gsd-trae 1.0.0 → 1.0.2
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/CHANGELOG.md +40 -0
- package/README.md +7 -76
- package/assets/screenshot.png +0 -0
- package/package.json +12 -3
- package/.claude/settings.local.json +0 -8
- package/.gitmodules +0 -6
- package/.trae/project_rules.md +0 -56
- package/.trae/rules/project_rules.md +0 -56
- package/.vscode/code-counter/code-counter.db +0 -0
- package/.vscode/settings.json +0 -5
- package/refs/gsd/.github/CODEOWNERS +0 -2
- package/refs/gsd/.github/FUNDING.yml +0 -1
- package/refs/gsd/.github/ISSUE_TEMPLATE/bug_report.yml +0 -59
- package/refs/gsd/.github/ISSUE_TEMPLATE/feature_request.yml +0 -37
- package/refs/gsd/.github/pull_request_template.md +0 -24
- package/refs/gsd/.github/workflows/auto-label-issues.yml +0 -21
- package/refs/gsd/CHANGELOG.md +0 -1520
- package/refs/gsd/LICENSE +0 -21
- package/refs/gsd/README.md +0 -704
- package/refs/gsd/SECURITY.md +0 -33
- package/refs/gsd/agents/gsd-codebase-mapper.md +0 -764
- package/refs/gsd/agents/gsd-debugger.md +0 -1246
- package/refs/gsd/agents/gsd-executor.md +0 -469
- package/refs/gsd/agents/gsd-integration-checker.md +0 -443
- package/refs/gsd/agents/gsd-phase-researcher.md +0 -546
- package/refs/gsd/agents/gsd-plan-checker.md +0 -690
- package/refs/gsd/agents/gsd-planner.md +0 -1275
- package/refs/gsd/agents/gsd-project-researcher.md +0 -621
- package/refs/gsd/agents/gsd-research-synthesizer.md +0 -239
- package/refs/gsd/agents/gsd-roadmapper.md +0 -642
- package/refs/gsd/agents/gsd-verifier.md +0 -573
- package/refs/gsd/assets/gsd-logo-2000-transparent.png +0 -0
- package/refs/gsd/assets/gsd-logo-2000-transparent.svg +0 -17
- package/refs/gsd/assets/gsd-logo-2000.png +0 -0
- package/refs/gsd/assets/gsd-logo-2000.svg +0 -21
- package/refs/gsd/assets/terminal.svg +0 -68
- package/refs/gsd/bin/install.js +0 -2090
- package/refs/gsd/commands/gsd/add-phase.md +0 -43
- package/refs/gsd/commands/gsd/add-tests.md +0 -41
- package/refs/gsd/commands/gsd/add-todo.md +0 -47
- package/refs/gsd/commands/gsd/audit-milestone.md +0 -36
- package/refs/gsd/commands/gsd/check-todos.md +0 -45
- package/refs/gsd/commands/gsd/cleanup.md +0 -18
- package/refs/gsd/commands/gsd/complete-milestone.md +0 -136
- package/refs/gsd/commands/gsd/debug.md +0 -167
- package/refs/gsd/commands/gsd/discuss-phase.md +0 -83
- package/refs/gsd/commands/gsd/execute-phase.md +0 -41
- package/refs/gsd/commands/gsd/health.md +0 -22
- package/refs/gsd/commands/gsd/help.md +0 -22
- package/refs/gsd/commands/gsd/insert-phase.md +0 -32
- package/refs/gsd/commands/gsd/join-discord.md +0 -18
- package/refs/gsd/commands/gsd/list-phase-assumptions.md +0 -46
- package/refs/gsd/commands/gsd/map-codebase.md +0 -71
- package/refs/gsd/commands/gsd/new-milestone.md +0 -44
- package/refs/gsd/commands/gsd/new-project.md +0 -42
- package/refs/gsd/commands/gsd/new-project.md.bak +0 -1041
- package/refs/gsd/commands/gsd/pause-work.md +0 -38
- package/refs/gsd/commands/gsd/plan-milestone-gaps.md +0 -34
- package/refs/gsd/commands/gsd/plan-phase.md +0 -45
- package/refs/gsd/commands/gsd/progress.md +0 -24
- package/refs/gsd/commands/gsd/quick.md +0 -41
- package/refs/gsd/commands/gsd/reapply-patches.md +0 -110
- package/refs/gsd/commands/gsd/remove-phase.md +0 -31
- package/refs/gsd/commands/gsd/research-phase.md +0 -189
- package/refs/gsd/commands/gsd/resume-work.md +0 -40
- package/refs/gsd/commands/gsd/set-profile.md +0 -34
- package/refs/gsd/commands/gsd/settings.md +0 -36
- package/refs/gsd/commands/gsd/update.md +0 -37
- package/refs/gsd/commands/gsd/verify-work.md +0 -38
- package/refs/gsd/docs/USER-GUIDE.md +0 -471
- package/refs/gsd/docs/context-monitor.md +0 -96
- package/refs/gsd/get-shit-done/bin/gsd-tools.cjs +0 -585
- package/refs/gsd/get-shit-done/bin/lib/commands.cjs +0 -553
