- package/lib/assets/.claude/skills/apply-okf-workspace/iteration-1/eval-3-deprecate-replaced-doc/with_skill/outputs/docs_after/operation/deploy-old.md +13 -0
- package/lib/assets/.claude/skills/apply-okf-workspace/iteration-1/eval-3-deprecate-replaced-doc/with_skill/outputs/docs_after/operation/deploy.md +12 -0
- package/lib/assets/.claude/skills/apply-okf-workspace/iteration-1/eval-3-deprecate-replaced-doc/with_skill/outputs/docs_after/operation/index.md +7 -0
- package/lib/assets/.claude/skills/apply-okf-workspace/iteration-1/eval-3-deprecate-replaced-doc/with_skill/outputs/docs_after/reference/OKF/345/260/216/345/205/245/343/202/254/343/202/244/343/203/211_V0.2.md +965 -0
- package/lib/assets/.claude/skills/apply-okf-workspace/iteration-1/eval-3-deprecate-replaced-doc/with_skill/outputs/report.md +83 -0
- package/lib/assets/.claude/skills/apply-okf-workspace/iteration-1/eval-3-deprecate-replaced-doc/without_skill/grading.json +34 -0
- package/lib/assets/.claude/skills/apply-okf-workspace/iteration-1/eval-3-deprecate-replaced-doc/without_skill/outputs/docs_after/adr/001-db.md +12 -0
- package/lib/assets/.claude/skills/apply-okf-workspace/iteration-1/eval-3-deprecate-replaced-doc/without_skill/outputs/docs_after/adr/002-cache-strategy.md +11 -0
- package/lib/assets/.claude/skills/apply-okf-workspace/iteration-1/eval-3-deprecate-replaced-doc/without_skill/outputs/docs_after/adr/index.md +3 -0
- package/lib/assets/.claude/skills/apply-okf-workspace/iteration-1/eval-3-deprecate-replaced-doc/without_skill/outputs/docs_after/design/data-model.md +12 -0
- package/lib/assets/.claude/skills/apply-okf-workspace/iteration-1/eval-3-deprecate-replaced-doc/without_skill/outputs/docs_after/design/index.md +3 -0
- package/lib/assets/.claude/skills/apply-okf-workspace/iteration-1/eval-3-deprecate-replaced-doc/without_skill/outputs/docs_after/index.md +10 -0
- package/lib/assets/.claude/skills/apply-okf-workspace/iteration-1/eval-3-deprecate-replaced-doc/without_skill/outputs/docs_after/log.md +7 -0
- package/lib/assets/.claude/skills/apply-okf-workspace/iteration-1/eval-3-deprecate-replaced-doc/without_skill/outputs/docs_after/operation/deploy-old.md +14 -0
- package/lib/assets/.claude/skills/apply-okf-workspace/iteration-1/eval-3-deprecate-replaced-doc/without_skill/outputs/docs_after/operation/deploy.md +12 -0
- package/lib/assets/.claude/skills/apply-okf-workspace/iteration-1/eval-3-deprecate-replaced-doc/without_skill/outputs/docs_after/operation/index.md +4 -0
- package/lib/assets/.claude/skills/apply-okf-workspace/iteration-1/eval-3-deprecate-replaced-doc/without_skill/outputs/docs_after/reference/OKF/345/260/216/345/205/245/343/202/254/343/202/244/343/203/211_V0.2.md +965 -0
- package/lib/assets/.claude/skills/apply-okf-workspace/iteration-1/eval-3-deprecate-replaced-doc/without_skill/outputs/report.md +15 -0
- package/lib/assets/.claude/skills/apply-okf-workspace/iteration-1/review.html +1325 -0
- package/lib/assets/.claude/skills/closing-iteration/SKILL.md +176 -176
- package/lib/assets/.claude/skills/creating-adr/SKILL.md +117 -117
- package/lib/assets/.claude/skills/creating-development-strategy/SKILL.md +187 -151
- package/lib/assets/.claude/skills/creating-iteration-report/SKILL.md +210 -210
- package/lib/assets/.claude/skills/creating-journal/SKILL.md +140 -140
- package/lib/assets/.claude/skills/creating-manual/SKILL.md +199 -199
- package/lib/assets/.claude/skills/creating-release-report/SKILL.md +161 -161
- package/lib/assets/.claude/skills/creating-slides/SKILL.md +86 -86
- package/lib/assets/.claude/skills/creating-slides/agents/openai.yaml +4 -4
- package/lib/assets/.claude/skills/creating-slides/references/manga-css.md +45 -45
- package/lib/assets/.claude/skills/creating-slides/scripts/slide_tools.py +239 -239
- package/lib/assets/.claude/skills/developing-backend/SKILL.md +138 -100
- package/lib/assets/.claude/skills/developing-frontend/SKILL.md +131 -93
- package/lib/assets/.claude/skills/developing-release/SKILL.md +120 -120
- package/lib/assets/.claude/skills/developing-review/SKILL.md +175 -175
- package/lib/assets/.claude/skills/developing-uiux-review/SKILL.md +207 -207
- package/lib/assets/.claude/skills/generating-bmc/SKILL.md +123 -123
- package/lib/assets/.claude/skills/generating-slides/SKILL.md +94 -94
- package/lib/assets/.claude/skills/git-commit/SKILL.md +81 -81
- package/lib/assets/.claude/skills/killing-processes/SKILL.md +44 -44
- package/lib/assets/.claude/skills/migrating-ai-dlc/evals/evals.json +59 -59
- package/lib/assets/.claude/skills/migrating-okf-workspace/iteration-1/benchmark.json +20 -0
- package/lib/assets/.claude/skills/migrating-okf-workspace/iteration-1/benchmark.md +13 -0
- package/lib/assets/.claude/skills/migrating-okf-workspace/iteration-1/eval-1-migrate-docs/eval_metadata.json +15 -0
- package/lib/assets/.claude/skills/migrating-okf-workspace/iteration-1/eval-1-migrate-docs/with_skill/grading.json +44 -0
- package/lib/assets/.claude/skills/migrating-okf-workspace/iteration-1/eval-1-migrate-docs/with_skill/outputs/docs_after/adr/index.md +10 -0
- package/lib/assets/.claude/skills/migrating-okf-workspace/iteration-1/eval-1-migrate-docs/with_skill/outputs/docs_after/index.md +15 -0
- package/lib/assets/.claude/skills/migrating-okf-workspace/iteration-1/eval-1-migrate-docs/with_skill/outputs/docs_after/log.md +5 -0
- package/lib/assets/.claude/skills/migrating-okf-workspace/iteration-1/eval-1-migrate-docs/with_skill/outputs/docs_after/reference/OKF/345/260/216/345/205/245/343/202/254/343/202/244/343/203/211_V0.2.md +966 -0
- package/lib/assets/.claude/skills/migrating-okf-workspace/iteration-1/eval-1-migrate-docs/with_skill/outputs/docs_after/reference/index.md +6 -0
- package/lib/assets/.claude/skills/migrating-okf-workspace/iteration-1/eval-1-migrate-docs/with_skill/outputs/docs_after/reference//343/202/210/343/201/204/343/202/275/343/203/225/343/203/210/343/202/246/343/202/247/343/202/242/343/201/250/343/201/257.md +261 -0
- package/lib/assets/.claude/skills/migrating-okf-workspace/iteration-1/eval-1-migrate-docs/with_skill/outputs/docs_after/reference//343/203/252/343/203/252/343/203/274/343/202/271/343/202/254/343/202/244/343/203/211.md +480 -0
- package/lib/assets/.claude/skills/migrating-okf-workspace/iteration-1/eval-1-migrate-docs/with_skill/outputs/docs_after/reference//347/222/260/345/242/203/345/244/211/346/225/260/347/256/241/347/220/206/343/202/254/343/202/244/343/203/211.md +681 -0
- package/lib/assets/.claude/skills/migrating-okf-workspace/iteration-1/eval-1-migrate-docs/with_skill/outputs/report.md +85 -0
- package/lib/assets/.claude/skills/migrating-okf-workspace/iteration-1/eval-1-migrate-docs/without_skill/grading.json +44 -0
- package/lib/assets/.claude/skills/migrating-okf-workspace/iteration-1/eval-1-migrate-docs/without_skill/outputs/docs_after/adr/index.md +8 -0
- package/lib/assets/.claude/skills/migrating-okf-workspace/iteration-1/eval-1-migrate-docs/without_skill/outputs/docs_after/index.md +11 -0
- package/lib/assets/.claude/skills/migrating-okf-workspace/iteration-1/eval-1-migrate-docs/without_skill/outputs/docs_after/log.md +7 -0
- package/lib/assets/.claude/skills/migrating-okf-workspace/iteration-1/eval-1-migrate-docs/without_skill/outputs/docs_after/reference/OKF/345/260/216/345/205/245/343/202/254/343/202/244/343/203/211_V0.2.md +964 -0
- package/lib/assets/.claude/skills/migrating-okf-workspace/iteration-1/eval-1-migrate-docs/without_skill/outputs/docs_after/reference/index.md +9 -0
- package/lib/assets/.claude/skills/migrating-okf-workspace/iteration-1/eval-1-migrate-docs/without_skill/outputs/docs_after/reference//343/202/210/343/201/204/343/202/275/343/203/225/343/203/210/343/202/246/343/202/247/343/202/242/343/201/250/343/201/257.md +250 -0
- package/lib/assets/.claude/skills/migrating-okf-workspace/iteration-1/eval-1-migrate-docs/without_skill/outputs/docs_after/reference//343/203/252/343/203/252/343/203/274/343/202/271/343/202/254/343/202/244/343/203/211.md +469 -0
- package/lib/assets/.claude/skills/migrating-okf-workspace/iteration-1/eval-1-migrate-docs/without_skill/outputs/docs_after/reference//347/222/260/345/242/203/345/244/211/346/225/260/347/256/241/347/220/206/343/202/254/343/202/244/343/203/211.md +677 -0
- package/lib/assets/.claude/skills/migrating-okf-workspace/iteration-1/eval-1-migrate-docs/without_skill/outputs/report.md +49 -0
- package/lib/assets/.claude/skills/migrating-okf-workspace/iteration-1/eval-2-upgrade-v01-to-v02/eval_metadata.json +13 -0
- package/lib/assets/.claude/skills/migrating-okf-workspace/iteration-1/eval-2-upgrade-v01-to-v02/with_skill/grading.json +34 -0
- package/lib/assets/.claude/skills/migrating-okf-workspace/iteration-1/eval-2-upgrade-v01-to-v02/with_skill/outputs/knowledge_after/index.md +7 -0
- package/lib/assets/.claude/skills/migrating-okf-workspace/iteration-1/eval-2-upgrade-v01-to-v02/with_skill/outputs/knowledge_after/log.md +7 -0
- package/lib/assets/.claude/skills/migrating-okf-workspace/iteration-1/eval-2-upgrade-v01-to-v02/with_skill/outputs/knowledge_after/metrics/churn.md +9 -0
- package/lib/assets/.claude/skills/migrating-okf-workspace/iteration-1/eval-2-upgrade-v01-to-v02/with_skill/outputs/knowledge_after/metrics/income-statement.md +15 -0
- package/lib/assets/.claude/skills/migrating-okf-workspace/iteration-1/eval-2-upgrade-v01-to-v02/with_skill/outputs/report.md +147 -0
- package/lib/assets/.claude/skills/migrating-okf-workspace/iteration-1/review.html +1325 -0
- package/lib/assets/.claude/skills/opening-iteration/SKILL.md +124 -124
- package/lib/assets/.claude/skills/operating-backup/SKILL.md +59 -59
- package/lib/assets/.claude/skills/operating-cicd/SKILL.md +54 -54
- package/lib/assets/.claude/skills/operating-deploy/SKILL.md +67 -67
- package/lib/assets/.claude/skills/operating-docs/SKILL.md +219 -219
- package/lib/assets/.claude/skills/operating-provision/SKILL.md +77 -77
- package/lib/assets/.claude/skills/operating-qt/SKILL.md +147 -147
- package/lib/assets/.claude/skills/operating-review/SKILL.md +171 -171
- package/lib/assets/.claude/skills/operating-script/SKILL.md +145 -145
- package/lib/assets/.claude/skills/operating-setup/SKILL.md +63 -63
- package/lib/assets/.claude/skills/orchestrating-analysis/SKILL.md +110 -110
- package/lib/assets/.claude/skills/orchestrating-development/SKILL.md +208 -172
- package/lib/assets/.claude/skills/orchestrating-operation/SKILL.md +161 -161
- package/lib/assets/.claude/skills/orchestrating-project/SKILL.md +149 -149
- package/lib/assets/.claude/skills/planning-releases/SKILL.md +121 -121
- package/lib/assets/.claude/skills/practicing-getting-start-tdd/SKILL.md +262 -262
- package/lib/assets/.claude/skills/syncing-github-project/SKILL.md +151 -151
- package/lib/assets/.claude/skills/tracking-progress/SKILL.md +91 -91
- package/lib/assets/.claude/skills/validating-design/SKILL.md +130 -130
- package/lib/assets/.claude/skills/validating-iteration-plan/SKILL.md +238 -238
- package/lib/assets/.claude/skills/validating-operating-setup/SKILL.md +118 -118
- package/lib/assets/.devcontainer/devcontainer.json +37 -37
- package/lib/assets/.env.example +32 -32
- package/lib/assets/.gitattributes +4 -4
- package/lib/assets/.github/workflows/docker-publish.yml +77 -77
- package/lib/assets/.github/workflows/mkdocs.yml +39 -39
- package/lib/assets/AGENTS.md +102 -102
- package/lib/assets/README.md +304 -304
- package/lib/assets/docker-compose.yml +33 -33
- package/lib/assets/docs/adr/index.md +10 -10
- package/lib/assets/docs/article/index.md +1 -0
- package/lib/assets/docs/assets/css/extra.css +29 -29
- package/lib/assets/docs/assets/js/extra.js +48 -48
- package/lib/assets/docs/assets/js/mathjax.js +27 -27
- package/lib/assets/docs/design/index.md +44 -44
- package/lib/assets/docs/development/index.md +39 -39
- package/lib/assets/docs/index.md +37 -37
- package/lib/assets/docs/log.md +28 -28
- package/lib/assets/docs/operation/index.md +41 -41
- package/lib/assets/docs/reference/BDD/345/260/216/345/205/245/343/202/254/343/202/244/343/203/211.md +766 -766