- package/refs/gsd/get-shit-done/bin/lib/config.cjs +0 -162
- package/refs/gsd/get-shit-done/bin/lib/core.cjs +0 -411
- package/refs/gsd/get-shit-done/bin/lib/frontmatter.cjs +0 -299
- package/refs/gsd/get-shit-done/bin/lib/init.cjs +0 -710
- package/refs/gsd/get-shit-done/bin/lib/milestone.cjs +0 -215
- package/refs/gsd/get-shit-done/bin/lib/phase.cjs +0 -870
- package/refs/gsd/get-shit-done/bin/lib/roadmap.cjs +0 -298
- package/refs/gsd/get-shit-done/bin/lib/state.cjs +0 -521
- package/refs/gsd/get-shit-done/bin/lib/template.cjs +0 -222
- package/refs/gsd/get-shit-done/bin/lib/verify.cjs +0 -772
- package/refs/gsd/get-shit-done/references/checkpoints.md +0 -776
- package/refs/gsd/get-shit-done/references/continuation-format.md +0 -249
- package/refs/gsd/get-shit-done/references/decimal-phase-calculation.md +0 -65
- package/refs/gsd/get-shit-done/references/git-integration.md +0 -248
- package/refs/gsd/get-shit-done/references/git-planning-commit.md +0 -38
- package/refs/gsd/get-shit-done/references/model-profile-resolution.md +0 -34
- package/refs/gsd/get-shit-done/references/model-profiles.md +0 -92
- package/refs/gsd/get-shit-done/references/phase-argument-parsing.md +0 -61
- package/refs/gsd/get-shit-done/references/planning-config.md +0 -196
- package/refs/gsd/get-shit-done/references/questioning.md +0 -145
- package/refs/gsd/get-shit-done/references/tdd.md +0 -263
- package/refs/gsd/get-shit-done/references/ui-brand.md +0 -160
- package/refs/gsd/get-shit-done/references/verification-patterns.md +0 -612
- package/refs/gsd/get-shit-done/templates/DEBUG.md +0 -164
- package/refs/gsd/get-shit-done/templates/UAT.md +0 -247
- package/refs/gsd/get-shit-done/templates/VALIDATION.md +0 -76
- package/refs/gsd/get-shit-done/templates/codebase/architecture.md +0 -255
- package/refs/gsd/get-shit-done/templates/codebase/concerns.md +0 -310
- package/refs/gsd/get-shit-done/templates/codebase/conventions.md +0 -307
- package/refs/gsd/get-shit-done/templates/codebase/integrations.md +0 -280
- package/refs/gsd/get-shit-done/templates/codebase/stack.md +0 -186
- package/refs/gsd/get-shit-done/templates/codebase/structure.md +0 -285
- package/refs/gsd/get-shit-done/templates/codebase/testing.md +0 -480
- package/refs/gsd/get-shit-done/templates/config.json +0 -37
- package/refs/gsd/get-shit-done/templates/context.md +0 -283
- package/refs/gsd/get-shit-done/templates/continue-here.md +0 -78
- package/refs/gsd/get-shit-done/templates/debug-subagent-prompt.md +0 -91
- package/refs/gsd/get-shit-done/templates/discovery.md +0 -146
- package/refs/gsd/get-shit-done/templates/milestone-archive.md +0 -123
- package/refs/gsd/get-shit-done/templates/milestone.md +0 -115
- package/refs/gsd/get-shit-done/templates/phase-prompt.md +0 -569
- package/refs/gsd/get-shit-done/templates/planner-subagent-prompt.md +0 -117
- package/refs/gsd/get-shit-done/templates/project.md +0 -184
- package/refs/gsd/get-shit-done/templates/requirements.md +0 -231
- package/refs/gsd/get-shit-done/templates/research-project/ARCHITECTURE.md +0 -204
- package/refs/gsd/get-shit-done/templates/research-project/FEATURES.md +0 -147
- package/refs/gsd/get-shit-done/templates/research-project/PITFALLS.md +0 -200
- package/refs/gsd/get-shit-done/templates/research-project/STACK.md +0 -120
- package/refs/gsd/get-shit-done/templates/research-project/SUMMARY.md +0 -170
- package/refs/gsd/get-shit-done/templates/research.md +0 -552
- package/refs/gsd/get-shit-done/templates/retrospective.md +0 -54
- package/refs/gsd/get-shit-done/templates/roadmap.md +0 -202
- package/refs/gsd/get-shit-done/templates/state.md +0 -176
- package/refs/gsd/get-shit-done/templates/summary-complex.md +0 -59
- package/refs/gsd/get-shit-done/templates/summary-minimal.md +0 -41
- package/refs/gsd/get-shit-done/templates/summary-standard.md +0 -48
- package/refs/gsd/get-shit-done/templates/summary.md +0 -248
- package/refs/gsd/get-shit-done/templates/user-setup.md +0 -311
- package/refs/gsd/get-shit-done/templates/verification-report.md +0 -322
- package/refs/gsd/get-shit-done/workflows/add-phase.md +0 -111
- package/refs/gsd/get-shit-done/workflows/add-tests.md +0 -350
- package/refs/gsd/get-shit-done/workflows/add-todo.md +0 -157
- package/refs/gsd/get-shit-done/workflows/audit-milestone.md +0 -297
- package/refs/gsd/get-shit-done/workflows/check-todos.md +0 -176
- package/refs/gsd/get-shit-done/workflows/cleanup.md +0 -152
- package/refs/gsd/get-shit-done/workflows/complete-milestone.md +0 -763
- package/refs/gsd/get-shit-done/workflows/diagnose-issues.md +0 -219
- package/refs/gsd/get-shit-done/workflows/discovery-phase.md +0 -289
- package/refs/gsd/get-shit-done/workflows/discuss-phase.md +0 -542
- package/refs/gsd/get-shit-done/workflows/execute-phase.md +0 -449
- package/refs/gsd/get-shit-done/workflows/execute-plan.md +0 -448
- package/refs/gsd/get-shit-done/workflows/health.md +0 -156
- package/refs/gsd/get-shit-done/workflows/help.md +0 -489
- package/refs/gsd/get-shit-done/workflows/insert-phase.md +0 -129
- package/refs/gsd/get-shit-done/workflows/list-phase-assumptions.md +0 -178
- package/refs/gsd/get-shit-done/workflows/map-codebase.md +0 -315
- package/refs/gsd/get-shit-done/workflows/new-milestone.md +0 -382
- package/refs/gsd/get-shit-done/workflows/new-project.md +0 -1116
- package/refs/gsd/get-shit-done/workflows/pause-work.md +0 -122
- package/refs/gsd/get-shit-done/workflows/plan-milestone-gaps.md +0 -274
- package/refs/gsd/get-shit-done/workflows/plan-phase.md +0 -569
- package/refs/gsd/get-shit-done/workflows/progress.md +0 -381
- package/refs/gsd/get-shit-done/workflows/quick.md +0 -453
- package/refs/gsd/get-shit-done/workflows/remove-phase.md +0 -154
- package/refs/gsd/get-shit-done/workflows/research-phase.md +0 -73
- package/refs/gsd/get-shit-done/workflows/resume-project.md +0 -306
- package/refs/gsd/get-shit-done/workflows/set-profile.md +0 -80
- package/refs/gsd/get-shit-done/workflows/settings.md +0 -213
- package/refs/gsd/get-shit-done/workflows/transition.md +0 -544
- package/refs/gsd/get-shit-done/workflows/update.md +0 -219
- package/refs/gsd/get-shit-done/workflows/verify-phase.md +0 -242
- package/refs/gsd/get-shit-done/workflows/verify-work.md +0 -569
- package/refs/gsd/hooks/gsd-check-update.js +0 -62
- package/refs/gsd/hooks/gsd-context-monitor.js +0 -122
- package/refs/gsd/hooks/gsd-statusline.js +0 -108
- package/refs/gsd/package.json +0 -50
- package/refs/gsd/scripts/build-hooks.js +0 -43
- package/refs/gsd/tests/commands.test.cjs +0 -661
- package/refs/gsd/tests/helpers.cjs +0 -40
- package/refs/gsd/tests/init.test.cjs +0 -205
- package/refs/gsd/tests/milestone.test.cjs +0 -98
- package/refs/gsd/tests/phase.test.cjs +0 -1241
- package/refs/gsd/tests/roadmap.test.cjs +0 -265
- package/refs/gsd/tests/state.test.cjs +0 -302
- package/refs/gsd/tests/verify.test.cjs +0 -80
- package/refs/vbenchmark/.agent/agents/codebase-explorer.md +0 -224
- package/refs/vbenchmark/.agent/agents/debugger.md +0 -180
- package/refs/vbenchmark/.agent/agents/documenter.md +0 -166
- package/refs/vbenchmark/.agent/agents/implementer.md +0 -70
- package/refs/vbenchmark/.agent/agents/orchestrator.md +0 -212
- package/refs/vbenchmark/.agent/agents/researcher.md +0 -80
- package/refs/vbenchmark/.agent/agents/reviewer.md +0 -184
- package/refs/vbenchmark/.agent/agents/tester.md +0 -170
- package/refs/vbenchmark/.agent/commands/commit.md +0 -29
- package/refs/vbenchmark/.agent/commands/debug.md +0 -59
- package/refs/vbenchmark/.agent/commands/document.md +0 -52
- package/refs/vbenchmark/.agent/commands/gather-context.md +0 -58
- package/refs/vbenchmark/.agent/commands/init.md +0 -56
- package/refs/vbenchmark/.agent/commands/preset-help.md +0 -50