- package/lib/assets/docs/reference/CodexCLIMCP/343/202/242/343/203/227/343/203/252/343/202/261/343/203/274/343/202/267/343/203/247/343/203/263/351/226/213/347/231/272/343/203/225/343/203/255/343/203/274.md +555 -555
- package/lib/assets/docs/reference/CodexCLIMCP/343/202/265/343/203/274/343/203/220/343/203/274/350/250/255/345/256/232/346/211/213/351/240/206.md +351 -351
- package/lib/assets/docs/reference/Java/343/202/242/343/203/227/343/203/252/343/202/261/343/203/274/343/202/267/343/203/247/343/203/263/347/222/260/345/242/203/346/247/213/347/257/211/343/202/254/343/202/244/343/203/211.md +592 -592
- package/lib/assets/docs/reference/LivingDocumentation/345/260/216/345/205/245/343/202/254/343/202/244/343/203/211.md +400 -0
- package/lib/assets/docs/reference/OKF/345/260/216/345/205/245/343/202/254/343/202/244/343/203/211_V0.2.md +965 -965
- package/lib/assets/docs/reference/SonarQube/343/203/255/343/203/274/343/202/253/343/203/253/347/222/260/345/242/203/343/202/273/343/203/203/343/203/210/343/202/242/343/203/203/343/203/227/346/211/213/351/240/206/346/233/270.md +652 -652
- package/lib/assets/docs/reference/TypeScript/343/202/242/343/203/227/343/203/252/343/202/261/343/203/274/343/202/267/343/203/247/343/203/263/347/222/260/345/242/203/346/247/213/347/257/211/343/202/254/343/202/244/343/203/211.md +476 -476
- package/lib/assets/docs/reference/UI/350/250/255/350/250/210/343/202/254/343/202/244/343/203/211.md +460 -460
- package/lib/assets/docs/reference/Vim/346/223/215/344/275/234/343/203/236/343/203/213/343/203/245/343/202/242/343/203/253.md +177 -177
- package/lib/assets/docs/reference/images/Ansoff.drawio.svg +3 -3
- package/lib/assets/docs/reference/images/BMC.drawio.svg +3 -3
- package/lib/assets/docs/reference/images/BrandBasicStrategy.drawio.svg +3 -3
- package/lib/assets/docs/reference/images/BrandCategorization.drawio.svg +3 -3
- package/lib/assets/docs/reference/images/BrandRecurutementStrategy.drawio.svg +3 -3
- package/lib/assets/docs/reference/images/BrandValue.drawio.svg +3 -3
- package/lib/assets/docs/reference/images/BusinessActivitiy.svg +3 -3
- package/lib/assets/docs/reference/images/HRM.drawio.svg +3 -3
- package/lib/assets/docs/reference/images/MarketingStructure.drawio.svg +3 -3
- package/lib/assets/docs/reference/images/OrganizationElemnts.svg +3 -3
- package/lib/assets/docs/reference/images/PPM.drawio.svg +3 -3
- package/lib/assets/docs/reference/images/PositioningMap.drawio.svg +3 -3
- package/lib/assets/docs/reference/images/ProductLayer.drawio.svg +3 -3
- package/lib/assets/docs/reference/images/ProductMix.drawio.svg +3 -3
- package/lib/assets/docs/reference/images/SWOT.drawio.svg +3 -3
- package/lib/assets/docs/reference/images/TargetMarket.drawio.svg +3 -3
- package/lib/assets/docs/reference/images/ThreeGenericStrategies.drawio.svg +3 -3
- package/lib/assets/docs/reference/images/VRIO.drawio.svg +3 -3
- package/lib/assets/docs/reference/images/ValueChain.drawio.svg +3 -3
- package/lib/assets/docs/reference/index.md +66 -62
- package/lib/assets/docs/reference//343/202/210/343/201/204/343/202/275/343/203/225/343/203/210/343/202/246/343/202/247/343/202/242/343/201/250/343/201/257.md +250 -250
- package/lib/assets/docs/reference//343/202/242/343/203/216/343/203/206/343/203/274/343/202/267/343/203/247/343/203/263/345/260/216/345/205/245/343/202/254/343/202/244/343/203/211.md +268 -0
- package/lib/assets/docs/reference//343/202/242/343/203/274/343/202/255/343/203/206/343/202/257/343/203/201/343/203/243/350/250/255/350/250/210/343/202/254/343/202/244/343/203/211.md +2226 -2226
- package/lib/assets/docs/reference//343/202/244/343/203/263/343/203/225/343/203/251/350/250/255/350/250/210/343/202/254/343/202/244/343/203/211.md +1888 -1888
- package/lib/assets/docs/reference//343/202/250/343/202/257/343/202/271/343/203/210/343/203/252/343/203/274/343/203/240/343/203/227/343/203/255/343/202/260/343/203/251/343/203/237/343/203/263/343/202/260.md +549 -549
- package/lib/assets/docs/reference//343/202/254/343/202/244/343/203/211/343/203/204/343/202/242/343/203/274/343/203/273/343/202/265/343/202/244/343/203/210/343/202/267/343/203/274/343/202/244/343/203/263/343/202/260/345/260/216/345/205/245/343/202/254/343/202/244/343/203/211.md +192 -0
- package/lib/assets/docs/reference//343/202/263/343/203/274/343/203/207/343/202/243/343/203/263/343/202/260/343/201/250/343/203/206/343/202/271/343/203/210/343/202/254/343/202/244/343/203/211.md +715 -715
- package/lib/assets/docs/reference//343/203/200/343/202/244/343/203/212/343/203/237/343/203/203/343/202/257/343/202/255/343/203/245/343/203/254/343/203/274/343/202/267/343/203/247/343/203/263/345/260/216/345/205/245/343/202/254/343/202/244/343/203/211.md +191 -0
- package/lib/assets/docs/reference//343/203/206/343/202/271/343/203/210/346/210/246/347/225/245/343/202/254/343/202/244/343/203/211.md +1323 -1323
- package/lib/assets/docs/reference//343/203/207/343/203/274/343/202/277/343/203/242/343/203/207/343/203/253/350/250/255/350/250/210/343/202/254/343/202/244/343/203/211.md +321 -321
- package/lib/assets/docs/reference//343/203/211/343/203/241/343/202/244/343/203/263/343/203/242/343/203/207/343/203/253/350/250/255/350/250/210/343/202/254/343/202/244/343/203/211.md +609 -609
- package/lib/assets/docs/reference//343/203/223/343/202/270/343/203/215/343/202/271/343/202/242/343/203/274/343/202/255/343/203/206/343/202/257/343/203/201/343/203/243/345/210/206/346/236/220/343/202/254/343/202/244/343/203/211.md +537 -537
- package/lib/assets/docs/reference//343/203/246/343/203/274/343/202/271/343/202/261/343/203/274/343/202/271/344/275/234/346/210/220/343/202/254/343/202/244/343/203/211.md +699 -699
- package/lib/assets/docs/reference//343/203/252/343/203/252/343/203/274/343/202/271/343/202/254/343/202/244/343/203/211.md +470 -470
- package/lib/assets/docs/reference//343/203/252/343/203/252/343/203/274/343/202/271/343/203/273/343/202/244/343/203/206/343/203/254/343/203/274/343/202/267/343/203/247/343/203/263/350/250/210/347/224/273/343/202/254/343/202/244/343/203/211.md +580 -580
- package/lib/assets/docs/reference//343/203/255/343/202/270/343/202/253/343/203/253/343/202/267/343/203/263/343/202/255/343/203/263/343/202/260.md +1376 -1376
- package/lib/assets/docs/reference//344/274/201/346/245/255/347/265/214/345/226/266/350/253/226.md +2647 -2647
- package/lib/assets/docs/reference//347/222/260/345/242/203/345/244/211/346/225/260/347/256/241/347/220/206/343/202/254/343/202/244/343/203/211.md +675 -675
- package/lib/assets/docs/reference//347/265/214/345/226/266/346/210/246/347/225/245/345/210/206/346/236/220/343/202/254/343/202/244/343/203/211.md +575 -575
- package/lib/assets/docs/reference//350/246/201/344/273/266/345/256/232/347/276/251/343/202/254/343/202/244/343/203/211.md +1258 -1258
- package/lib/assets/docs/reference//350/250/200/350/252/236/345/210/245/351/226/213/347/231/272/343/202/254/343/202/244/343/203/211.md +527 -527
- package/lib/assets/docs/reference//351/201/213/345/226/266/347/256/241/347/220/206.md +1492 -1492
- package/lib/assets/docs/reference//351/201/213/347/224/250/343/202/271/343/202/257/343/203/252/343/203/227/343/203/210/344/275/234/346/210/220/343/202/254/343/202/244/343/203/211.md +430 -430
- package/lib/assets/docs/reference//351/201/213/347/224/250/350/246/201/344/273/266/345/256/232/347/276/251/343/202/254/343/202/244/343/203/211.md +402 -402
- package/lib/assets/docs/reference//351/226/213/347/231/272/343/202/254/343/202/244/343/203/211.md +314 -314
- package/lib/assets/docs/reference//351/235/236/346/251/237/350/203/275/350/246/201/344/273/266/345/256/232/347/276/251/343/202/254/343/202/244/343/203/211.md +1246 -1246
- package/lib/assets/docs/requirements/index.md +17 -17
- package/lib/assets/docs/review/index.md +5 -5
- package/lib/assets/docs/strategy/index.md +17 -17
- package/lib/assets/docs/template/ADR.md +39 -39
- package/lib/assets/docs/template/AWS/343/202/271/343/203/206/343/203/274/343/202/270/343/203/263/343/202/260/347/222/260/345/242/203/343/202/273/343/203/203/343/203/210/343/202/242/343/203/203/343/203/227/346/211/213/351/240/206/346/233/270.md +1375 -1375
- package/lib/assets/docs/template/AWS/343/203/227/343/203/255/343/203/200/343/202/257/343/202/267/343/203/247/343/203/263/347/222/260/345/242/203/343/202/273/343/203/203/343/203/210/343/202/242/343/203/203/343/203/227/346/211/213/351/240/206/346/233/270.md +643 -643
- package/lib/assets/docs/template/README.md +59 -59
- package/lib/assets/docs/template/index.md +24 -24
- package/lib/assets/docs/template//343/201/276/343/201/232/343/201/223/343/202/214/343/202/222/350/252/255/343/202/202/343/201/206/343/203/252/343/202/271/343/203/210.md +21 -21
- package/lib/assets/docs/template//343/202/242/343/203/227/343/203/252/343/202/261/343/203/274/343/202/267/343/203/247/343/203/263/351/226/213/347/231/272/347/222/260/345/242/203/343/202/273/343/203/203/343/203/210/343/202/242/343/203/203/343/203/227/346/211/213/351/240/206/346/233/270.md +556 -556
- package/lib/assets/docs/template//343/202/244/343/203/206/343/203/254/343/203/274/343/202/267/343/203/247/343/203/263/345/256/214/344/272/206/345/240/261/345/221/212/346/233/270.md +68 -68
- package/lib/assets/docs/template//343/202/244/343/203/206/343/203/254/343/203/274/343/202/267/343/203/247/343/203/263/350/250/210/347/224/273.md +336 -336
- package/lib/assets/docs/template//343/202/244/343/203/263/343/202/273/343/203/227/343/202/267/343/203/247/343/203/263/343/203/207/343/203/203/343/202/255.md +22 -22
- package/lib/assets/docs/template//343/203/223/343/202/270/343/203/215/343/202/271/343/202/242/343/203/274/343/202/255/343/203/206/343/202/257/343/203/201/343/203/243.md +388 -388
- package/lib/assets/docs/template//343/203/252/343/203/252/343/203/274/343/202/271/345/256/214/344/272/206/345/240/261/345/221/212/346/233/270.md +284 -284
- package/lib/assets/docs/template//343/203/252/343/203/252/343/203/274/343/202/271/350/250/210/347/224/273.md +289 -289
- package/lib/assets/docs/template//344/272/213/344/276/213/345/210/206/346/236/220.md +522 -522
- package/lib/assets/docs/template//344/274/201/346/245/255/345/210/206/346/236/220.md +582 -582
- package/lib/assets/docs/template//345/256/214/345/205/250/345/275/242/345/274/217/343/201/256/343/203/246/343/203/274/343/202/271/343/202/261/343/203/274/343/202/271.md +69 -69
- package/lib/assets/docs/template//350/246/201/344/273/266/345/256/232/347/276/251.md +669 -669
- package/lib/assets/docs/template//350/250/255/350/250/210.md +183 -183
- package/lib/assets/docs/template//351/226/213/347/231/272/347/222/260/345/242/203/343/202/273/343/203/203/343/203/210/343/202/242/343/203/203/343/203/227/346/211/213/351/240/206/346/233/270.md +697 -697
- package/lib/assets/gulpfile.js +29 -29
- package/lib/assets/mkdocs.yml +151 -147
- package/lib/assets/ops/docker/sonarqube-local/docker-compose.yml +57 -57
- package/lib/assets/ops/scripts/journal.js +180 -180
- package/lib/assets/ops/scripts/mkdocs.js +82 -82
- package/lib/assets/ops/scripts/release.js +431 -431
- package/lib/assets/ops/scripts/sonar_local.js +726 -726
- package/lib/assets/ops/scripts/ssh.js +190 -190
- package/lib/assets/ops/scripts/vault.js +299 -299
- package/lib/assets/package-lock.json +1673 -1673
- package/lib/assets/package.json +45 -45
- package/lib/gulpfile.js +37 -37
- package/package.json +41 -41
|
@@ -0,0 +1,1325 @@
|
|
|
1
|
+
<!DOCTYPE html>
|
|
2
|
+
<html lang="en">
|
|
3
|
+
<head>
|
|
4
|
+
<meta charset="UTF-8">
|
|
5
|
+
<meta name="viewport" content="width=device-width, initial-scale=1.0">
|
|
6
|
+
<title>Eval Review</title>
|
|
7
|
+
<link rel="preconnect" href="https://fonts.googleapis.com">
|
|
8
|
+
<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin>
|
|
9
|
+
<link href="https://fonts.googleapis.com/css2?family=Poppins:wght@500;600&family=Lora:wght@400;500&display=swap" rel="stylesheet">
|
|
10
|
+
<script src="https://cdn.sheetjs.com/xlsx-0.20.3/package/dist/xlsx.full.min.js" integrity="sha384-EnyY0/GSHQGSxSgMwaIPzSESbqoOLSexfnSMN2AP+39Ckmn92stwABZynq1JyzdT" crossorigin="anonymous"></script>