- package/refs/vbenchmark/.agent/commands/refactor.md +0 -71
- package/refs/vbenchmark/.agent/commands/research.md +0 -37
- package/refs/vbenchmark/.agent/commands/review.md +0 -38
- package/refs/vbenchmark/.agent/commands/test.md +0 -61
- package/refs/vbenchmark/.agent/rules/01-code-quality.md +0 -33
- package/refs/vbenchmark/.agent/rules/02-typescript-go.md +0 -46
- package/refs/vbenchmark/.agent/rules/03-security-git.md +0 -34
- package/refs/vbenchmark/.agent/rules/04-architecture.md +0 -40
- package/refs/vbenchmark/.agent/sync.js +0 -536
- package/refs/vbenchmark/.agent/workflows/commit.md +0 -29
- package/refs/vbenchmark/.agent/workflows/debug.md +0 -59
- package/refs/vbenchmark/.agent/workflows/document.md +0 -52
- package/refs/vbenchmark/.agent/workflows/gather-context.md +0 -58
- package/refs/vbenchmark/.agent/workflows/init.md +0 -56
- package/refs/vbenchmark/.agent/workflows/preset-help.md +0 -50
- package/refs/vbenchmark/.agent/workflows/refactor.md +0 -71
- package/refs/vbenchmark/.agent/workflows/research.md +0 -37
- package/refs/vbenchmark/.agent/workflows/review.md +0 -38
- package/refs/vbenchmark/.agent/workflows/test.md +0 -61
- package/refs/vbenchmark/.claude/commands/agentic-dev/apply.md +0 -222
- package/refs/vbenchmark/.claude/commands/agentic-dev/done.md +0 -166
- package/refs/vbenchmark/.claude/commands/agentic-dev/proposal.md +0 -220
- package/refs/vbenchmark/.claude/commands/openspec/apply.md +0 -23
- package/refs/vbenchmark/.claude/commands/openspec/archive.md +0 -27
- package/refs/vbenchmark/.claude/commands/openspec/proposal.md +0 -28
- package/refs/vbenchmark/.clinerules/01-rules.md +0 -73
- package/refs/vbenchmark/.clinerules/02-agents.md +0 -34
- package/refs/vbenchmark/.cursor/commands/commit.md +0 -29
- package/refs/vbenchmark/.cursor/commands/debug.md +0 -59
- package/refs/vbenchmark/.cursor/commands/document.md +0 -52
- package/refs/vbenchmark/.cursor/commands/gather-context.md +0 -58
- package/refs/vbenchmark/.cursor/commands/init.md +0 -56
- package/refs/vbenchmark/.cursor/commands/preset-help.md +0 -50
- package/refs/vbenchmark/.cursor/commands/refactor.md +0 -71
- package/refs/vbenchmark/.cursor/commands/research.md +0 -37
- package/refs/vbenchmark/.cursor/commands/review.md +0 -38
- package/refs/vbenchmark/.cursor/commands/test.md +0 -61
- package/refs/vbenchmark/.cursor/rules/agents.mdc +0 -1357
- package/refs/vbenchmark/.factory/droids/codebase-explorer.md +0 -224
- package/refs/vbenchmark/.factory/droids/debugger.md +0 -180
- package/refs/vbenchmark/.factory/droids/documenter.md +0 -166
- package/refs/vbenchmark/.factory/droids/implementer.md +0 -70
- package/refs/vbenchmark/.factory/droids/orchestrator.md +0 -212
- package/refs/vbenchmark/.factory/droids/researcher.md +0 -80
- package/refs/vbenchmark/.factory/droids/reviewer.md +0 -184
- package/refs/vbenchmark/.factory/droids/tester.md +0 -170
- package/refs/vbenchmark/.gemini/workflows/commit.md +0 -29
- package/refs/vbenchmark/.gemini/workflows/debug.md +0 -59
- package/refs/vbenchmark/.gemini/workflows/document.md +0 -52
- package/refs/vbenchmark/.gemini/workflows/gather-context.md +0 -58
- package/refs/vbenchmark/.gemini/workflows/init.md +0 -56
- package/refs/vbenchmark/.gemini/workflows/preset-help.md +0 -50
- package/refs/vbenchmark/.gemini/workflows/refactor.md +0 -71
- package/refs/vbenchmark/.gemini/workflows/research.md +0 -37
- package/refs/vbenchmark/.gemini/workflows/review.md +0 -38
- package/refs/vbenchmark/.gemini/workflows/test.md +0 -61
- package/refs/vbenchmark/.github/CODEOWNERS +0 -20
- package/refs/vbenchmark/.github/FUNDING.yml +0 -4
- package/refs/vbenchmark/.github/ISSUE_TEMPLATE/bug-report.yml +0 -76
- package/refs/vbenchmark/.github/ISSUE_TEMPLATE/new-task.yml +0 -106
- package/refs/vbenchmark/.github/PULL_REQUEST_TEMPLATE.md +0 -38