|
|
11
|
+
<style>
|
|
12
|
+
:root {
|
|
13
|
+
--bg: #faf9f5;
|
|
14
|
+
--surface: #ffffff;
|
|
15
|
+
--border: #e8e6dc;
|
|
16
|
+
--text: #141413;
|
|
17
|
+
--text-muted: #b0aea5;
|
|
18
|
+
--accent: #d97757;
|
|
19
|
+
--accent-hover: #c4613f;
|
|
20
|
+
--green: #788c5d;
|
|
21
|
+
--green-bg: #eef2e8;
|
|
22
|
+
--red: #c44;
|
|
23
|
+
--red-bg: #fceaea;
|
|
24
|
+
--header-bg: #141413;
|
|
25
|
+
--header-text: #faf9f5;
|
|
26
|
+
--radius: 6px;
|
|
27
|
+
}
|
|
28
|
+
|
|
29
|
+
* { box-sizing: border-box; margin: 0; padding: 0; }
|
|
30
|
+
|
|
31
|
+
body {
|
|
32
|
+
font-family: 'Lora', Georgia, serif;
|
|
33
|
+
background: var(--bg);
|
|
34
|
+
color: var(--text);
|
|
35
|
+
height: 100vh;
|
|
36
|
+
display: flex;
|
|
37
|
+
flex-direction: column;
|
|
38
|
+
}
|
|
39
|
+
|
|
40
|
+
/* ---- Header ---- */
|
|
41
|
+
.header {
|
|
42
|
+
background: var(--header-bg);
|
|
43
|
+
color: var(--header-text);
|
|
44
|
+
padding: 1rem 2rem;
|
|
45
|
+
display: flex;
|
|
46
|
+
justify-content: space-between;
|
|
47
|
+
align-items: center;
|
|
48
|
+
flex-shrink: 0;
|
|
49
|
+
}
|
|
50
|
+
.header h1 {
|
|
51
|
+
font-family: 'Poppins', sans-serif;
|
|
52
|
+
font-size: 1.25rem;
|
|
53
|
+
font-weight: 600;
|
|
54
|
+
}
|
|
55
|
+
.header .instructions {
|
|
56
|
+
font-size: 0.8rem;
|
|
57
|
+
opacity: 0.7;
|
|
58
|
+
margin-top: 0.25rem;
|
|
59
|
+
}
|
|
60
|
+
.header .progress {
|
|
61
|
+
font-size: 0.875rem;
|
|
62
|
+
opacity: 0.8;
|
|
63
|
+
text-align: right;
|
|
64
|
+
}
|
|
65
|
+
|
|
66
|
+
/* ---- Main content ---- */
|
|
67
|
+
.main {
|
|
68
|
+
flex: 1;
|
|
69
|
+
overflow-y: auto;
|
|
70
|
+
padding: 1.5rem 2rem;
|
|
71
|
+
display: flex;
|
|
72
|
+
flex-direction: column;
|
|
73
|
+
gap: 1.25rem;
|
|
74
|
+
}
|
|
75
|
+
|
|
76
|
+
/* ---- Sections ---- */
|
|
77
|
+
.section {
|
|
78
|
+
background: var(--surface);
|
|
79
|
+
border: 1px solid var(--border);
|
|
80
|
+
border-radius: var(--radius);
|
|
81
|
+
flex-shrink: 0;
|
|
82
|
+
}
|
|
83
|
+
.section-header {
|
|
84
|
+
font-family: 'Poppins', sans-serif;
|
|
85
|
+
padding: 0.75rem 1rem;
|
|
86
|
+
font-size: 0.75rem;
|
|
87
|
+
font-weight: 500;
|
|
88
|
+
text-transform: uppercase;
|
|
89
|
+
letter-spacing: 0.05em;
|
|
90
|
+
color: var(--text-muted);
|
|
91
|
+
border-bottom: 1px solid var(--border);
|
|
92
|
+
background: var(--bg);
|
|
93
|
+
}
|
|
94
|
+
.section-body {
|
|
95
|
+
padding: 1rem;
|
|
96
|
+
}
|
|
97
|
+
|
|
98
|
+
/* ---- Config badge ---- */
|
|
99
|
+
.config-badge {
|
|
100
|
+
display: inline-block;
|
|
101
|
+
padding: 0.2rem 0.625rem;
|
|
102
|
+
border-radius: 9999px;
|
|
103
|
+
font-family: 'Poppins', sans-serif;
|
|
104
|
+
font-size: 0.6875rem;
|
|
105
|
+
font-weight: 600;
|
|
106
|
+
text-transform: uppercase;
|
|
107
|
+
letter-spacing: 0.03em;
|
|
108
|
+
margin-left: 0.75rem;
|
|
109
|
+
vertical-align: middle;
|
|
110
|
+
}
|
|
111
|
+
.config-badge.config-primary {
|
|
112
|
+
background: rgba(33, 150, 243, 0.12);
|
|
113
|
+
color: #1976d2;
|
|
114
|
+
}
|
|
115
|
+
.config-badge.config-baseline {
|
|
116
|
+
background: rgba(255, 193, 7, 0.15);
|
|
117
|
+
color: #f57f17;
|
|
118
|
+
}
|
|
119
|
+
|
|
120
|
+
/* ---- Prompt ---- */
|
|
121
|
+
.prompt-text {
|
|
122
|
+
white-space: pre-wrap;
|
|
123
|
+
font-size: 0.9375rem;
|
|
124
|
+
line-height: 1.6;
|
|
125
|
+
}
|
|
126
|
+
|
|
127
|
+
/* ---- Outputs ---- */
|
|
128
|
+
.output-file {
|
|
129
|
+
border: 1px solid var(--border);
|
|
130
|
+
border-radius: var(--radius);
|
|
131
|
+
overflow: hidden;
|
|
132
|
+
}
|
|
133
|
+
.output-file + .output-file {
|
|
134
|
+
margin-top: 1rem;
|
|
135
|
+
}
|
|
136
|
+
.output-file-header {
|
|
137
|
+
padding: 0.5rem 0.75rem;
|
|
138
|
+
font-size: 0.8rem;
|
|
139
|
+
font-weight: 600;
|
|
140
|
+
color: var(--text-muted);
|
|
141
|
+
background: var(--bg);
|
|
142
|
+
border-bottom: 1px solid var(--border);
|
|
143
|
+
font-family: 'SF Mono', SFMono-Regular, Consolas, 'Liberation Mono', Menlo, monospace;
|
|
144
|
+
display: flex;
|
|
145
|
+
justify-content: space-between;
|
|
146
|
+
align-items: center;
|
|
147
|
+
}
|
|
148
|
+
.output-file-header .dl-btn {
|
|
149
|
+
font-size: 0.7rem;
|
|
150
|
+
color: var(--accent);
|
|
151
|
+
text-decoration: none;
|
|
152
|
+
cursor: pointer;
|
|
153
|
+
font-family: -apple-system, BlinkMacSystemFont, 'Segoe UI', sans-serif;
|
|
154
|
+
font-weight: 500;
|
|
155
|
+
opacity: 0.8;
|
|
156
|
+
}
|
|
157
|
+
.output-file-header .dl-btn:hover {
|
|
158
|
+
opacity: 1;
|
|
159
|
+
text-decoration: underline;
|
|
160
|
+
}
|
|
161
|
+
.output-file-content {
|
|
162
|
+
padding: 0.75rem;
|
|
163
|
+
overflow-x: auto;
|
|
164
|
+
}
|
|
165
|
+
.output-file-content pre {
|
|
166
|
+
font-size: 0.8125rem;
|
|
167
|
+
line-height: 1.5;
|
|
168
|
+
white-space: pre-wrap;
|
|
169
|
+
word-break: break-word;
|
|
170
|
+
font-family: 'SF Mono', SFMono-Regular, Consolas, 'Liberation Mono', Menlo, monospace;
|
|
171
|
+
}
|
|
172
|
+
.output-file-content img {
|
|
173
|
+
max-width: 100%;
|
|
174
|
+
height: auto;
|
|
175
|
+
border-radius: 4px;
|
|
176
|
+
}
|
|
177
|
+
.output-file-content iframe {
|
|
178
|
+
width: 100%;
|
|
179
|
+
height: 600px;
|
|
180
|
+
border: none;
|
|
181
|
+
}
|
|
182
|
+
.output-file-content table {
|
|
183
|
+
border-collapse: collapse;
|
|
184
|
+
font-size: 0.8125rem;
|
|
185
|
+
width: 100%;
|
|
186
|
+
}
|
|
187
|
+
.output-file-content table td,
|
|
188
|
+
.output-file-content table th {
|
|
189
|
+
border: 1px solid var(--border);
|
|
190
|
+
padding: 0.375rem 0.5rem;
|
|
191
|
+
text-align: left;
|
|
192
|
+
}
|
|
193
|
+
.output-file-content table th {
|
|
194
|
+
background: var(--bg);
|
|
195
|
+
font-weight: 600;
|
|
196
|
+
}
|
|
197
|
+
.output-file-content .download-link {
|
|
198
|
+
display: inline-flex;
|
|
199
|
+
align-items: center;
|
|
200
|
+
gap: 0.5rem;
|
|
201
|
+
padding: 0.5rem 1rem;
|
|
202
|
+
background: var(--bg);
|
|
203
|
+
border: 1px solid var(--border);
|
|
204
|
+
border-radius: 4px;
|
|
205
|
+
color: var(--accent);
|
|
206
|
+
text-decoration: none;
|
|
207
|
+
font-size: 0.875rem;
|
|
208
|
+
cursor: pointer;
|
|
209
|
+
}
|
|
210
|
+
.output-file-content .download-link:hover {
|
|
211
|
+
background: var(--border);
|
|
212
|
+
}
|
|
213
|
+
.empty-state {
|
|
214
|
+
color: var(--text-muted);
|
|
215
|
+
font-style: italic;
|
|
216
|
+
padding: 2rem;
|
|
217
|
+
text-align: center;
|
|
218
|
+
}
|
|
219
|
+
|
|
220
|
+
/* ---- Feedback ---- */
|
|
221
|
+
.prev-feedback {
|
|
222
|
+
background: var(--bg);
|
|
223
|
+
border: 1px solid var(--border);
|
|
224
|
+
border-radius: 4px;
|
|
225
|
+
padding: 0.625rem 0.75rem;
|
|
226
|
+
margin-top: 0.75rem;
|
|
227
|
+
font-size: 0.8125rem;
|
|
228
|
+
color: var(--text-muted);
|
|
229
|
+
line-height: 1.5;
|
|
230
|
+
}
|
|
231
|
+
.prev-feedback-label {
|
|
232
|
+
font-size: 0.7rem;
|
|
233
|
+
font-weight: 600;
|
|
234
|
+
text-transform: uppercase;
|
|
235
|
+
letter-spacing: 0.04em;
|
|
236
|
+
margin-bottom: 0.25rem;
|
|
237
|
+
color: var(--text-muted);
|
|
238
|
+
}
|
|
239
|
+
.feedback-textarea {
|
|
240
|
+
width: 100%;
|
|
241
|
+
min-height: 100px;
|
|
242
|
+
padding: 0.75rem;
|
|
243
|
+
border: 1px solid var(--border);
|
|
244
|
+
border-radius: 4px;
|
|
245
|
+
font-family: inherit;
|
|
246
|
+
font-size: 0.9375rem;
|
|
247
|
+
line-height: 1.5;
|
|
248
|
+
resize: vertical;
|
|
249
|
+
color: var(--text);
|
|
250
|
+
}
|
|
251
|
+
.feedback-textarea:focus {
|
|
252
|
+
outline: none;
|
|
253
|
+
border-color: var(--accent);
|
|
254
|
+
box-shadow: 0 0 0 3px rgba(37, 99, 235, 0.1);
|
|
255
|
+
}
|
|
256
|
+
.feedback-status {
|
|
257
|
+
font-size: 0.75rem;
|
|
258
|
+
color: var(--text-muted);
|
|
259
|
+
margin-top: 0.5rem;
|
|
260
|
+
min-height: 1.1em;
|
|
261
|
+
}
|
|
262
|
+
|
|
263
|
+
/* ---- Grades (collapsible) ---- */
|
|
264
|
+
.grades-toggle {
|
|
265
|
+
display: flex;
|
|
266
|
+
align-items: center;
|
|
267
|
+
cursor: pointer;
|
|
268
|
+
user-select: none;
|
|
269
|
+
}
|
|
270
|
+
.grades-toggle:hover {
|
|
271
|
+
color: var(--accent);
|
|
272
|
+
}
|
|
273
|
+
.grades-toggle .arrow {
|
|
274
|
+
margin-right: 0.5rem;
|
|
275
|
+
transition: transform 0.15s;
|
|
276
|
+
font-size: 0.75rem;
|
|
277
|
+
}
|
|
278
|
+
.grades-toggle .arrow.open {
|
|
279
|
+
transform: rotate(90deg);
|
|
280
|
+
}
|
|
281
|
+
.grades-content {
|
|
282
|
+
display: none;
|
|
283
|
+
margin-top: 0.75rem;
|
|
284
|
+
}
|
|
285
|
+
.grades-content.open {
|
|
286
|
+
display: block;
|
|
287
|
+
}
|
|
288
|
+
.grades-summary {
|
|
289
|
+
font-size: 0.875rem;
|
|
290
|
+
margin-bottom: 0.75rem;
|
|
291
|
+
display: flex;
|
|
292
|
+
align-items: center;
|
|
293
|
+
gap: 0.5rem;
|
|
294
|
+
}
|
|
295
|
+
.grade-badge {
|
|
296
|
+
display: inline-block;
|
|
297
|
+
padding: 0.125rem 0.5rem;
|
|
298
|
+
border-radius: 9999px;
|
|
299
|
+
font-size: 0.75rem;
|
|
300
|
+
font-weight: 600;
|
|
301
|
+
}
|
|
302
|
+
.grade-pass { background: var(--green-bg); color: var(--green); }
|
|
303
|
+
.grade-fail { background: var(--red-bg); color: var(--red); }
|
|
304
|
+
.assertion-list {
|
|
305
|
+
list-style: none;
|
|
306
|
+
}
|
|
307
|
+
.assertion-item {
|
|
308
|
+
padding: 0.625rem 0;
|
|
309
|
+
border-bottom: 1px solid var(--border);
|
|
310
|
+
font-size: 0.8125rem;
|
|
311
|
+
}
|
|
312
|
+
.assertion-item:last-child { border-bottom: none; }
|
|
313
|
+
.assertion-status {
|
|
314
|
+
font-weight: 600;
|
|
315
|
+
margin-right: 0.5rem;
|
|
316
|
+
}
|
|
317
|
+
.assertion-status.pass { color: var(--green); }
|
|
318
|
+
.assertion-status.fail { color: var(--red); }
|
|
319
|
+
.assertion-evidence {
|
|
320
|
+
color: var(--text-muted);
|
|
321
|
+
font-size: 0.75rem;
|
|
322
|
+
margin-top: 0.25rem;
|
|
323
|
+
padding-left: 1.5rem;
|
|
324
|
+
}
|
|
325
|
+
|
|
326
|
+
/* ---- View tabs ---- */
|
|
327
|
+
.view-tabs {
|
|
328
|
+
display: flex;
|
|
329
|
+
gap: 0;
|
|
330
|
+
padding: 0 2rem;
|
|
331
|
+
background: var(--bg);
|
|
332
|
+
border-bottom: 1px solid var(--border);
|
|
333
|
+
flex-shrink: 0;
|
|
334
|
+
}
|
|
335
|
+
.view-tab {
|
|
336
|
+
font-family: 'Poppins', sans-serif;
|
|
337
|
+
padding: 0.625rem 1.25rem;
|
|
338
|
+
font-size: 0.8125rem;
|
|
339
|
+
font-weight: 500;
|
|
340
|
+
cursor: pointer;
|
|
341
|
+
border: none;
|
|
342
|
+
background: none;
|
|
343
|
+
color: var(--text-muted);
|
|
344
|
+
border-bottom: 2px solid transparent;
|
|
345
|
+
transition: all 0.15s;
|
|
346
|
+
}
|
|
347
|
+
.view-tab:hover { color: var(--text); }
|
|
348
|
+
.view-tab.active {
|
|
349
|
+
color: var(--accent);
|
|
350
|
+
border-bottom-color: var(--accent);
|
|
351
|
+
}
|
|
352
|
+
.view-panel { display: none; }
|
|
353
|
+
.view-panel.active { display: flex; flex-direction: column; flex: 1; overflow: hidden; }
|
|
354
|
+
|
|
355
|
+
/* ---- Benchmark view ---- */
|
|
356
|
+
.benchmark-view {
|
|
357
|
+
padding: 1.5rem 2rem;
|
|
358
|
+
overflow-y: auto;
|
|
359
|
+
flex: 1;
|
|
360
|
+
}
|
|
361
|
+
.benchmark-table {
|
|
362
|
+
border-collapse: collapse;
|
|
363
|
+
background: var(--surface);
|
|
364
|
+
border: 1px solid var(--border);
|
|
365
|
+
border-radius: var(--radius);
|
|
366
|
+
font-size: 0.8125rem;
|
|
367
|
+
width: 100%;
|
|
368
|
+
margin-bottom: 1.5rem;
|
|
369
|
+
}
|
|
370
|
+
.benchmark-table th, .benchmark-table td {
|
|
371
|
+
padding: 0.625rem 0.75rem;
|
|
372
|
+
text-align: left;
|
|
373
|
+
border: 1px solid var(--border);
|
|
374
|
+
}
|
|
375
|
+
.benchmark-table th {
|
|
376
|
+
font-family: 'Poppins', sans-serif;
|
|
377
|
+
background: var(--header-bg);
|
|
378
|
+
color: var(--header-text);
|
|
379
|
+
font-weight: 500;
|
|
380
|
+
font-size: 0.75rem;
|
|
381
|
+
text-transform: uppercase;
|
|
382
|
+
letter-spacing: 0.04em;
|
|
383
|
+
}
|
|
384
|
+
.benchmark-table tr:hover { background: var(--bg); }
|
|
385
|
+
.benchmark-table tr.benchmark-row-with { background: rgba(33, 150, 243, 0.06); }
|
|
386
|
+
.benchmark-table tr.benchmark-row-without { background: rgba(255, 193, 7, 0.06); }
|
|
387
|
+
.benchmark-table tr.benchmark-row-with:hover { background: rgba(33, 150, 243, 0.12); }
|
|
388
|
+
.benchmark-table tr.benchmark-row-without:hover { background: rgba(255, 193, 7, 0.12); }
|
|
389
|
+
.benchmark-table tr.benchmark-row-avg { font-weight: 600; border-top: 2px solid var(--border); }
|
|
390
|
+
.benchmark-table tr.benchmark-row-avg.benchmark-row-with { background: rgba(33, 150, 243, 0.12); }
|
|
391
|
+
.benchmark-table tr.benchmark-row-avg.benchmark-row-without { background: rgba(255, 193, 7, 0.12); }
|
|
392
|
+
.benchmark-delta-positive { color: var(--green); font-weight: 600; }
|
|
393
|
+
.benchmark-delta-negative { color: var(--red); font-weight: 600; }
|
|
394
|
+
.benchmark-notes {
|
|
395
|
+
background: var(--surface);
|
|
396
|
+
border: 1px solid var(--border);
|
|
397
|
+
border-radius: var(--radius);
|
|
398
|
+
padding: 1rem;
|
|
399
|
+
}
|
|
400
|
+
.benchmark-notes h3 {
|
|
401
|
+
font-family: 'Poppins', sans-serif;
|
|
402
|
+
font-size: 0.875rem;
|
|
403
|
+
margin-bottom: 0.75rem;
|
|
404
|
+
}
|
|
405
|
+
.benchmark-notes ul {
|
|
406
|
+
list-style: disc;
|
|
407
|
+
padding-left: 1.25rem;
|
|
408
|
+
}
|
|
409
|
+
.benchmark-notes li {
|
|
410
|
+
font-size: 0.8125rem;
|
|
411
|
+
line-height: 1.6;
|
|
412
|
+
margin-bottom: 0.375rem;
|
|
413
|
+
}
|
|
414
|
+
.benchmark-empty {
|
|
415
|
+
color: var(--text-muted);
|
|
416
|
+
font-style: italic;
|
|
417
|
+
text-align: center;
|
|
418
|
+
padding: 3rem;
|
|
419
|
+
}
|
|
420
|
+
|
|
421
|
+
/* ---- Navigation ---- */
|
|
422
|
+
.nav {
|
|
423
|
+
display: flex;
|
|
424
|
+
justify-content: space-between;
|
|
425
|
+
align-items: center;
|
|
426
|
+
padding: 1rem 2rem;
|
|
427
|
+
border-top: 1px solid var(--border);
|
|
428
|
+
background: var(--surface);
|
|
429
|
+
flex-shrink: 0;
|
|
430
|
+
}
|
|
431
|
+
.nav-btn {
|
|
432
|
+
font-family: 'Poppins', sans-serif;
|
|
433
|
+
padding: 0.5rem 1.25rem;
|
|
434
|
+
border: 1px solid var(--border);
|
|
435
|
+
border-radius: var(--radius);
|
|
436
|
+
background: var(--surface);
|
|
437
|
+
cursor: pointer;
|
|
438
|
+
font-size: 0.875rem;
|
|
439
|
+
font-weight: 500;
|
|
440
|
+
color: var(--text);
|
|
441
|
+
transition: all 0.15s;
|
|
442
|
+
}
|
|
443
|
+
.nav-btn:hover:not(:disabled) {
|
|
444
|
+
background: var(--bg);
|
|
445
|
+
border-color: var(--text-muted);
|
|
446
|
+
}
|
|
447
|
+
.nav-btn:disabled {
|
|
448
|
+
opacity: 0.4;
|
|
449
|
+
cursor: not-allowed;
|
|
450
|
+
}
|
|
451
|
+
.done-btn {
|
|
452
|
+
font-family: 'Poppins', sans-serif;
|
|
453
|
+
padding: 0.5rem 1.5rem;
|
|
454
|
+
border: 1px solid var(--border);
|
|
455
|
+
border-radius: var(--radius);
|
|
456
|
+
background: var(--surface);
|
|
457
|
+
color: var(--text);
|
|
458
|
+
cursor: pointer;
|
|
459
|
+
font-size: 0.875rem;
|
|
460
|
+
font-weight: 500;
|
|
461
|
+
transition: all 0.15s;
|
|
462
|
+
}
|
|
463
|
+
.done-btn:hover {
|
|
464
|
+
background: var(--bg);
|
|
465
|
+
border-color: var(--text-muted);
|
|
466
|
+
}
|
|
467
|
+
.done-btn.ready {
|
|
468
|
+
border: none;
|
|
469
|
+
background: var(--accent);
|
|
470
|
+
color: white;
|
|
471
|
+
font-weight: 600;
|
|
472
|
+
}
|
|
473
|
+
.done-btn.ready:hover {
|
|
474
|
+
background: var(--accent-hover);
|
|
475
|
+
}
|
|
476
|
+
/* ---- Done overlay ---- */
|
|
477
|
+
.done-overlay {
|
|
478
|
+
display: none;
|
|
479
|
+
position: fixed;
|
|
480
|
+
inset: 0;
|
|
481
|
+
background: rgba(0, 0, 0, 0.5);
|
|
482
|
+
z-index: 100;
|
|
483
|
+
justify-content: center;
|
|
484
|
+
align-items: center;
|
|
485
|
+
}
|
|
486
|
+
.done-overlay.visible {
|
|
487
|
+
display: flex;
|
|
488
|
+
}
|
|
489
|
+
.done-card {
|
|
490
|
+
background: var(--surface);
|
|
491
|
+
border-radius: 12px;
|
|
492
|
+
padding: 2rem 3rem;
|
|
493
|
+
text-align: center;
|
|
494
|
+
box-shadow: 0 20px 60px rgba(0, 0, 0, 0.3);
|
|
495
|
+
max-width: 500px;
|
|
496
|
+
}
|
|
497
|
+
.done-card h2 {
|
|
498
|
+
font-size: 1.5rem;
|
|
499
|
+
margin-bottom: 0.5rem;
|
|
500
|
+
}
|
|
501
|
+
.done-card p {
|
|
502
|
+
color: var(--text-muted);
|
|
503
|
+
margin-bottom: 1.5rem;
|
|
504
|
+
line-height: 1.5;
|
|
505
|
+
}
|
|
506
|
+
.done-card .btn-row {
|
|
507
|
+
display: flex;
|
|
508
|
+
gap: 0.5rem;
|
|
509
|
+
justify-content: center;
|
|
510
|
+
}
|
|
511
|
+
.done-card button {
|
|
512
|
+
padding: 0.5rem 1.25rem;
|
|
513
|
+
border: 1px solid var(--border);
|
|
514
|
+
border-radius: var(--radius);
|
|
515
|
+
background: var(--surface);
|
|
516
|
+
cursor: pointer;
|
|
517
|
+
font-size: 0.875rem;
|
|
518
|
+
}
|
|
519
|
+
.done-card button:hover {
|
|
520
|
+
background: var(--bg);
|
|
521
|
+
}
|
|
522
|
+
/* ---- Toast ---- */
|
|
523
|
+
.toast {
|
|
524
|
+
position: fixed;
|
|
525
|
+
bottom: 5rem;
|
|
526
|
+
left: 50%;
|
|
527
|
+
transform: translateX(-50%);
|
|
528
|
+
background: var(--header-bg);
|
|
529
|
+
color: var(--header-text);
|
|
530
|
+
padding: 0.625rem 1.25rem;
|
|
531
|
+
border-radius: var(--radius);
|
|
532
|
+
font-size: 0.875rem;
|
|
533
|
+
opacity: 0;
|
|
534
|
+
transition: opacity 0.3s;
|
|
535
|
+
pointer-events: none;
|
|
536
|
+
z-index: 200;
|
|
537
|
+
}
|
|
538
|
+
.toast.visible {
|
|
539
|
+
opacity: 1;
|
|
540
|
+
}
|
|
541
|
+
</style>
|
|
542
|
+
</head>
|
|
543
|
+
<body>
|
|
544
|
+
<div id="app" style="height:100vh; display:flex; flex-direction:column;">
|
|
545
|
+
<div class="header">
|
|
546
|
+
<div>
|
|
547
|
+
<h1>Eval Review: <span id="skill-name"></span></h1>
|
|
548
|
+
<div class="instructions">Review each output and leave feedback below. Navigate with arrow keys or buttons. When done, copy feedback and paste into Claude Code.</div>
|
|
549
|
+
</div>
|
|
550
|
+
<div class="progress" id="progress"></div>
|
|
551
|
+
</div>
|
|
552
|
+
|
|
553
|
+
<!-- View tabs (only shown when benchmark data exists) -->
|
|
554
|
+
<div class="view-tabs" id="view-tabs" style="display:none;">
|
|
555
|
+
<button class="view-tab active" onclick="switchView('outputs')">Outputs</button>
|
|
556
|
+
<button class="view-tab" onclick="switchView('benchmark')">Benchmark</button>
|
|
557
|
+
</div>
|
|
558
|
+
|
|
559
|
+
<!-- Outputs panel (qualitative review) -->
|
|
560
|
+
<div class="view-panel active" id="panel-outputs">
|
|
561
|
+
<div class="main">
|
|
562
|
+
<!-- Prompt -->
|
|
563
|
+
<div class="section">
|
|
564
|
+
<div class="section-header">Prompt <span class="config-badge" id="config-badge" style="display:none;"></span></div>
|
|
565
|
+
<div class="section-body">
|
|
566
|
+
<div class="prompt-text" id="prompt-text"></div>
|
|
567
|
+
</div>
|
|
568
|
+
</div>
|
|
569
|
+
|
|
570
|
+
<!-- Outputs -->
|
|
571
|
+
<div class="section">
|
|
572
|
+
<div class="section-header">Output</div>
|
|
573
|
+
<div class="section-body" id="outputs-body">
|
|
574
|
+
<div class="empty-state">No output files found</div>
|
|
575
|
+
</div>
|
|
576
|
+
</div>
|
|
577
|
+
|
|
578
|
+
<!-- Previous Output (collapsible) -->
|
|
579
|
+
<div class="section" id="prev-outputs-section" style="display:none;">
|
|
580
|
+
<div class="section-header">
|
|
581
|
+
<div class="grades-toggle" onclick="togglePrevOutputs()">
|
|
582
|
+
<span class="arrow" id="prev-outputs-arrow">▶</span>
|
|
583
|
+
Previous Output
|
|
584
|
+
</div>
|
|
585
|
+
</div>
|
|
586
|
+
<div class="grades-content" id="prev-outputs-content"></div>
|
|
587
|
+
</div>
|
|
588
|
+
|
|
589
|
+
<!-- Grades (collapsible) -->
|
|
590
|
+
<div class="section" id="grades-section" style="display:none;">
|
|
591
|
+
<div class="section-header">
|
|
592
|
+
<div class="grades-toggle" onclick="toggleGrades()">
|
|
593
|
+
<span class="arrow" id="grades-arrow">▶</span>
|
|
594
|
+
Formal Grades
|
|
595
|
+
</div>
|
|
596
|
+
</div>
|
|
597
|
+
<div class="grades-content" id="grades-content"></div>
|
|
598
|
+
</div>
|
|
599
|
+
|
|
600
|
+
<!-- Feedback -->
|
|
601
|
+
<div class="section">
|
|
602
|
+
<div class="section-header">Your Feedback</div>
|
|
603
|
+
<div class="section-body">
|
|
604
|
+
<textarea
|
|
605
|
+
class="feedback-textarea"
|
|
606
|
+
id="feedback"
|
|
607
|
+
placeholder="What do you think of this output? Any issues, suggestions, or things that look great?"
|
|
608
|
+
></textarea>
|
|
609
|
+
<div class="feedback-status" id="feedback-status"></div>
|
|
610
|
+
<div class="prev-feedback" id="prev-feedback" style="display:none;">
|
|
611
|
+
<div class="prev-feedback-label">Previous feedback</div>
|
|
612
|
+
<div id="prev-feedback-text"></div>
|
|
613
|
+
</div>
|
|
614
|
+
</div>
|
|
615
|
+
</div>
|
|
616
|
+
</div>
|
|
617
|
+
|
|
618
|
+
<div class="nav" id="outputs-nav">
|
|
619
|
+
<button class="nav-btn" id="prev-btn" onclick="navigate(-1)">← Previous</button>
|
|
620
|
+
<button class="done-btn" id="done-btn" onclick="showDoneDialog()">Submit All Reviews</button>
|
|
621
|
+
<button class="nav-btn" id="next-btn" onclick="navigate(1)">Next →</button>
|
|
622
|
+
</div>
|
|
623
|
+
</div><!-- end panel-outputs -->
|
|
624
|
+
|
|
625
|
+
<!-- Benchmark panel (quantitative stats) -->
|
|
626
|
+
<div class="view-panel" id="panel-benchmark">
|
|
627
|
+
<div class="benchmark-view" id="benchmark-content">
|
|
628
|
+
<div class="benchmark-empty">No benchmark data available. Run a benchmark to see quantitative results here.</div>
|
|
629
|
+
</div>
|
|
630
|
+
</div>
|
|
631
|
+
</div>
|
|
632
|
+
|
|
633
|
+
<!-- Done overlay -->
|
|
634
|
+
<div class="done-overlay" id="done-overlay">
|
|
635
|
+
<div class="done-card">
|
|
636
|
+
<h2>Review Complete</h2>
|
|
637
|
+
<p>Your feedback has been saved. Go back to your Claude Code session and tell Claude you're done reviewing.</p>
|
|
638
|
+
<div class="btn-row">
|
|
639
|
+
<button onclick="closeDoneDialog()">OK</button>
|
|
640
|
+
</div>
|
|
641
|
+
</div>
|
|
642
|
+
</div>
|
|
643
|
+
|
|
644
|
+
<!-- Toast -->
|
|
645
|
+
<div class="toast" id="toast"></div>
|
|
646
|
+
|
|
647
|
+
<script>
|
|
648
|
+
// ---- Embedded data (injected by generate_review.py) ----
|
|
649
|
+
const EMBEDDED_DATA = {"skill_name": "apply-okf", "runs": [{"id": "eval-1-register-new-adr-with_skill", "prompt": "docs/adr/002-cache-strategy.md \u3092\u66f8\u3044\u305f\u306e\u3067 OKF \u30d0\u30f3\u30c9\u30eb\u306b\u767b\u9332\u3057\u3066\u3002docs/ \u306f OKF v0.2 \u30d0\u30f3\u30c9\u30eb\u3002", "eval_id": 1, "outputs": [{"name": "report.md", "type": "text", "content": "# eval-1: \u65b0\u898f ADR \u306e OKF \u30d0\u30f3\u30c9\u30eb\u767b\u9332\uff08with_skill\uff09\n\n## OKF \u9069\u7528\u7d50\u679c\n\n- \u5bfe\u8c61: `docs/adr/002-cache-strategy.md`\uff08\u64cd\u4f5c: apply\uff09\n- generated: `{ by: claude-code/claude-fable-5, at: 2026-08-25T02:52:49Z }`\uff08\u672c\u6587\u306f\u30a8\u30fc\u30b8\u30a7\u30f3\u30c8\u304c\u672c\u30bb\u30c3\u30b7\u30e7\u30f3\u3067\u57f7\u7b46\u3057\u305f\u305f\u3081 `<producer>/<version>` \u5f62\u5f0f\uff09\n- type: `ADR`\uff08\u89aa\u30c7\u30a3\u30ec\u30af\u30c8\u30ea `adr/` \u304b\u3089\u63a8\u5b9a\u3002\u65e2\u5b58 ADR-001 \u3068\u540c\u578b\uff09\n- description: `--description` \u3067\u660e\u793a\u6307\u5b9a\uff08\u5192\u982d\u6bb5\u843d\u3068\u540c\u6587\uff09\n- stale_after: \u4ed8\u4e0e\u305b\u305a\uff08\u8a2d\u8a08\u5224\u65ad\u306f\u671f\u9593\u3067\u9673\u8150\u5316\u3057\u306a\u3044\u305f\u3081\uff09\n- verified: \u4ed8\u4e0e\u305b\u305a\uff08\u81ea\u5206\u304c\u66f8\u3044\u305f\u76f4\u5f8c\u306b\u81ea\u5206\u3067\u691c\u8a3c\u3057\u306a\u3044\u3002\u30e6\u30fc\u30b6\u30fc\u306e\u30ec\u30d3\u30e5\u30fc\u5f8c\u306b `verify --by human:<id>` \u3092\u5b9f\u65bd\u3059\u308b\uff09\n- index.md: `docs/adr/index.md` \u672b\u5c3e\u306b ADR-002 \u306e\u30a8\u30f3\u30c8\u30ea\u8ffd\u52a0\uff08\u30bb\u30af\u30b7\u30e7\u30f3\u5206\u3051\u7121\u3057\u306e\u305f\u3081\u4f4d\u7f6e\u8abf\u6574\u4e0d\u8981\uff09\n- log.md: `docs/log.md` \u306b 2026-08-25 \u306e Creation \u30a8\u30f3\u30c8\u30ea\u8ffd\u52a0\n- \u691c\u8a3c: ERROR 0 / WARN 0\n- \u8981\u78ba\u8a8d: \u306a\u3057\n\n## \u5224\u65ad\u30e1\u30e2\n\n- `PROJECT.md` \u306f `.claude/skills/apply-okf/` \u306b\u5b58\u5728\u3057\u306a\u3044\u305f\u3081\u3001SKILL.md \u306e\u307f\u3092\u6307\u91dd\u3068\u3057\u305f\u3002\n- `gulp okf:check` \u306f\u30d7\u30ed\u30b8\u30a7\u30af\u30c8\u306b gulpfile \u304c\u7121\u3044\u305f\u3081\u3001\u4ee3\u66ff\u3068\u3057\u3066 `migrating-okf/scripts/okf_check.py --check` \u3092\u4f7f\u7528\u3057\u305f\u3002\n- \u30d5\u30ed\u30f3\u30c8\u30de\u30bf\u30fc\u306f\u624b\u66f8\u304d\u305b\u305a\u3001\u540c\u68b1\u30b9\u30af\u30ea\u30d7\u30c8 `okf_apply.py` \u3067\u4ed8\u4e0e\u3057\u305f\u3002\n\n## \u5b9f\u884c\u30b3\u30de\u30f3\u30c9\u3068\u51fa\u529b\n\n```text\n$ python .claude/skills/apply-okf/scripts/okf_apply.py apply docs docs/adr/002-cache-strategy.md --by claude-code/claude-fable-5 --description \"Redis \u3092\u30bb\u30c3\u30b7\u30e7\u30f3\u3068\u5546\u54c1\u30de\u30b9\u30bf\u306e\u30ad\u30e3\u30c3\u30b7\u30e5\u306b\u63a1\u7528\u3059\u308b\u3002\"\ndocs\\adr\\002-cache-strategy.md: creation\uff08index.md \u306b\u30a8\u30f3\u30c8\u30ea\u8ffd\u52a0\uff09\n\u6b21: okf_check.py --check\uff08\u307e\u305f\u306f gulp okf:check\uff09\u3067\u78ba\u8a8d\u3059\u308b\n\n$ python .claude/skills/apply-okf/scripts/okf_apply.py status docs docs/adr/002-cache-strategy.md\ndocs\\adr\\002-cache-strategy.md: type=ADR, title=\"ADR-002: \u30ad\u30e3\u30c3\u30b7\u30e5\u6226\u7565\", status=stable, generated={ by: claude-code/claude-fable-5, at: 2026-08-25T02:52:49Z }\n\n$ python .claude/skills/migrating-okf/scripts/okf_check.py docs --check\n\nERROR 0 / WARN 0\n```\n\n## \u5909\u66f4\u5f8c\u30d5\u30a1\u30a4\u30eb\n\n### docs/adr/002-cache-strategy.md\uff08\u30d5\u30ed\u30f3\u30c8\u30de\u30bf\u30fc\u90e8\uff09\n\n```yaml\n---\ntype: ADR\ntitle: \"ADR-002: \u30ad\u30e3\u30c3\u30b7\u30e5\u6226\u7565\"\ndescription: \"Redis \u3092\u30bb\u30c3\u30b7\u30e7\u30f3\u3068\u5546\u54c1\u30de\u30b9\u30bf\u306e\u30ad\u30e3\u30c3\u30b7\u30e5\u306b\u63a1\u7528\u3059\u308b\u3002\"\ntags: [adr]\nstatus: stable\ngenerated: { by: claude-code/claude-fable-5, at: 2026-08-25T02:52:49Z }\n---\n```\n\n### docs/adr/index.md\n\n```markdown\n# ADR\n\n* [ADR-001: DB \u9078\u5b9a](./001-db.md) - PostgreSQL \u3092\u63a1\u7528\n* [ADR-002: \u30ad\u30e3\u30c3\u30b7\u30e5\u6226\u7565](./002-cache-strategy.md) - Redis \u3092\u30bb\u30c3\u30b7\u30e7\u30f3\u3068\u5546\u54c1\u30de\u30b9\u30bf\u306e\u30ad\u30e3\u30c3\u30b7\u30e5\u306b\u63a1\u7528\u3059\u308b\u3002\n```\n\n### docs/log.md\n\n```markdown\n# Docs Update Log\n\n## 2026-08-25\n* **Creation**: [002-cache-strategy](/adr/002-cache-strategy.md) \u3092\u4f5c\u6210\uff08claude-code/claude-fable-5\uff09\n\n## 2026-08-20\n* **Creation**: \u30d0\u30f3\u30c9\u30eb\u3092\u521d\u671f\u5316\n```\n\n## \u6b21\u306e\u30b9\u30c6\u30c3\u30d7\n\n- \u30e6\u30fc\u30b6\u30fc\u304c ADR-002 \u3092\u30ec\u30d3\u30e5\u30fc\u3057\u3066\u627f\u8a8d\u3057\u305f\u3089 `python okf_apply.py verify docs docs/adr/002-cache-strategy.md --by human:kakimomokuri`\n- `git add docs/adr/002-cache-strategy.md docs/adr/index.md docs/log.md` \u3057\u3066\u30b3\u30df\u30c3\u30c8\n"}], "grading": {"expectations": [{"text": "frontmatter-added: type \u304c ADR", "passed": true, "evidence": "type: ADR"}, {"text": "generated-is-agent: generated.by \u304c <producer>/<version>", "passed": true, "evidence": "claude-code/claude-fable-5"}, {"text": "no-self-verified: verified \u7121\u3057", "passed": true, "evidence": "none"}, {"text": "index-entry-added: adr/index.md \u306b 002", "passed": true, "evidence": ""}, {"text": "log-creation-entry: log.md \u306b Creation", "passed": true, "evidence": ""}, {"text": "body-unchanged: \u672c\u6587\u4e0d\u5909", "passed": true, "evidence": ""}, {"text": "check-zero-errors", "passed": true, "evidence": "ERROR 0 / WARN 0"}]}}, {"id": "eval-1-register-new-adr-without_skill", "prompt": "docs/adr/002-cache-strategy.md \u3092\u66f8\u3044\u305f\u306e\u3067 OKF \u30d0\u30f3\u30c9\u30eb\u306b\u767b\u9332\u3057\u3066\u3002docs/ \u306f OKF v0.2 \u30d0\u30f3\u30c9\u30eb\u3002", "eval_id": 1, "outputs": [{"name": "report.md", "type": "text", "content": "# \u5b8c\u4e86\u5831\u544a\uff1aADR-002 \u3092 OKF v0.2 \u30d0\u30f3\u30c9\u30eb\u306b\u767b\u9332\n\n## \u5909\u66f4\u5185\u5bb9\n\n- `docs/adr/002-cache-strategy.md`\uff1aOKF v0.2 \u306e\u30d5\u30ed\u30f3\u30c8\u30de\u30bf\u30fc\u3092\u4ed8\u4e0e\n - `type: ADR`\u3001`title`\u3001`description`\u3001`tags: [adr]`\uff08\u65e2\u5b58 ADR-001 \u3068\u540c\u3058\u5f62\u5f0f\uff09\n - `status: draft` \u2014 \u672c\u6587\u306f\u30a8\u30fc\u30b8\u30a7\u30f3\u30c8\u304c\u66f8\u304d\u3001\u4eba\u306e\u30ec\u30d3\u30e5\u30fc\u304c\u672a\u5b9f\u65bd\u306e\u305f\u3081\uff08\u00a75.4\uff09\n - `generated: { by: claude-code/claude-fable-5, at: 2026-08-25T02:53:10Z }` \u2014 \u30a8\u30fc\u30b8\u30a7\u30f3\u30c8\u57f7\u7b46\u306a\u306e\u3067 `<producer>/<version>` \u5f62\u5f0f\uff08\u00a77\u30fb\u00a714.5\uff09\n - `verified` \u306f\u4ed8\u4e0e\u3057\u3066\u3044\u307e\u305b\u3093\u3002\u4eba\u304c\u30ec\u30d3\u30e5\u30fc\u3057\u305f\u3089 `verified: { by: human:<id>, at: ... }` \u3092\u8ffd\u52a0\u3057\u3066 `status: stable` \u306b\u5909\u66f4\u3057\u3066\u304f\u3060\u3055\u3044\n - \u672c\u6587\u306f\u5909\u66f4\u3057\u3066\u3044\u307e\u305b\u3093\n- `docs/adr/index.md`\uff1aADR-002 \u306e\u30a8\u30f3\u30c8\u30ea\u3092 description \u4ed8\u304d\u3067\u8ffd\u52a0\uff08\u00a78\uff09\n- `docs/log.md`\uff1a`## 2026-08-25` \u898b\u51fa\u3057\u3092\u5148\u982d\u306b\u8ffd\u52a0\u3057\u3001`**Creation**` \u30a8\u30f3\u30c8\u30ea\u3092\u8a18\u9332\uff08\u00a79\u3001\u65b0\u3057\u3044\u65e5\u4ed8\u304c\u5148\u982d\uff09\n\n## \u5224\u65ad\n\n- \u6765\u6b74 `sources` \u306f\u3001\u672c\u6587\u306b\u5916\u90e8\u8cc7\u6599\u3078\u306e\u8a00\u53ca\u304c\u306a\u3044\u305f\u3081\u4ed8\u3051\u3066\u3044\u307e\u305b\u3093\u3002\n- `stale_after` \u306f ADR\uff08\u610f\u601d\u6c7a\u5b9a\u8a18\u9332\uff09\u306b\u306f\u901a\u5e38\u4e0d\u8981\u3068\u5224\u65ad\u3057\u3001\u4ed8\u3051\u3066\u3044\u307e\u305b\u3093\u3002\n\n## \u6b21\u306e\u30b9\u30c6\u30c3\u30d7\n\n- ADR-002 \u306e\u672c\u6587\u30ec\u30d3\u30e5\u30fc\uff08\u4eba\uff09\u3002\u30ec\u30d3\u30e5\u30fc\u5f8c\u306b `verified` \u3092\u8ffd\u52a0\u3057 `status: stable` \u3078\u66f4\u65b0\n- \u672c\u6587\u304c\u8584\u3044\u306e\u3067\u300c\u691c\u8a0e\u3057\u305f\u9078\u629e\u80a2\u300d\u300c\u5f71\u97ff\u300d\u306e\u7bc0\u3092\u88dc\u3046\u3053\u3068\u3092\u63a8\u5968\n"}], "grading": {"expectations": [{"text": "frontmatter-added: type \u304c ADR", "passed": true, "evidence": "type: ADR"}, {"text": "generated-is-agent: generated.by \u304c <producer>/<version>", "passed": true, "evidence": "claude-code/claude-fable-5"}, {"text": "no-self-verified: verified \u7121\u3057", "passed": true, "evidence": "none"}, {"text": "index-entry-added: adr/index.md \u306b 002", "passed": true, "evidence": ""}, {"text": "log-creation-entry: log.md \u306b Creation", "passed": true, "evidence": ""}, {"text": "body-unchanged: \u672c\u6587\u4e0d\u5909", "passed": true, "evidence": ""}, {"text": "check-zero-errors", "passed": true, "evidence": "ERROR 0 / WARN 0"}]}}, {"id": "eval-2-verify-reviewed-doc-with_skill", "prompt": "docs/design/data-model.md \u3092\u30ec\u30d3\u30e5\u30fc\u3057\u3066\u554f\u984c\u306a\u304b\u3063\u305f\u3002OKF \u7684\u306b\u78ba\u8a8d\u6e08\u307f\u306b\u3057\u3066\u304a\u3044\u3066\u3002\u79c1\u306f human:kakimomokuri\u3002", "eval_id": 2, "outputs": [{"name": "report.md", "type": "text", "content": "# eval-2 (with skill) \u5b8c\u4e86\u5831\u544a\n\n## OKF \u9069\u7528\u7d50\u679c\n\n- \u5bfe\u8c61: `docs/design/data-model.md`\uff08\u64cd\u4f5c: verify\uff09\n- generated: \u5909\u66f4\u306a\u3057\uff08\u672c\u6587\u672a\u5909\u66f4\u306e\u305f\u3081 `{ by: claude-code/claude-fable-5, at: 2026-08-21T00:00:00Z }` \u3092\u7dad\u6301\uff09\n- verified: `{ by: human:kakimomokuri, at: 2026-08-25T02:52:50Z }` \u3092\u8ffd\u8a18\n- index.md: \u66f4\u65b0\u306a\u3057\uff08\u65e2\u5b58\u30a8\u30f3\u30c8\u30ea\u3042\u308a\u3001verify \u3067\u306f\u4e0d\u8981\uff09 / log.md: `2026-08-25` \u306b Verification \u3092\u8a18\u9332\n- \u691c\u8a3c: ERROR 1 / WARN 0 \u2014 \u305f\u3060\u3057 ERROR \u306f\u4f9d\u983c\u5bfe\u8c61\u5916\u306e `docs/adr/002-cache-strategy.md`\uff08\u672a\u8ffd\u8de1\u30fb\u30d5\u30ed\u30f3\u30c8\u30de\u30bf\u30fc\u7121\u3057\uff09\n- \u8981\u78ba\u8a8d: `adr/002-cache-strategy.md` \u306f\u8457\u8005\u4e0d\u660e\u306e\u305f\u3081 `apply` \u3092\u5b9f\u884c\u3057\u3066\u3044\u306a\u3044\u3002\u8457\u8005\u304c\u5206\u304b\u308c\u3070 `python okf_apply.py apply docs docs/adr/002-cache-strategy.md --by <actor>` \u3067\u89e3\u6d88\u3067\u304d\u308b\n\n## \u5224\u65ad\n\n- `verified` \u306f\u81ea\u5206\u3067\u306f\u4ed8\u3051\u305a\u3001\u30e6\u30fc\u30b6\u30fc\u7533\u544a\u306e\u30a2\u30af\u30bf\u30fc `human:kakimomokuri` \u3067\u4ed8\u4e0e\uff08SKILL.md\u300cverified \u3092\u4ed8\u3051\u3066\u3088\u3044\u304b\u300d\u306b\u6e96\u62e0\uff09\n- \u30d5\u30ed\u30f3\u30c8\u30de\u30bf\u30fc\u306f\u624b\u66f8\u304d\u305b\u305a\u540c\u68b1\u30b9\u30af\u30ea\u30d7\u30c8\u3067\u64cd\u4f5c\n- PROJECT.md \u306f\u5b58\u5728\u3057\u306a\u3044\u305f\u3081\u65e2\u5b9a\uff08\u30d0\u30f3\u30c9\u30eb = `docs/`\uff09\u3092\u4f7f\u7528\n\n## \u5b9f\u884c\u30b3\u30de\u30f3\u30c9\u3068\u51fa\u529b\n\n```\n$ python .claude/skills/apply-okf/scripts/okf_apply.py verify docs docs/design/data-model.md --by human:kakimomokuri\ndocs\\design\\data-model.md: verified \u306b human:kakimomokuri \u3092\u8ffd\u8a18\n\u6b21: okf_check.py --check\uff08\u307e\u305f\u306f gulp okf:check\uff09\u3067\u78ba\u8a8d\u3059\u308b\nexit=0\n\n$ python .claude/skills/apply-okf/scripts/okf_apply.py status docs docs/design/data-model.md\ndocs\\design\\data-model.md: type=Design, title=\"\u30c7\u30fc\u30bf\u30e2\u30c7\u30eb\", status=stable, generated={ by: claude-code/claude-fable-5, at: 2026-08-21T00:00:00Z }, verified=(block)\n\n$ python .claude/skills/migrating-okf/scripts/okf_check.py docs --check\nERROR adr/002-cache-strategy.md: \u30d5\u30ed\u30f3\u30c8\u30de\u30bf\u30fc\u304c\u7121\u3044\n\nERROR 1 / WARN 0\nexit=1\n\n$ git diff --stat\n docs/design/data-model.md | 2 ++\n docs/log.md | 3 +++\n 2 files changed, 5 insertions(+)\n```\n\n## \u5909\u66f4\u5f8c\u30d5\u30ed\u30f3\u30c8\u30de\u30bf\u30fc\uff08data-model.md\uff09\n\n```yaml\n---\ntype: Design\ntitle: \"\u30c7\u30fc\u30bf\u30e2\u30c7\u30eb\"\ndescription: \"\u53d7\u6ce8\u7ba1\u7406\u306e\u30c7\u30fc\u30bf\u30e2\u30c7\u30eb\u3002\"\ntags: [design]\nstatus: stable\ngenerated: { by: claude-code/claude-fable-5, at: 2026-08-21T00:00:00Z }\nverified:\n - { by: human:kakimomokuri, at: 2026-08-25T02:52:50Z }\n---\n```\n\n## log.md \u8ffd\u8a18\n\n```\n## 2026-08-25\n* **Verification**: [data-model](/design/data-model.md) \u3092 human:kakimomokuri \u304c\u691c\u8a3c\n```\n"}], "grading": {"expectations": [{"text": "verified-human-added", "passed": true, "evidence": "verified:\n - { by: human:kakimomokuri, at: 2026-08-25T02:52:50Z"}, {"text": "generated-untouched", "passed": true, "evidence": ""}, {"text": "timestamp-format: verified.at ISO8601+TZ", "passed": true, "evidence": "2026-08-25T02:52:50Z"}, {"text": "log-verification-entry", "passed": true, "evidence": ""}, {"text": "body-unchanged", "passed": true, "evidence": ""}, {"text": "check-zero-errors", "passed": false, "evidence": "ERROR 1 / WARN 0"}]}}, {"id": "eval-2-verify-reviewed-doc-without_skill", "prompt": "docs/design/data-model.md \u3092\u30ec\u30d3\u30e5\u30fc\u3057\u3066\u554f\u984c\u306a\u304b\u3063\u305f\u3002OKF \u7684\u306b\u78ba\u8a8d\u6e08\u307f\u306b\u3057\u3066\u304a\u3044\u3066\u3002\u79c1\u306f human:kakimomokuri\u3002", "eval_id": 2, "outputs": [{"name": "report.md", "type": "text", "content": "## \u5b9f\u884c\u5b8c\u4e86\n\n### \u5909\u66f4\u5185\u5bb9\n\n- `docs/design/data-model.md` \u306e\u30d5\u30ed\u30f3\u30c8\u30de\u30bf\u30fc\u306b `verified: { by: human:kakimomokuri, at: 2026-08-25T02:53:08Z }` \u3092\u8ffd\u52a0\uff08OKF \u00a75.2 \u306e\u88f8\u30de\u30c3\u30d4\u30f3\u30b0\u5f62\u5f0f\u3001\u00a77 \u306e `human:<id>` \u30a2\u30af\u30bf\u30fc\u898f\u7d04\u306b\u6e96\u62e0\uff09\u3002\u3053\u308c\u306b\u3088\u308a\u4fe1\u983c\u30c6\u30a3\u30a2\u306f unverified \u2192 **human-reviewed**\uff08\u00a75.3\uff09\u306b\u306a\u308b\u3002\n- `generated`\u30fb`status: stable` \u306f\u5909\u66f4\u3057\u3066\u3044\u306a\u3044\uff08`verified` \u306f `generated.at` \u3068\u72ec\u7acb\u3001\u00a75.2\uff09\u3002\n- `docs/log.md` \u306b `## 2026-08-25` \u898b\u51fa\u3057\u3092\u65b0\u8a2d\u3057\u3001\u30ec\u30d3\u30e5\u30fc\u5b8c\u4e86\u306e Update \u30a8\u30f3\u30c8\u30ea\u3092\u8ffd\u52a0\uff08\u00a79\uff09\u3002\n- `index.md` \u306f description \u306b\u5909\u66f4\u304c\u306a\u3044\u305f\u3081\u66f4\u65b0\u4e0d\u8981\u3002\n\n### \u5224\u65ad\u3057\u305f\u3053\u3068\n\n- \u691c\u8a3c\u65e5\u6642\u306f\u30e6\u30fc\u30b6\u30fc\u304b\u3089\u306e\u6307\u793a\u304c\u306a\u3044\u305f\u3081\u3001\u4f5c\u696d\u6642\u70b9\u306e UTC\uff08`date -u`\uff09\u3092\u63a1\u7528\u3002\n- \u30ec\u30d3\u30e5\u30fc\u7d50\u679c\u300c\u554f\u984c\u306a\u3057\u300d\u306e\u305f\u3081\u672c\u6587\u306f\u7121\u5909\u66f4\u3002\n\n### \u6b21\u306e\u30b9\u30c6\u30c3\u30d7\n\n- \u5909\u66f4\u3092\u30b3\u30df\u30c3\u30c8\u3059\u308b\uff08`docs(design): data-model \u3092 human-reviewed \u306b\u66f4\u65b0`\uff09\u3002\n- \u5b9a\u671f\u898b\u76f4\u3057\u304c\u5fc5\u8981\u306a\u3089 `stale_after` \u306e\u8a2d\u5b9a\u3092\u691c\u8a0e\u3059\u308b\u3002\n"}], "grading": {"expectations": [{"text": "verified-human-added", "passed": true, "evidence": "verified: { by: human:kakimomokuri, at: 2026-08-25T02:53:08Z"}, {"text": "generated-untouched", "passed": true, "evidence": ""}, {"text": "timestamp-format: verified.at ISO8601+TZ", "passed": true, "evidence": "2026-08-25T02:53:08Z"}, {"text": "log-verification-entry", "passed": true, "evidence": ""}, {"text": "body-unchanged", "passed": true, "evidence": ""}, {"text": "check-zero-errors", "passed": false, "evidence": "ERROR 1 / WARN 0"}]}}, {"id": "eval-3-deprecate-replaced-doc-with_skill", "prompt": "docs/operation/deploy-old.md \u306f deploy.md \u306b\u7f6e\u304d\u63db\u3048\u305f\u304b\u3089\u3082\u3046\u4f7f\u308f\u306a\u3044\u3002\u30d0\u30f3\u30c9\u30eb\u4e0a\u3067\u6574\u7406\u3057\u3066\u3002", "eval_id": 3, "outputs": [{"name": "report.md", "type": "text", "content": "# eval-3: deploy-old.md \u306e\u5ec3\u6b62\uff08with_skill\uff09\n\n## OKF \u9069\u7528\u7d50\u679c\n\n- \u5bfe\u8c61: `docs/operation/deploy-old.md`\uff08\u64cd\u4f5c: deprecate\uff09\n - `status: stable` \u2192 `status: deprecated`\n - `replaced_by: /operation/deploy.md` \u3092\u8ffd\u52a0\n - \u30d5\u30a1\u30a4\u30eb\u306f\u524a\u9664\u3057\u306a\u3044\uff08OKF \u898f\u7d04: \u5ec3\u6b62\u6587\u66f8\u306f\u5c65\u6b74\u3068\u3057\u3066\u6b8b\u3059\uff09\n- generated: \u5909\u66f4\u306a\u3057\uff08\u672c\u6587\u306f\u5909\u3048\u3066\u3044\u306a\u3044\u305f\u3081 `human:kakimomokuri, 2026-06-01` \u3092\u7dad\u6301\uff09\n- index.md: `docs/operation/index.md` \u3092\u66f4\u65b0\u3002\u901a\u5e38\u4e00\u89a7\u304b\u3089\u5916\u3057\u300c\u5ec3\u6b62\u300d\u30bb\u30af\u30b7\u30e7\u30f3\u3078\u79fb\u52d5\u3001\u5f8c\u7d99\u3078\u306e\u30ea\u30f3\u30af\u3092\u660e\u8a18\n- log.md: 2026-08-25 \u306b Deprecation \u30a8\u30f3\u30c8\u30ea\u3092\u8ffd\u52a0\uff08\u7406\u7531: deploy.md\uff08CI/CD \u81ea\u52d5\u30c7\u30d7\u30ed\u30a4\uff09\u306b\u7f6e\u304d\u63db\u3048\u305f\u305f\u3081\u5ec3\u6b62\uff09\n- \u691c\u8a3c: `okf_check.py docs --check` \u2192 ERROR 1 / WARN 0\n - ERROR \u306f `adr/002-cache-strategy.md: \u30d5\u30ed\u30f3\u30c8\u30de\u30bf\u30fc\u304c\u7121\u3044`\u3002\u4eca\u56de\u306e\u4f9d\u983c\u3068\u306f\u7121\u95a2\u4fc2\u306e\u672a\u8ffd\u8de1\u30d5\u30a1\u30a4\u30eb\u306e\u305f\u3081\u672a\u5909\u66f4\n - \u4eca\u56de\u306e\u5bfe\u8c61\uff08operation/ \u914d\u4e0b\uff09\u306b\u30a8\u30e9\u30fc\u30fb\u8b66\u544a\u306a\u3057\n- \u8981\u78ba\u8a8d:\n - `adr/002-cache-strategy.md` \u306b `apply` \u3092\u639b\u3051\u308b\u304b\u3069\u3046\u304b\uff08\u8ab0\u304c\u66f8\u3044\u305f\u304b\u4e0d\u660e\u306e\u305f\u3081 `--by` \u306e\u5224\u65ad\u304c\u5fc5\u8981\uff09\n - Git Bash \u74b0\u5883\u3067\u306f `--replaced-by /operation/deploy.md` \u304c Windows \u30d1\u30b9\u306b\u5909\u63db\u3055\u308c\u308b\u3002`MSYS_NO_PATHCONV=1` \u3092\u4ed8\u3051\u3066\u5b9f\u884c\u3059\u308b\u5fc5\u8981\u304c\u3042\u3063\u305f\uff08\u521d\u56de\u5b9f\u884c\u3067 `C:/Program Files/Git/operation/deploy.md` \u306b\u5316\u3051\u305f\u305f\u3081\u518d\u5b9f\u884c\u3057\u3066\u4fee\u6b63\uff09\n\n## \u5b9f\u884c\u30b3\u30de\u30f3\u30c9\u3068\u51fa\u529b\n\n```\n$ python .claude/skills/apply-okf/scripts/okf_apply.py deprecate docs docs/operation/deploy-old.md --replaced-by /operation/deploy.md --log \"deploy.md\uff08CI/CD \u81ea\u52d5\u30c7\u30d7\u30ed\u30a4\uff09\u306b\u7f6e\u304d\u63db\u3048\u305f\u305f\u3081\u5ec3\u6b62\"\ndocs\\operation\\deploy-old.md: status: deprecated\uff08\u2192 C:/Program Files/Git/operation/deploy.md\uff09 # Git Bash \u306e\u30d1\u30b9\u5909\u63db\u3067\u58ca\u308c\u305f\n\u6b21: okf_check.py --check\uff08\u307e\u305f\u306f gulp okf:check\uff09\u3067\u78ba\u8a8d\u3059\u308b\n\n$ MSYS_NO_PATHCONV=1 python .claude/skills/apply-okf/scripts/okf_apply.py deprecate docs docs/operation/deploy-old.md --replaced-by /operation/deploy.md --no-log\ndocs\\operation\\deploy-old.md: status: deprecated\uff08\u2192 /operation/deploy.md\uff09\n\u6b21: okf_check.py --check\uff08\u307e\u305f\u306f gulp okf:check\uff09\u3067\u78ba\u8a8d\u3059\u308b\n\n$ python .claude/skills/migrating-okf/scripts/okf_check.py docs --check\nERROR adr/002-cache-strategy.md: \u30d5\u30ed\u30f3\u30c8\u30de\u30bf\u30fc\u304c\u7121\u3044\n\nERROR 1 / WARN 0\n\n$ python .claude/skills/apply-okf/scripts/okf_apply.py status docs docs/operation/*.md\ndocs\\operation\\deploy-old.md: type=Playbook, title=\"\u30c7\u30d7\u30ed\u30a4\u624b\u9806\uff08\u65e7\uff09\", status=deprecated, generated={ by: human:kakimomokuri, at: 2026-06-01T00:00:00Z }\ndocs\\operation\\deploy.md: type=Playbook, title=\"\u30c7\u30d7\u30ed\u30a4\u624b\u9806\", status=stable, generated={ by: human:kakimomokuri, at: 2026-08-15T00:00:00Z }\n```\n\n## git diff\n\n```diff\ndiff --git a/docs/log.md b/docs/log.md\nindex 69894b0..64e827d 100644\n--- a/docs/log.md\n+++ b/docs/log.md\n@@ -1,4 +1,7 @@\n # Docs Update Log\n \n+## 2026-08-25\n+* **Deprecation**: deploy.md\uff08CI/CD \u81ea\u52d5\u30c7\u30d7\u30ed\u30a4\uff09\u306b\u7f6e\u304d\u63db\u3048\u305f\u305f\u3081\u5ec3\u6b62\n+\n ## 2026-08-20\n * **Creation**: \u30d0\u30f3\u30c9\u30eb\u3092\u521d\u671f\u5316\ndiff --git a/docs/operation/deploy-old.md b/docs/operation/deploy-old.md\nindex 9c0d9d6..88834bb 100644\n--- a/docs/operation/deploy-old.md\n+++ b/docs/operation/deploy-old.md\n@@ -3,8 +3,9 @@ type: Playbook\n title: \"\u30c7\u30d7\u30ed\u30a4\u624b\u9806\uff08\u65e7\uff09\"\n description: \"ECS \u3078\u306e\u624b\u52d5\u30c7\u30d7\u30ed\u30a4\u624b\u9806\u3002\"\n tags: [operation]\n-status: stable\n+status: deprecated\n generated: { by: human:kakimomokuri, at: 2026-06-01T00:00:00Z }\n+replaced_by: /operation/deploy.md\n ---\n \n # \u30c7\u30d7\u30ed\u30a4\u624b\u9806\uff08\u65e7\uff09\ndiff --git a/docs/operation/index.md b/docs/operation/index.md\nindex af4033e..978027d 100644\n--- a/docs/operation/index.md\n+++ b/docs/operation/index.md\n@@ -1,4 +1,7 @@\n # \u904b\u7528\n \n-* [\u30c7\u30d7\u30ed\u30a4\u624b\u9806\uff08\u65e7\uff09](./deploy-old.md) - ECS \u3078\u306e\u624b\u52d5\u30c7\u30d7\u30ed\u30a4\n * [\u30c7\u30d7\u30ed\u30a4\u624b\u9806](./deploy.md) - CI/CD \u304b\u3089\u306e\u81ea\u52d5\u30c7\u30d7\u30ed\u30a4\n+\n+## \u5ec3\u6b62\n+\n+* [\u30c7\u30d7\u30ed\u30a4\u624b\u9806\uff08\u65e7\uff09](./deploy-old.md) - ECS \u3078\u306e\u624b\u52d5\u30c7\u30d7\u30ed\u30a4\uff08deprecated\u3002\u5f8c\u7d99: [\u30c7\u30d7\u30ed\u30a4\u624b\u9806](./deploy.md)\uff09\n```\n"}], "grading": {"expectations": [{"text": "status-deprecated", "passed": true, "evidence": ""}, {"text": "file-not-deleted", "passed": true, "evidence": ""}, {"text": "successor-recorded: deploy.md \u3078\u306e\u53c2\u7167", "passed": true, "evidence": ""}, {"text": "log-deprecation-entry", "passed": true, "evidence": ""}, {"text": "generated-untouched", "passed": true, "evidence": ""}, {"text": "check-zero-errors", "passed": false, "evidence": "ERROR 1 / WARN 0"}]}}, {"id": "eval-3-deprecate-replaced-doc-without_skill", "prompt": "docs/operation/deploy-old.md \u306f deploy.md \u306b\u7f6e\u304d\u63db\u3048\u305f\u304b\u3089\u3082\u3046\u4f7f\u308f\u306a\u3044\u3002\u30d0\u30f3\u30c9\u30eb\u4e0a\u3067\u6574\u7406\u3057\u3066\u3002", "eval_id": 3, "outputs": [{"name": "report.md", "type": "text", "content": "# \u5b8c\u4e86\u5831\u544a: deploy-old.md \u306e\u6574\u7406\n\n## \u5224\u65ad\n\nOKF v0.2 \u30ac\u30a4\u30c9\uff08\u00a75.4\u3001\u00a714.2 Step 3\uff09\u306b\u5f93\u3044\u3001\u7f6e\u304d\u63db\u3048\u6e08\u307f\u6587\u66f8\u306f\u524a\u9664\u305b\u305a `status: deprecated` \u306b\u3057\u3066\u30ea\u30f3\u30af\u3092\u4fdd\u3064\u65b9\u91dd\u3092\u63a1\u7528\u3057\u307e\u3057\u305f\u3002\n\n## \u5909\u66f4\u5185\u5bb9\n\n- `docs/operation/deploy-old.md`: `status: stable` \u2192 `deprecated`\u3002description \u306b\u7f6e\u304d\u63db\u3048\u5148\u3092\u660e\u8a18\u3057\u3001\u672c\u6587\u5192\u982d\u306b\u5ec3\u6b62\u6ce8\u8a18\u3068 `/operation/deploy.md` \u3078\u306e\u30ea\u30f3\u30af\u3092\u8ffd\u52a0\u3002`generated` \u306f\u5185\u5bb9\u5909\u66f4\u3067\u306f\u306a\u304f\u72b6\u614b\u5909\u66f4\u306e\u305f\u3081\u636e\u3048\u7f6e\u304d\u3002\n- `docs/operation/index.md`: \u73fe\u884c\u306e deploy.md \u3092\u5148\u982d\u306b\u4e26\u3079\u66ff\u3048\u3001deploy-old.md \u306e\u30a8\u30f3\u30c8\u30ea\u306b\u300c\u5ec3\u6b62\u6e08\u307f\u300d\u3092\u660e\u8a18\u3002\n- `docs/log.md`: 2026-08-25 \u306e `**Deprecation**` \u30a8\u30f3\u30c8\u30ea\u3092\u8ffd\u52a0\u3002\n\n## \u524a\u9664\u3057\u306a\u304b\u3063\u305f\u7406\u7531\n\ndeploy-old.md \u3078\u306e\u65e2\u5b58\u30ea\u30f3\u30af\uff08operation/index.md\uff09\u3068\u5c65\u6b74\u3092\u4fdd\u3064\u305f\u3081\u3002\u5b8c\u5168\u306b\u4e0d\u8981\u3068\u5224\u65ad\u3057\u305f\u5834\u5408\u306f\u3001\u30d5\u30a1\u30a4\u30eb\u524a\u9664\u3068 index.md \u306e\u30a8\u30f3\u30c8\u30ea\u9664\u53bb\u3001log.md \u3078\u306e\u8a18\u9332\u3092\u8ffd\u52a0\u3067\u884c\u3063\u3066\u304f\u3060\u3055\u3044\u3002\n"}], "grading": {"expectations": [{"text": "status-deprecated", "passed": true, "evidence": ""}, {"text": "file-not-deleted", "passed": true, "evidence": ""}, {"text": "successor-recorded: deploy.md \u3078\u306e\u53c2\u7167", "passed": true, "evidence": ""}, {"text": "log-deprecation-entry", "passed": true, "evidence": ""}, {"text": "generated-untouched", "passed": true, "evidence": ""}, {"text": "check-zero-errors", "passed": false, "evidence": "ERROR 1 / WARN 0"}]}}], "previous_feedback": {}, "previous_outputs": {}, "benchmark": {"metadata": {"skill_name": "apply-okf", "skill_path": "<path/to/skill>", "executor_model": "<model-name>", "analyzer_model": "<model-name>", "timestamp": "2026-08-25T02:54:55Z", "evals_run": [], "runs_per_configuration": 3}, "runs": [], "run_summary": {"delta": {"pass_rate": "+0.00", "time_seconds": "+0.0", "tokens": "+0"}}, "notes": []}};
|
|
650
|
+
|
|
651
|
+
// ---- State ----
|
|
652
|
+
let feedbackMap = {}; // run_id -> feedback text
|
|
653
|
+
let currentIndex = 0;
|
|
654
|
+
let visitedRuns = new Set();
|
|
655
|
+
|
|
656
|
+
// ---- Init ----
|
|
657
|
+
async function init() {
|
|
658
|
+
// Load saved feedback from server — but only if this isn't a fresh
|
|
659
|
+
// iteration (indicated by previous_feedback being present). When
|
|
660
|
+
// previous feedback exists, the feedback.json on disk is stale from
|
|
661
|
+
// the prior iteration and should not pre-fill the textareas.