- package/refs/vbenchmark/.github/copilot-instructions.md +0 -73
- package/refs/vbenchmark/.github/workflows/ci.yaml +0 -33
- package/refs/vbenchmark/.github/workflows/vercel-auto-pr.yml +0 -478
- package/refs/vbenchmark/.github/workflows/vercel-deploy.yaml +0 -487
- package/refs/vbenchmark/.github/workflows/vercel-pr-command.yaml +0 -337
- package/refs/vbenchmark/.github/workflows/vercel-project-init.yaml +0 -208
- package/refs/vbenchmark/.opencode/agent/codebase-explorer.md +0 -224
- package/refs/vbenchmark/.opencode/agent/debugger.md +0 -180
- package/refs/vbenchmark/.opencode/agent/documenter.md +0 -166
- package/refs/vbenchmark/.opencode/agent/implementer.md +0 -70
- package/refs/vbenchmark/.opencode/agent/orchestrator.md +0 -212
- package/refs/vbenchmark/.opencode/agent/researcher.md +0 -80
- package/refs/vbenchmark/.opencode/agent/reviewer.md +0 -184
- package/refs/vbenchmark/.opencode/agent/tester.md +0 -170
- package/refs/vbenchmark/.opencode/command/commit.md +0 -29
- package/refs/vbenchmark/.opencode/command/debug.md +0 -59
- package/refs/vbenchmark/.opencode/command/document.md +0 -52
- package/refs/vbenchmark/.opencode/command/gather-context.md +0 -58
- package/refs/vbenchmark/.opencode/command/init.md +0 -56
- package/refs/vbenchmark/.opencode/command/preset-help.md +0 -50
- package/refs/vbenchmark/.opencode/command/refactor.md +0 -71
- package/refs/vbenchmark/.opencode/command/research.md +0 -37
- package/refs/vbenchmark/.opencode/command/review.md +0 -38
- package/refs/vbenchmark/.opencode/command/test.md +0 -61
- package/refs/vbenchmark/.trae/project_rules.md +0 -73
- package/refs/vbenchmark/.windsurf/rules/rules.md +0 -85
- package/refs/vbenchmark/AGENTS.md +0 -73
- package/refs/vbenchmark/CONTRIBUTING.md +0 -332
- package/refs/vbenchmark/Caddyfile +0 -3
- package/refs/vbenchmark/LICENSE +0 -47
- package/refs/vbenchmark/README.md +0 -354
- package/refs/vbenchmark/docker-compose.prod.yaml +0 -35
- package/refs/vbenchmark/docker-compose.yaml +0 -53
- package/refs/vbenchmark/docs/TASK_EXPANSION_PLAN.md +0 -211
- package/refs/vbenchmark/docs/THESIS.md +0 -441
- package/refs/vbenchmark/docs/categories/code-evolution.md +0 -138
- package/refs/vbenchmark/openspec/changes/init-vibecodingbench/design.md +0 -111
- package/refs/vbenchmark/openspec/changes/init-vibecodingbench/proposal.md +0 -15
- package/refs/vbenchmark/openspec/changes/init-vibecodingbench/specs/evaluation/spec.md +0 -105
- package/refs/vbenchmark/openspec/changes/init-vibecodingbench/specs/leaderboard/spec.md +0 -68
- package/refs/vbenchmark/openspec/changes/init-vibecodingbench/specs/task-definition/spec.md +0 -45
- package/refs/vbenchmark/openspec/changes/init-vibecodingbench/specs/task-runner/spec.md +0 -49
- package/refs/vbenchmark/openspec/changes/init-vibecodingbench/tasks.md +0 -413
- package/refs/vbenchmark/package.json +0 -51
- package/refs/vbenchmark/packages/cli/eslint.config.js +0 -16
- package/refs/vbenchmark/packages/cli/package.json +0 -35
- package/refs/vbenchmark/packages/cli/src/agents/index.ts +0 -655
- package/refs/vbenchmark/packages/cli/src/commands/eval.ts +0 -197
- package/refs/vbenchmark/packages/cli/src/commands/list.ts +0 -63
- package/refs/vbenchmark/packages/cli/src/commands/run.ts +0 -147
- package/refs/vbenchmark/packages/cli/src/evaluator.ts +0 -125
- package/refs/vbenchmark/packages/cli/src/index.ts +0 -21
- package/refs/vbenchmark/packages/cli/src/lib/task-variation.ts +0 -153
- package/refs/vbenchmark/packages/cli/src/loader.ts +0 -258
- package/refs/vbenchmark/packages/cli/src/reporter.ts +0 -222
- package/refs/vbenchmark/packages/cli/src/runtime/docker.ts +0 -385
- package/refs/vbenchmark/packages/cli/tsconfig.json +0 -8
- package/refs/vbenchmark/packages/dashboard/Dockerfile +0 -42
- package/refs/vbenchmark/packages/dashboard/index.html +0 -21
- package/refs/vbenchmark/packages/dashboard/package.json +0 -29
- package/refs/vbenchmark/packages/dashboard/postcss.config.js +0 -6
- package/refs/vbenchmark/packages/dashboard/public/favicon.svg +0 -24
- package/refs/vbenchmark/packages/dashboard/public/logo.png +0 -0
- package/refs/vbenchmark/packages/dashboard/public/logo.svg +0 -39
- package/refs/vbenchmark/packages/dashboard/src/App.tsx +0 -1468
- package/refs/vbenchmark/packages/dashboard/src/data/category-performance.json +0 -1
- package/refs/vbenchmark/packages/dashboard/src/data/leaderboard.json +0 -1
- package/refs/vbenchmark/packages/dashboard/src/data/task-results.json +0 -1
- package/refs/vbenchmark/packages/dashboard/src/data/tasks.json +0 -1
- package/refs/vbenchmark/packages/dashboard/src/index.css +0 -3
- package/refs/vbenchmark/packages/dashboard/src/main.tsx +0 -13
- package/refs/vbenchmark/packages/dashboard/src/vite-env.d.ts +0 -9
- package/refs/vbenchmark/packages/dashboard/tailwind.config.js +0 -11
- package/refs/vbenchmark/packages/dashboard/tsconfig.json +0 -21
- package/refs/vbenchmark/packages/dashboard/tsconfig.node.json +0 -11
- package/refs/vbenchmark/packages/dashboard/vercel.json +0 -6
- package/refs/vbenchmark/packages/dashboard/vite.config.ts +0 -28
- package/refs/vbenchmark/packages/evaluator/eslint.config.js +0 -16
- package/refs/vbenchmark/packages/evaluator/package.json +0 -24
- package/refs/vbenchmark/packages/evaluator/src/index.ts +0 -15
- package/refs/vbenchmark/packages/evaluator/src/runners/functional.ts +0 -88
- package/refs/vbenchmark/packages/evaluator/src/runners/quality.ts +0 -140
- package/refs/vbenchmark/packages/evaluator/src/runners/security.ts +0 -94
- package/refs/vbenchmark/packages/evaluator/src/runners/visual.ts +0 -108
- package/refs/vbenchmark/packages/evaluator/src/types.d.ts +0 -19
- package/refs/vbenchmark/packages/evaluator/tsconfig.json +0 -8
- package/refs/vbenchmark/packages/leaderboard/Dockerfile +0 -38
- package/refs/vbenchmark/packages/leaderboard/drizzle.config.ts +0 -10
- package/refs/vbenchmark/packages/leaderboard/eslint.config.js +0 -16
- package/refs/vbenchmark/packages/leaderboard/fly.toml +0 -29
- package/refs/vbenchmark/packages/leaderboard/package.json +0 -36
- package/refs/vbenchmark/packages/leaderboard/src/app.ts +0 -29
- package/refs/vbenchmark/packages/leaderboard/src/components/BrowserPreview.tsx +0 -190
- package/refs/vbenchmark/packages/leaderboard/src/components/ComparisonView.tsx +0 -205
- package/refs/vbenchmark/packages/leaderboard/src/components/LeaderboardTable.tsx +0 -150
- package/refs/vbenchmark/packages/leaderboard/src/components/LiveRunCard.tsx +0 -133
- package/refs/vbenchmark/packages/leaderboard/src/components/SubmissionForm.tsx +0 -406
- package/refs/vbenchmark/packages/leaderboard/src/components/SubmitForm.tsx +0 -293
- package/refs/vbenchmark/packages/leaderboard/src/components/TerminalStream.tsx +0 -111
- package/refs/vbenchmark/packages/leaderboard/src/config/pricing.ts +0 -206
- package/refs/vbenchmark/packages/leaderboard/src/db/index.ts +0 -31
- package/refs/vbenchmark/packages/leaderboard/src/db/schema.ts +0 -125
- package/refs/vbenchmark/packages/leaderboard/src/index.ts +0 -13
- package/refs/vbenchmark/packages/leaderboard/src/lib/websocket.ts +0 -124
- package/refs/vbenchmark/packages/leaderboard/src/routes/leaderboard.ts +0 -698
- package/refs/vbenchmark/packages/leaderboard/src/routes/live.ts +0 -175
- package/refs/vbenchmark/packages/leaderboard/src/routes/submissions.ts +0 -183
- package/refs/vbenchmark/packages/leaderboard/src/routes/tasks.ts +0 -215
- package/refs/vbenchmark/packages/leaderboard/tests/api.test.ts +0 -228
- package/refs/vbenchmark/packages/leaderboard/tsconfig.json +0 -9
- package/refs/vbenchmark/scripts/deploy.sh +0 -70