|
|
662
|
+
const hasPrevious = Object.keys(EMBEDDED_DATA.previous_feedback || {}).length > 0
|
|
663
|
+
|| Object.keys(EMBEDDED_DATA.previous_outputs || {}).length > 0;
|
|
664
|
+
if (!hasPrevious) {
|
|
665
|
+
try {
|
|
666
|
+
const resp = await fetch("/api/feedback");
|
|
667
|
+
const data = await resp.json();
|
|
668
|
+
if (data.reviews) {
|
|
669
|
+
for (const r of data.reviews) feedbackMap[r.run_id] = r.feedback;
|
|
670
|
+
}
|
|
671
|
+
} catch { /* first run, no feedback yet */ }
|
|
672
|
+
}
|
|
673
|
+
|
|
674
|
+
document.getElementById("skill-name").textContent = EMBEDDED_DATA.skill_name;
|
|
675
|
+
showRun(0);
|
|
676
|
+
|
|
677
|
+
// Wire up feedback auto-save
|
|
678
|
+
const textarea = document.getElementById("feedback");
|
|
679
|
+
let saveTimeout = null;
|
|
680
|
+
textarea.addEventListener("input", () => {
|
|
681
|
+
clearTimeout(saveTimeout);
|
|
682
|
+
document.getElementById("feedback-status").textContent = "";
|
|
683
|
+
saveTimeout = setTimeout(() => saveCurrentFeedback(), 800);
|
|
684
|
+
});
|
|
685
|
+
}
|
|
686
|
+
|
|
687
|
+
// ---- Navigation ----
|
|
688
|
+
function navigate(delta) {
|
|
689
|
+
const newIndex = currentIndex + delta;
|
|
690
|
+
if (newIndex >= 0 && newIndex < EMBEDDED_DATA.runs.length) {
|
|
691
|
+
saveCurrentFeedback();
|
|
692
|
+
showRun(newIndex);
|
|
693
|
+
}
|
|
694
|
+
}
|
|
695
|
+
|
|
696
|
+
function updateNavButtons() {
|
|
697
|
+
document.getElementById("prev-btn").disabled = currentIndex === 0;
|
|
698
|
+
document.getElementById("next-btn").disabled =
|
|
699
|
+
currentIndex === EMBEDDED_DATA.runs.length - 1;
|
|
700
|
+
}
|
|
701
|
+
|
|
702
|
+
// ---- Show a run ----
|
|
703
|
+
function showRun(index) {
|
|
704
|
+
currentIndex = index;
|
|
705
|
+
const run = EMBEDDED_DATA.runs[index];
|
|
706
|
+
|
|
707
|
+
// Progress
|
|
708
|
+
document.getElementById("progress").textContent =
|
|
709
|
+
`${index + 1} of ${EMBEDDED_DATA.runs.length}`;
|
|
710
|
+
|
|
711
|
+
// Prompt
|
|
712
|
+
document.getElementById("prompt-text").textContent = run.prompt;
|
|
713
|
+
|
|
714
|
+
// Config badge
|
|
715
|
+
const badge = document.getElementById("config-badge");
|
|
716
|
+
const configMatch = run.id.match(/(with_skill|without_skill|new_skill|old_skill)/);
|
|
717
|
+
if (configMatch) {
|
|
718
|
+
const config = configMatch[1];
|
|
719
|
+
const isBaseline = config === "without_skill" || config === "old_skill";
|
|
720
|
+
badge.textContent = config.replace(/_/g, " ");
|
|
721
|
+
badge.className = "config-badge " + (isBaseline ? "config-baseline" : "config-primary");
|
|
722
|
+
badge.style.display = "inline-block";
|
|
723
|
+
} else {
|
|
724
|
+
badge.style.display = "none";
|
|
725
|
+
}
|
|
726
|
+
|
|
727
|
+
// Outputs
|
|
728
|
+
renderOutputs(run);
|
|
729
|
+
|
|
730
|
+
// Previous outputs
|
|
731
|
+
renderPrevOutputs(run);
|
|
732
|
+
|
|
733
|
+
// Grades
|
|
734
|
+
renderGrades(run);
|
|
735
|
+
|
|
736
|
+
// Previous feedback
|
|
737
|
+
const prevFb = (EMBEDDED_DATA.previous_feedback || {})[run.id];
|
|
738
|
+
const prevEl = document.getElementById("prev-feedback");
|
|
739
|
+
if (prevFb) {
|
|
740
|
+
document.getElementById("prev-feedback-text").textContent = prevFb;
|
|
741
|
+
prevEl.style.display = "block";
|
|
742
|
+
} else {
|
|
743
|
+
prevEl.style.display = "none";
|
|
744
|
+
}
|
|
745
|
+
|
|
746
|
+
// Feedback
|
|
747
|
+
document.getElementById("feedback").value = feedbackMap[run.id] || "";
|
|
748
|
+
document.getElementById("feedback-status").textContent = "";
|
|
749
|
+
|
|
750
|
+
updateNavButtons();
|
|
751
|
+
|
|
752
|
+
// Track visited runs and promote done button when all visited
|
|
753
|
+
visitedRuns.add(index);
|
|
754
|
+
const doneBtn = document.getElementById("done-btn");
|
|
755
|
+
if (visitedRuns.size >= EMBEDDED_DATA.runs.length) {
|
|
756
|
+
doneBtn.classList.add("ready");
|
|
757
|
+
}
|
|
758
|
+
|
|
759
|
+
// Scroll main content to top
|
|
760
|
+
document.querySelector(".main").scrollTop = 0;
|
|
761
|
+
}
|
|
762
|
+
|
|
763
|
+
// ---- Render outputs ----
|
|
764
|
+
function renderOutputs(run) {
|
|
765
|
+
const container = document.getElementById("outputs-body");
|
|
766
|
+
container.innerHTML = "";
|
|
767
|
+
|
|
768
|
+
const outputs = run.outputs || [];
|
|
769
|
+
if (outputs.length === 0) {
|
|
770
|
+
container.innerHTML = '<div class="empty-state">No output files</div>';
|
|
771
|
+
return;
|
|
772
|
+
}
|
|
773
|
+
|
|
774
|
+
for (const file of outputs) {
|
|
775
|
+
const fileDiv = document.createElement("div");
|
|
776
|
+
fileDiv.className = "output-file";
|
|
777
|
+
|
|
778
|
+
// Always show file header with download link
|
|
779
|
+
const header = document.createElement("div");
|
|
780
|
+
header.className = "output-file-header";
|
|
781
|
+
const nameSpan = document.createElement("span");
|
|
782
|
+
nameSpan.textContent = file.name;
|
|
783
|
+
header.appendChild(nameSpan);
|
|
784
|
+
const dlBtn = document.createElement("a");
|
|
785
|
+
dlBtn.className = "dl-btn";
|
|
786
|
+
dlBtn.textContent = "Download";
|
|
787
|
+
dlBtn.download = file.name;
|
|
788
|
+
dlBtn.href = getDownloadUri(file);
|
|
789
|
+
header.appendChild(dlBtn);
|
|
790
|
+
fileDiv.appendChild(header);
|
|
791
|
+
|
|
792
|
+
const content = document.createElement("div");
|
|
793
|
+
content.className = "output-file-content";
|
|
794
|
+
|
|
795
|
+
if (file.type === "text") {
|
|
796
|
+
const pre = document.createElement("pre");
|
|
797
|
+
pre.textContent = file.content;
|
|
798
|
+
content.appendChild(pre);
|
|
799
|
+
} else if (file.type === "image") {
|
|
800
|
+
const img = document.createElement("img");
|
|
801
|
+
img.src = file.data_uri;
|
|
802
|
+
img.alt = file.name;
|
|
803
|
+
content.appendChild(img);
|
|
804
|
+
} else if (file.type === "pdf") {
|
|
805
|
+
const iframe = document.createElement("iframe");
|
|
806
|
+
iframe.src = file.data_uri;
|
|
807
|
+
content.appendChild(iframe);
|
|
808
|
+
} else if (file.type === "xlsx") {
|
|
809
|
+
renderXlsx(content, file.data_b64);
|
|
810
|
+
} else if (file.type === "binary") {
|
|
811
|
+
const a = document.createElement("a");
|
|
812
|
+
a.className = "download-link";
|
|
813
|
+
a.href = file.data_uri;
|
|
814
|
+
a.download = file.name;
|
|
815
|
+
a.textContent = "Download " + file.name;
|
|
816
|
+
content.appendChild(a);
|
|
817
|
+
} else if (file.type === "error") {
|
|
818
|
+
const pre = document.createElement("pre");
|
|
819
|
+
pre.textContent = file.content;
|
|
820
|
+
pre.style.color = "var(--red)";
|
|
821
|
+
content.appendChild(pre);
|
|
822
|
+
}
|
|
823
|
+
|
|
824
|
+
fileDiv.appendChild(content);
|
|
825
|
+
container.appendChild(fileDiv);
|
|
826
|
+
}
|
|
827
|
+
}
|
|
828
|
+
|
|
829
|
+
// ---- XLSX rendering via SheetJS ----
|
|
830
|
+
function renderXlsx(container, b64Data) {
|
|
831
|
+
try {
|
|
832
|
+
const raw = Uint8Array.from(atob(b64Data), c => c.charCodeAt(0));
|
|
833
|
+
const wb = XLSX.read(raw, { type: "array" });
|
|
834
|
+
|
|
835
|
+
for (let i = 0; i < wb.SheetNames.length; i++) {
|
|
836
|
+
const sheetName = wb.SheetNames[i];
|
|
837
|
+
const ws = wb.Sheets[sheetName];
|
|
838
|
+
|
|
839
|
+
if (wb.SheetNames.length > 1) {
|
|
840
|
+
const sheetLabel = document.createElement("div");
|
|
841
|
+
sheetLabel.style.cssText =
|
|
842
|
+
"font-weight:600; font-size:0.8rem; color:#b0aea5; margin-top:0.5rem; margin-bottom:0.25rem;";
|
|
843
|
+
sheetLabel.textContent = "Sheet: " + sheetName;
|
|
844
|
+
container.appendChild(sheetLabel);
|
|
845
|
+
}
|
|
846
|
+
|
|
847
|
+
const htmlStr = XLSX.utils.sheet_to_html(ws, { editable: false });
|
|
848
|
+
const wrapper = document.createElement("div");
|
|
849
|
+
wrapper.innerHTML = htmlStr;
|
|
850
|
+
container.appendChild(wrapper);
|
|
851
|
+
}
|
|
852
|
+
} catch (err) {
|
|
853
|
+
container.textContent = "Error rendering spreadsheet: " + err.message;
|
|
854
|
+
}
|
|
855
|
+
}
|
|
856
|
+
|
|
857
|
+
// ---- Grades ----
|
|
858
|
+
function renderGrades(run) {
|
|
859
|
+
const section = document.getElementById("grades-section");
|
|
860
|
+
const content = document.getElementById("grades-content");
|
|
861
|
+
|
|
862
|
+
if (!run.grading) {
|
|
863
|
+
section.style.display = "none";
|
|
864
|
+
return;
|
|
865
|
+
}
|
|
866
|
+
|
|
867
|
+
const grading = run.grading;
|
|
868
|
+
section.style.display = "block";
|
|
869
|
+
// Reset to collapsed
|
|
870
|
+
content.classList.remove("open");
|
|
871
|
+
document.getElementById("grades-arrow").classList.remove("open");
|
|
872
|
+
|
|
873
|
+
const summary = grading.summary || {};
|
|
874
|
+
const expectations = grading.expectations || [];
|
|
875
|
+
|
|
876
|
+
let html = '<div style="padding: 1rem;">';
|
|
877
|
+
|
|
878
|
+
// Summary line
|
|
879
|
+
const passRate = summary.pass_rate != null
|
|
880
|
+
? Math.round(summary.pass_rate * 100) + "%"
|
|
881
|
+
: "?";
|
|
882
|
+
const badgeClass = summary.pass_rate >= 0.8 ? "grade-pass" : summary.pass_rate >= 0.5 ? "" : "grade-fail";
|
|
883
|
+
html += '<div class="grades-summary">';
|
|
884
|
+
html += '<span class="grade-badge ' + badgeClass + '">' + passRate + '</span>';
|
|
885
|
+
html += '<span>' + (summary.passed || 0) + ' passed, ' + (summary.failed || 0) + ' failed of ' + (summary.total || 0) + '</span>';
|
|
886
|
+
html += '</div>';
|
|
887
|
+
|
|
888
|
+
// Assertions list
|
|
889
|
+
html += '<ul class="assertion-list">';
|
|
890
|
+
for (const exp of expectations) {
|
|
891
|
+
const statusClass = exp.passed ? "pass" : "fail";
|
|
892
|
+
const statusIcon = exp.passed ? "\u2713" : "\u2717";
|
|
893
|
+
html += '<li class="assertion-item">';
|
|
894
|
+
html += '<span class="assertion-status ' + statusClass + '">' + statusIcon + '</span>';
|
|
895
|
+
html += '<span>' + escapeHtml(exp.text) + '</span>';
|
|
896
|
+
if (exp.evidence) {
|
|
897
|
+
html += '<div class="assertion-evidence">' + escapeHtml(exp.evidence) + '</div>';
|
|
898
|
+
}
|
|
899
|
+
html += '</li>';
|
|
900
|
+
}
|
|
901
|
+
html += '</ul>';
|
|
902
|
+
|
|
903
|
+
html += '</div>';
|
|
904
|
+
content.innerHTML = html;
|
|
905
|
+
}
|
|
906
|
+
|
|
907
|
+
function toggleGrades() {
|
|
908
|
+
const content = document.getElementById("grades-content");
|
|
909
|
+
const arrow = document.getElementById("grades-arrow");
|
|
910
|
+
content.classList.toggle("open");
|
|
911
|
+
arrow.classList.toggle("open");
|
|
912
|
+
}
|
|
913
|
+
|
|
914
|
+
// ---- Previous outputs (collapsible) ----
|
|
915
|
+
function renderPrevOutputs(run) {
|
|
916
|
+
const section = document.getElementById("prev-outputs-section");
|
|
917
|
+
const content = document.getElementById("prev-outputs-content");
|
|
918
|
+
const prevOutputs = (EMBEDDED_DATA.previous_outputs || {})[run.id];
|
|
919
|
+
|
|
920
|
+
if (!prevOutputs || prevOutputs.length === 0) {
|
|
921
|
+
section.style.display = "none";
|
|
922
|
+
return;
|
|
923
|
+
}
|
|
924
|
+
|
|
925
|
+
section.style.display = "block";
|
|
926
|
+
// Reset to collapsed
|
|
927
|
+
content.classList.remove("open");
|
|
928
|
+
document.getElementById("prev-outputs-arrow").classList.remove("open");
|
|
929
|
+
|
|
930
|
+
// Render the files into the content area
|
|
931
|
+
content.innerHTML = "";
|
|
932
|
+
const wrapper = document.createElement("div");
|
|
933
|
+
wrapper.style.padding = "1rem";
|
|
934
|
+
|
|
935
|
+
for (const file of prevOutputs) {
|
|
936
|
+
const fileDiv = document.createElement("div");
|
|
937
|
+
fileDiv.className = "output-file";
|
|
938
|
+
|
|
939
|
+
const header = document.createElement("div");
|
|
940
|
+
header.className = "output-file-header";
|
|
941
|
+
const nameSpan = document.createElement("span");
|
|
942
|
+
nameSpan.textContent = file.name;
|
|
943
|
+
header.appendChild(nameSpan);
|
|
944
|
+
const dlBtn = document.createElement("a");
|
|
945
|
+
dlBtn.className = "dl-btn";
|
|
946
|
+
dlBtn.textContent = "Download";
|
|
947
|
+
dlBtn.download = file.name;
|
|
948
|
+
dlBtn.href = getDownloadUri(file);
|
|
949
|
+
header.appendChild(dlBtn);
|
|
950
|
+
fileDiv.appendChild(header);
|
|
951
|
+
|
|
952
|
+
const fc = document.createElement("div");
|
|
953
|
+
fc.className = "output-file-content";
|
|
954
|
+
|
|
955
|
+
if (file.type === "text") {
|
|
956
|
+
const pre = document.createElement("pre");
|
|
957
|
+
pre.textContent = file.content;
|
|
958
|
+
fc.appendChild(pre);
|
|
959
|
+
} else if (file.type === "image") {
|
|
960
|
+
const img = document.createElement("img");
|
|
961
|
+
img.src = file.data_uri;
|
|
962
|
+
img.alt = file.name;
|
|
963
|
+
fc.appendChild(img);
|
|
964
|
+
} else if (file.type === "pdf") {
|
|
965
|
+
const iframe = document.createElement("iframe");
|
|
966
|
+
iframe.src = file.data_uri;
|
|
967
|
+
fc.appendChild(iframe);
|
|
968
|
+
} else if (file.type === "xlsx") {
|
|
969
|
+
renderXlsx(fc, file.data_b64);
|
|
970
|
+
} else if (file.type === "binary") {
|
|
971
|
+
const a = document.createElement("a");
|
|
972
|
+
a.className = "download-link";
|
|
973
|
+
a.href = file.data_uri;
|
|
974
|
+
a.download = file.name;
|
|
975
|
+
a.textContent = "Download " + file.name;
|
|
976
|
+
fc.appendChild(a);
|
|
977
|
+
}
|
|
978
|
+
|
|
979
|
+
fileDiv.appendChild(fc);
|
|
980
|
+
wrapper.appendChild(fileDiv);
|
|
981
|
+
}
|
|
982
|
+
|
|
983
|
+
content.appendChild(wrapper);
|
|
984
|
+
}
|
|
985
|
+
|
|
986
|
+
function togglePrevOutputs() {
|
|
987
|
+
const content = document.getElementById("prev-outputs-content");
|
|
988
|
+
const arrow = document.getElementById("prev-outputs-arrow");
|
|
989
|
+
content.classList.toggle("open");
|
|
990
|
+
arrow.classList.toggle("open");
|
|
991
|
+
}
|
|
992
|
+
|
|
993
|
+
// ---- Feedback (saved to server -> feedback.json) ----
|
|
994
|
+
function saveCurrentFeedback() {
|
|
995
|
+
const run = EMBEDDED_DATA.runs[currentIndex];
|
|
996
|
+
const text = document.getElementById("feedback").value;
|
|
997
|
+
|
|
998
|
+
if (text.trim() === "") {
|
|
999
|
+
delete feedbackMap[run.id];
|
|
1000
|
+
} else {
|
|
1001
|
+
feedbackMap[run.id] = text;
|
|
1002
|
+
}
|
|
1003
|
+
|
|
1004
|
+
// Build reviews array from map
|
|
1005
|
+
const reviews = [];
|
|
1006
|
+
for (const [run_id, feedback] of Object.entries(feedbackMap)) {
|
|
1007
|
+
if (feedback.trim()) {
|
|
1008
|
+
reviews.push({ run_id, feedback, timestamp: new Date().toISOString() });
|
|
1009
|
+
}
|
|
1010
|
+
}
|
|
1011
|
+
|
|
1012
|
+
fetch("/api/feedback", {
|
|
1013
|
+
method: "POST",
|
|
1014
|
+
headers: { "Content-Type": "application/json" },
|
|
1015
|
+
body: JSON.stringify({ reviews, status: "in_progress" }),
|
|
1016
|
+
}).then(() => {
|
|
1017
|
+
document.getElementById("feedback-status").textContent = "Saved";
|
|
1018
|
+
}).catch(() => {
|
|
1019
|
+
// Static mode or server unavailable — no-op on auto-save,