- package/refs/vbenchmark/tasks/ai-integration/advanced/context-management/PROMPT.md +0 -15
- package/refs/vbenchmark/tasks/ai-integration/advanced/context-management/task.yaml +0 -16
- package/refs/vbenchmark/tasks/ai-integration/advanced/evaluation-framework/PROMPT.md +0 -15
- package/refs/vbenchmark/tasks/ai-integration/advanced/evaluation-framework/task.yaml +0 -16
- package/refs/vbenchmark/tasks/ai-integration/advanced/guardrails-safety/PROMPT.md +0 -15
- package/refs/vbenchmark/tasks/ai-integration/advanced/guardrails-safety/task.yaml +0 -16
- package/refs/vbenchmark/tasks/ai-integration/advanced/memory-system/PROMPT.md +0 -15
- package/refs/vbenchmark/tasks/ai-integration/advanced/memory-system/task.yaml +0 -16
- package/refs/vbenchmark/tasks/ai-integration/advanced/model-routing/PROMPT.md +0 -15
- package/refs/vbenchmark/tasks/ai-integration/advanced/model-routing/task.yaml +0 -16
- package/refs/vbenchmark/tasks/ai-integration/advanced/multi-agent-system/PROMPT.md +0 -15
- package/refs/vbenchmark/tasks/ai-integration/advanced/multi-agent-system/task.yaml +0 -16
- package/refs/vbenchmark/tasks/ai-integration/advanced/prompt-optimization/PROMPT.md +0 -15
- package/refs/vbenchmark/tasks/ai-integration/advanced/prompt-optimization/task.yaml +0 -16
- package/refs/vbenchmark/tasks/ai-integration/advanced/reasoning-chain/PROMPT.md +0 -15
- package/refs/vbenchmark/tasks/ai-integration/advanced/reasoning-chain/task.yaml +0 -16
- package/refs/vbenchmark/tasks/ai-integration/advanced/streaming-pipeline/PROMPT.md +0 -15
- package/refs/vbenchmark/tasks/ai-integration/advanced/streaming-pipeline/task.yaml +0 -16
- package/refs/vbenchmark/tasks/ai-integration/advanced/tool-use-orchestration/PROMPT.md +0 -15
- package/refs/vbenchmark/tasks/ai-integration/advanced/tool-use-orchestration/task.yaml +0 -16
- package/refs/vbenchmark/tasks/ai-integration/agents/code-review-agent/PROMPT.md +0 -64
- package/refs/vbenchmark/tasks/ai-integration/agents/code-review-agent/task.yaml +0 -24
- package/refs/vbenchmark/tasks/ai-integration/agents/research-agent/PROMPT.md +0 -61
- package/refs/vbenchmark/tasks/ai-integration/agents/research-agent/task.yaml +0 -24
- package/refs/vbenchmark/tasks/ai-integration/agents/web-scraper-agent/PROMPT.md +0 -57
- package/refs/vbenchmark/tasks/ai-integration/agents/web-scraper-agent/task.yaml +0 -24
- package/refs/vbenchmark/tasks/ai-integration/embeddings/duplicate-detection/PROMPT.md +0 -50
- package/refs/vbenchmark/tasks/ai-integration/embeddings/duplicate-detection/task.yaml +0 -24
- package/refs/vbenchmark/tasks/ai-integration/embeddings/recommendation-engine/PROMPT.md +0 -51
- package/refs/vbenchmark/tasks/ai-integration/embeddings/recommendation-engine/task.yaml +0 -24
- package/refs/vbenchmark/tasks/ai-integration/embeddings/semantic-search/PROMPT.md +0 -50
- package/refs/vbenchmark/tasks/ai-integration/embeddings/semantic-search/task.yaml +0 -24
- package/refs/vbenchmark/tasks/ai-integration/fine-tuning/classification-model/PROMPT.md +0 -50
- package/refs/vbenchmark/tasks/ai-integration/fine-tuning/classification-model/task.yaml +0 -24
- package/refs/vbenchmark/tasks/ai-integration/function-calling/api-orchestrator/PROMPT.md +0 -60
- package/refs/vbenchmark/tasks/ai-integration/function-calling/api-orchestrator/task.yaml +0 -24
- package/refs/vbenchmark/tasks/ai-integration/function-calling/calendar-assistant/PROMPT.md +0 -50
- package/refs/vbenchmark/tasks/ai-integration/function-calling/calendar-assistant/task.yaml +0 -24
- package/refs/vbenchmark/tasks/ai-integration/function-calling/database-query/PROMPT.md +0 -62
- package/refs/vbenchmark/tasks/ai-integration/function-calling/database-query/task.yaml +0 -24
- package/refs/vbenchmark/tasks/ai-integration/multimodal/chart-interpreter/PROMPT.md +0 -60
- package/refs/vbenchmark/tasks/ai-integration/multimodal/chart-interpreter/task.yaml +0 -24