|
|
1020
|
+
// feedback will be downloaded on final submit
|
|
1021
|
+
document.getElementById("feedback-status").textContent = "Will download on submit";
|
|
1022
|
+
});
|
|
1023
|
+
}
|
|
1024
|
+
|
|
1025
|
+
// ---- Done ----
|
|
1026
|
+
function showDoneDialog() {
|
|
1027
|
+
// Save current textarea to feedbackMap (but don't POST yet)
|
|
1028
|
+
const run = EMBEDDED_DATA.runs[currentIndex];
|
|
1029
|
+
const text = document.getElementById("feedback").value;
|
|
1030
|
+
if (text.trim() === "") {
|
|
1031
|
+
delete feedbackMap[run.id];
|
|
1032
|
+
} else {
|
|
1033
|
+
feedbackMap[run.id] = text;
|
|
1034
|
+
}
|
|
1035
|
+
|
|
1036
|
+
// POST once with status: complete — include ALL runs so the model
|
|
1037
|
+
// can distinguish "no feedback" (looks good) from "not reviewed"
|
|
1038
|
+
const reviews = [];
|
|
1039
|
+
const ts = new Date().toISOString();
|
|
1040
|
+
for (const r of EMBEDDED_DATA.runs) {
|
|
1041
|
+
reviews.push({ run_id: r.id, feedback: feedbackMap[r.id] || "", timestamp: ts });
|
|
1042
|
+
}
|
|
1043
|
+
const payload = JSON.stringify({ reviews, status: "complete" }, null, 2);
|
|
1044
|
+
fetch("/api/feedback", {
|
|
1045
|
+
method: "POST",
|
|
1046
|
+
headers: { "Content-Type": "application/json" },
|
|
1047
|
+
body: payload,
|
|
1048
|
+
}).then(() => {
|
|
1049
|
+
document.getElementById("done-overlay").classList.add("visible");
|
|
1050
|
+
}).catch(() => {
|
|
1051
|
+
// Server not available (static mode) — download as file
|
|
1052
|
+
const blob = new Blob([payload], { type: "application/json" });
|
|
1053
|
+
const url = URL.createObjectURL(blob);
|
|
1054
|
+
const a = document.createElement("a");
|
|
1055
|
+
a.href = url;
|
|
1056
|
+
a.download = "feedback.json";
|
|
1057
|
+
a.click();
|
|
1058
|
+
URL.revokeObjectURL(url);
|
|
1059
|
+
document.getElementById("done-overlay").classList.add("visible");
|
|
1060
|
+
});
|
|
1061
|
+
}
|
|
1062
|
+
|
|
1063
|
+
function closeDoneDialog() {
|
|
1064
|
+
// Reset status back to in_progress
|
|
1065
|
+
saveCurrentFeedback();
|
|
1066
|
+
document.getElementById("done-overlay").classList.remove("visible");
|
|
1067
|
+
}
|
|
1068
|
+
|
|
1069
|
+
// ---- Toast ----
|
|
1070
|
+
function showToast(message) {
|
|
1071
|
+
const toast = document.getElementById("toast");
|
|
1072
|
+
toast.textContent = message;
|
|
1073
|
+
toast.classList.add("visible");
|
|
1074
|
+
setTimeout(() => toast.classList.remove("visible"), 2000);
|
|
1075
|
+
}
|
|
1076
|
+
|
|
1077
|
+
// ---- Keyboard nav ----
|
|
1078
|
+
document.addEventListener("keydown", (e) => {
|
|
1079
|
+
// Don't capture when typing in textarea
|
|
1080
|
+
if (e.target.tagName === "TEXTAREA") return;
|
|
1081
|
+
|
|
1082
|
+
if (e.key === "ArrowLeft" || e.key === "ArrowUp") {
|
|
1083
|
+
e.preventDefault();
|
|
1084
|
+
navigate(-1);
|
|
1085
|
+
} else if (e.key === "ArrowRight" || e.key === "ArrowDown") {
|
|
1086
|
+
e.preventDefault();
|
|
1087
|
+
navigate(1);
|
|
1088
|
+
}
|
|
1089
|
+
});
|
|
1090
|
+
|
|
1091
|
+
// ---- Util ----
|
|
1092
|
+
function getDownloadUri(file) {
|
|
1093
|
+
if (file.data_uri) return file.data_uri;
|
|
1094
|
+
if (file.data_b64) return "data:application/octet-stream;base64," + file.data_b64;
|
|
1095
|
+
if (file.type === "text") return "data:text/plain;charset=utf-8," + encodeURIComponent(file.content);
|
|
1096
|
+
return "#";
|
|
1097
|
+
}
|
|
1098
|
+
|
|
1099
|
+
function escapeHtml(text) {
|
|
1100
|
+
const div = document.createElement("div");
|
|
1101
|
+
div.textContent = text;
|
|
1102
|
+
return div.innerHTML;
|
|
1103
|
+
}
|
|
1104
|
+
|
|
1105
|
+
// ---- View switching ----
|
|
1106
|
+
function switchView(view) {
|
|
1107
|
+
document.querySelectorAll(".view-tab").forEach(t => t.classList.remove("active"));
|
|
1108
|
+
document.querySelectorAll(".view-panel").forEach(p => p.classList.remove("active"));
|
|
1109
|
+
document.querySelector(`[onclick="switchView('${view}')"]`).classList.add("active");
|
|
1110
|
+
document.getElementById("panel-" + view).classList.add("active");
|
|
1111
|
+
}
|
|
1112
|
+
|
|
1113
|
+
// ---- Benchmark rendering ----
|
|
1114
|
+
function renderBenchmark() {
|
|
1115
|
+
const data = EMBEDDED_DATA.benchmark;
|
|
1116
|
+
if (!data) return;
|
|
1117
|
+
|
|
1118
|
+
// Show the tabs
|
|
1119
|
+
document.getElementById("view-tabs").style.display = "flex";
|
|
1120
|
+
|
|
1121
|
+
const container = document.getElementById("benchmark-content");
|
|
1122
|
+
const summary = data.run_summary || {};
|
|
1123
|
+
const metadata = data.metadata || {};
|
|
1124
|
+
const notes = data.notes || [];
|
|
1125
|
+
|
|
1126
|
+
let html = "";
|
|
1127
|
+
|
|
1128
|
+
// Header
|
|
1129
|
+
html += "<h2 style='font-family: Poppins, sans-serif; margin-bottom: 0.5rem;'>Benchmark Results</h2>";
|
|
1130
|
+
html += "<p style='color: var(--text-muted); font-size: 0.875rem; margin-bottom: 1.25rem;'>";
|
|
1131
|
+
if (metadata.skill_name) html += "<strong>" + escapeHtml(metadata.skill_name) + "</strong> — ";
|
|
1132
|
+
if (metadata.timestamp) html += metadata.timestamp + " — ";
|
|
1133
|
+
if (metadata.evals_run) html += "Evals: " + metadata.evals_run.join(", ") + " — ";
|
|
1134
|
+
html += (metadata.runs_per_configuration || "?") + " runs per configuration";
|
|
1135
|
+
html += "</p>";
|
|
1136
|
+
|
|
1137
|
+
// Summary table
|
|
1138
|
+
html += '<table class="benchmark-table">';
|
|
1139
|
+
|
|
1140
|
+
function fmtStat(stat, pct) {
|
|
1141
|
+
if (!stat) return "—";
|
|
1142
|
+
const suffix = pct ? "%" : "";
|
|
1143
|
+
const m = pct ? (stat.mean * 100).toFixed(0) : stat.mean.toFixed(1);
|
|
1144
|
+
const s = pct ? (stat.stddev * 100).toFixed(0) : stat.stddev.toFixed(1);
|
|
1145
|
+
return m + suffix + " ± " + s + suffix;
|
|
1146
|
+
}
|
|
1147
|
+
|
|
1148
|
+
function deltaClass(val) {
|
|
1149
|
+
if (!val) return "";
|
|
1150
|
+
const n = parseFloat(val);
|
|
1151
|
+
if (n > 0) return "benchmark-delta-positive";
|
|
1152
|
+
if (n < 0) return "benchmark-delta-negative";
|
|
1153
|
+
return "";
|
|
1154
|
+
}
|
|
1155
|
+
|
|
1156
|
+
// Discover config names dynamically (everything except "delta")
|
|
1157
|
+
const configs = Object.keys(summary).filter(k => k !== "delta");
|
|
1158
|
+
const configA = configs[0] || "config_a";
|
|
1159
|
+
const configB = configs[1] || "config_b";
|
|
1160
|
+
const labelA = configA.replace(/_/g, " ").replace(/\b\w/g, c => c.toUpperCase());
|
|
1161
|
+
const labelB = configB.replace(/_/g, " ").replace(/\b\w/g, c => c.toUpperCase());
|
|
1162
|
+
const a = summary[configA] || {};
|
|
1163
|
+
const b = summary[configB] || {};
|
|
1164
|
+
const delta = summary.delta || {};
|
|
1165
|
+
|
|
1166
|
+
html += "<thead><tr><th>Metric</th><th>" + escapeHtml(labelA) + "</th><th>" + escapeHtml(labelB) + "</th><th>Delta</th></tr></thead>";
|
|
1167
|
+
html += "<tbody>";
|
|
1168
|
+
|
|
1169
|
+
html += "<tr><td><strong>Pass Rate</strong></td>";
|
|
1170
|
+
html += "<td>" + fmtStat(a.pass_rate, true) + "</td>";
|
|
1171
|
+
html += "<td>" + fmtStat(b.pass_rate, true) + "</td>";
|
|
1172
|
+
html += '<td class="' + deltaClass(delta.pass_rate) + '">' + (delta.pass_rate || "—") + "</td></tr>";
|
|
1173
|
+
|
|
1174
|
+
// Time (only show row if data exists)
|
|
1175
|
+
if (a.time_seconds || b.time_seconds) {
|
|
1176
|
+
html += "<tr><td><strong>Time (s)</strong></td>";
|
|
1177
|
+
html += "<td>" + fmtStat(a.time_seconds, false) + "</td>";
|
|
1178
|
+
html += "<td>" + fmtStat(b.time_seconds, false) + "</td>";
|
|
1179
|
+
html += '<td class="' + deltaClass(delta.time_seconds) + '">' + (delta.time_seconds ? delta.time_seconds + "s" : "—") + "</td></tr>";
|
|
1180
|
+
}
|
|
1181
|
+
|
|
1182
|
+
// Tokens (only show row if data exists)
|
|
1183
|
+
if (a.tokens || b.tokens) {
|
|
1184
|
+
html += "<tr><td><strong>Tokens</strong></td>";
|
|
1185
|
+
html += "<td>" + fmtStat(a.tokens, false) + "</td>";
|
|
1186
|
+
html += "<td>" + fmtStat(b.tokens, false) + "</td>";
|
|
1187
|
+
html += '<td class="' + deltaClass(delta.tokens) + '">' + (delta.tokens || "—") + "</td></tr>";
|
|
1188
|
+
}
|
|
1189
|
+
|
|
1190
|
+
html += "</tbody></table>";
|
|
1191
|
+
|
|
1192
|
+
// Per-eval breakdown (if runs data available)
|
|
1193
|
+
const runs = data.runs || [];
|
|
1194
|
+
if (runs.length > 0) {
|
|
1195
|
+
const evalIds = [...new Set(runs.map(r => r.eval_id))].sort((a, b) => a - b);
|
|
1196
|
+
|
|
1197
|
+
html += "<h3 style='font-family: Poppins, sans-serif; margin-bottom: 0.75rem;'>Per-Eval Breakdown</h3>";
|
|
1198
|
+
|
|
1199
|
+
const hasTime = runs.some(r => r.result && r.result.time_seconds != null);
|
|
1200
|
+
const hasErrors = runs.some(r => r.result && r.result.errors > 0);
|
|
1201
|
+
|
|
1202
|
+
for (const evalId of evalIds) {
|
|
1203
|
+
const evalRuns = runs.filter(r => r.eval_id === evalId);
|
|
1204
|
+
const evalName = evalRuns[0] && evalRuns[0].eval_name ? evalRuns[0].eval_name : "Eval " + evalId;
|
|
1205
|
+
|
|
1206
|
+
html += "<h4 style='font-family: Poppins, sans-serif; margin: 1rem 0 0.5rem; color: var(--text);'>" + escapeHtml(evalName) + "</h4>";
|
|
1207
|
+
html += '<table class="benchmark-table">';
|
|
1208
|
+
html += "<thead><tr><th>Config</th><th>Run</th><th>Pass Rate</th>";
|
|
1209
|
+
if (hasTime) html += "<th>Time (s)</th>";
|
|
1210
|
+
if (hasErrors) html += "<th>Crashes During Execution</th>";
|
|
1211
|
+
html += "</tr></thead>";
|
|
1212
|
+
html += "<tbody>";
|
|
1213
|
+
|
|
1214
|
+
// Group by config and render with average rows
|
|
1215
|
+
const configGroups = [...new Set(evalRuns.map(r => r.configuration))];
|
|
1216
|
+
for (let ci = 0; ci < configGroups.length; ci++) {
|
|
1217
|
+
const config = configGroups[ci];
|
|
1218
|
+
const configRuns = evalRuns.filter(r => r.configuration === config);
|
|
1219
|
+
if (configRuns.length === 0) continue;
|
|
1220
|
+
|
|
1221
|
+
const rowClass = ci === 0 ? "benchmark-row-with" : "benchmark-row-without";
|
|
1222
|
+
const configLabel = config.replace(/_/g, " ").replace(/\b\w/g, c => c.toUpperCase());
|
|
1223
|
+
|
|
1224
|
+
for (const run of configRuns) {
|
|
1225
|
+
const r = run.result || {};
|
|
1226
|
+
const prClass = r.pass_rate >= 0.8 ? "benchmark-delta-positive" : r.pass_rate < 0.5 ? "benchmark-delta-negative" : "";
|
|
1227
|
+
html += '<tr class="' + rowClass + '">';
|
|
1228
|
+
html += "<td>" + configLabel + "</td>";
|
|
1229
|
+
html += "<td>" + run.run_number + "</td>";
|
|
1230
|
+
html += '<td class="' + prClass + '">' + ((r.pass_rate || 0) * 100).toFixed(0) + "% (" + (r.passed || 0) + "/" + (r.total || 0) + ")</td>";
|
|
1231
|
+
if (hasTime) html += "<td>" + (r.time_seconds != null ? r.time_seconds.toFixed(1) : "—") + "</td>";
|
|
1232
|
+
if (hasErrors) html += "<td>" + (r.errors || 0) + "</td>";
|
|
1233
|
+
html += "</tr>";
|
|
1234
|
+
}
|
|
1235
|
+
|
|
1236
|
+
// Average row
|
|
1237
|
+
const rates = configRuns.map(r => (r.result || {}).pass_rate || 0);
|
|
1238
|
+
const avgRate = rates.reduce((a, b) => a + b, 0) / rates.length;
|
|
1239
|
+
const avgPrClass = avgRate >= 0.8 ? "benchmark-delta-positive" : avgRate < 0.5 ? "benchmark-delta-negative" : "";
|
|
1240
|
+
html += '<tr class="benchmark-row-avg ' + rowClass + '">';
|
|
1241
|
+
html += "<td>" + configLabel + "</td>";
|
|
1242
|
+
html += "<td>Avg</td>";
|
|
1243
|
+
html += '<td class="' + avgPrClass + '">' + (avgRate * 100).toFixed(0) + "%</td>";
|
|
1244
|
+
if (hasTime) {
|
|
1245
|
+
const times = configRuns.map(r => (r.result || {}).time_seconds).filter(t => t != null);
|
|
1246
|
+
html += "<td>" + (times.length ? (times.reduce((a, b) => a + b, 0) / times.length).toFixed(1) : "—") + "</td>";
|
|
1247
|
+
}
|
|
1248
|
+
if (hasErrors) html += "<td></td>";
|
|
1249
|
+
html += "</tr>";
|
|
1250
|
+
}
|
|
1251
|
+
html += "</tbody></table>";
|
|
1252
|
+
|
|
1253
|
+
// Per-assertion detail for this eval
|
|
1254
|
+
const runsWithExpectations = {};
|
|
1255
|
+
for (const config of configGroups) {
|
|
1256
|
+
runsWithExpectations[config] = evalRuns.filter(r => r.configuration === config && r.expectations && r.expectations.length > 0);
|
|
1257
|
+
}
|
|
1258
|
+
const hasAnyExpectations = Object.values(runsWithExpectations).some(runs => runs.length > 0);
|
|
1259
|
+
if (hasAnyExpectations) {
|
|
1260
|
+
// Collect all unique assertion texts across all configs
|
|
1261
|
+
const allAssertions = [];
|
|
1262
|
+
const seen = new Set();
|
|
1263
|
+
for (const config of configGroups) {
|
|
1264
|
+
for (const run of runsWithExpectations[config]) {
|
|
1265
|
+
for (const exp of (run.expectations || [])) {
|
|
1266
|
+
if (!seen.has(exp.text)) {
|
|
1267
|
+
seen.add(exp.text);
|
|
1268
|
+
allAssertions.push(exp.text);
|
|
1269
|
+
}
|
|
1270
|
+
}
|
|
1271
|
+
}
|
|
1272
|
+
}
|
|
1273
|
+
|
|
1274
|
+
html += '<table class="benchmark-table" style="margin-top: 0.5rem;">';
|
|
1275
|
+
html += "<thead><tr><th>Assertion</th>";
|
|
1276
|
+
for (const config of configGroups) {
|
|
1277
|
+
const label = config.replace(/_/g, " ").replace(/\b\w/g, c => c.toUpperCase());
|
|
1278
|
+
html += "<th>" + escapeHtml(label) + "</th>";
|
|
1279
|
+
}
|
|
1280
|
+
html += "</tr></thead><tbody>";
|
|
1281
|
+
|
|
1282
|
+
for (const assertionText of allAssertions) {
|
|
1283
|
+
html += "<tr><td>" + escapeHtml(assertionText) + "</td>";
|
|
1284
|
+
|
|
1285
|
+
for (const config of configGroups) {
|
|
1286
|
+
html += "<td>";
|
|
1287
|
+
for (const run of runsWithExpectations[config]) {
|
|
1288
|
+
const exp = (run.expectations || []).find(e => e.text === assertionText);
|
|
1289
|
+
if (exp) {
|
|
1290
|
+
const cls = exp.passed ? "benchmark-delta-positive" : "benchmark-delta-negative";
|
|
1291
|
+
const icon = exp.passed ? "\u2713" : "\u2717";
|
|
1292
|
+
html += '<span class="' + cls + '" title="Run ' + run.run_number + ': ' + escapeHtml(exp.evidence || "") + '">' + icon + "</span> ";
|
|
1293
|
+
} else {
|
|
1294
|
+
html += "— ";
|
|
1295
|
+
}
|
|
1296
|
+
}
|
|
1297
|
+
html += "</td>";
|
|
1298
|
+
}
|
|
1299
|
+
html += "</tr>";
|
|
1300
|
+
}
|
|
1301
|
+
html += "</tbody></table>";
|
|
1302
|
+
}
|
|
1303
|
+
}
|
|
1304
|
+
}
|
|
1305
|
+
|
|
1306
|
+
// Notes
|
|
1307
|
+
if (notes.length > 0) {
|
|
1308
|
+
html += '<div class="benchmark-notes">';
|
|
1309
|
+
html += "<h3>Analysis Notes</h3>";
|
|
1310
|
+
html += "<ul>";
|
|
1311
|
+
for (const note of notes) {
|
|
1312
|
+
html += "<li>" + escapeHtml(note) + "</li>";
|
|
1313
|
+
}
|
|
1314
|
+
html += "</ul></div>";
|
|
1315
|
+
}
|
|
1316
|
+
|
|
1317
|
+
container.innerHTML = html;
|
|
1318
|
+
}
|
|
1319
|
+
|
|
1320
|
+
// ---- Start ----
|
|
1321
|
+
init();
|
|
1322
|
+
renderBenchmark();
|
|
1323
|
+
</script>
|
|
1324
|
+
</body>
|
|
1325
|
+
</html>
|