- package/refs/vbenchmark/tasks/ai-integration/multimodal/image-captioning/PROMPT.md +0 -49
- package/refs/vbenchmark/tasks/ai-integration/multimodal/image-captioning/task.yaml +0 -24
- package/refs/vbenchmark/tasks/ai-integration/rag-chatbot/code-assistant/PROMPT.md +0 -51
- package/refs/vbenchmark/tasks/ai-integration/rag-chatbot/code-assistant/task.yaml +0 -24
- package/refs/vbenchmark/tasks/ai-integration/rag-chatbot/doc-search/PROMPT.md +0 -51
- package/refs/vbenchmark/tasks/ai-integration/rag-chatbot/doc-search/task.yaml +0 -24
- package/refs/vbenchmark/tasks/ai-integration/rag-chatbot/pdf-qa/PROMPT.md +0 -76
- package/refs/vbenchmark/tasks/ai-integration/rag-chatbot/pdf-qa/docker-compose.yaml +0 -30
- package/refs/vbenchmark/tasks/ai-integration/rag-chatbot/pdf-qa/task.yaml +0 -30
- package/refs/vbenchmark/tasks/ai-integration/rag-chatbot/pdf-qa/tests/functional/qa.test.py +0 -146
- package/refs/vbenchmark/tasks/ai-integration/rag-chatbot/support-bot/PROMPT.md +0 -51
- package/refs/vbenchmark/tasks/ai-integration/rag-chatbot/support-bot/task.yaml +0 -24
- package/refs/vbenchmark/tasks/ai-integration/structured-output/contract-analyzer/PROMPT.md +0 -67
- package/refs/vbenchmark/tasks/ai-integration/structured-output/contract-analyzer/task.yaml +0 -24
- package/refs/vbenchmark/tasks/ai-integration/structured-output/invoice-parser/PROMPT.md +0 -61
- package/refs/vbenchmark/tasks/ai-integration/structured-output/invoice-parser/task.yaml +0 -27
- package/refs/vbenchmark/tasks/ai-integration/structured-output/receipt-scanner/PROMPT.md +0 -65
- package/refs/vbenchmark/tasks/ai-integration/structured-output/receipt-scanner/task.yaml +0 -24
- package/refs/vbenchmark/tasks/ai-integration/structured-output/resume-parser/PROMPT.md +0 -70
- package/refs/vbenchmark/tasks/ai-integration/structured-output/resume-parser/task.yaml +0 -24
- package/refs/vbenchmark/tasks/api-integrations/advanced/api-analytics/PROMPT.md +0 -15
- package/refs/vbenchmark/tasks/api-integrations/advanced/api-analytics/task.yaml +0 -16
- package/refs/vbenchmark/tasks/api-integrations/advanced/api-gateway/PROMPT.md +0 -15
- package/refs/vbenchmark/tasks/api-integrations/advanced/api-gateway/task.yaml +0 -16
- package/refs/vbenchmark/tasks/api-integrations/advanced/api-mocking/PROMPT.md +0 -15
- package/refs/vbenchmark/tasks/api-integrations/advanced/api-mocking/task.yaml +0 -16
- package/refs/vbenchmark/tasks/api-integrations/advanced/contract-testing/PROMPT.md +0 -15
- package/refs/vbenchmark/tasks/api-integrations/advanced/contract-testing/task.yaml +0 -16
- package/refs/vbenchmark/tasks/api-integrations/advanced/graphql-federation/PROMPT.md +0 -15
- package/refs/vbenchmark/tasks/api-integrations/advanced/graphql-federation/task.yaml +0 -16
- package/refs/vbenchmark/tasks/api-integrations/advanced/grpc-gateway/PROMPT.md +0 -15
- package/refs/vbenchmark/tasks/api-integrations/advanced/grpc-gateway/task.yaml +0 -16
- package/refs/vbenchmark/tasks/api-integrations/advanced/rate-limiter/PROMPT.md +0 -15
- package/refs/vbenchmark/tasks/api-integrations/advanced/rate-limiter/task.yaml +0 -16
- package/refs/vbenchmark/tasks/api-integrations/advanced/request-validator/PROMPT.md +0 -15
- package/refs/vbenchmark/tasks/api-integrations/advanced/request-validator/task.yaml +0 -16
- package/refs/vbenchmark/tasks/api-integrations/advanced/sdk-generator/PROMPT.md +0 -15
- package/refs/vbenchmark/tasks/api-integrations/advanced/sdk-generator/task.yaml +0 -16
- package/refs/vbenchmark/tasks/api-integrations/advanced/webhook-processor/PROMPT.md +0 -15
- package/refs/vbenchmark/tasks/api-integrations/advanced/webhook-processor/task.yaml +0 -16
- package/refs/vbenchmark/tasks/api-integrations/analytics/mixpanel-events/PROMPT.md +0 -42
- package/refs/vbenchmark/tasks/api-integrations/analytics/mixpanel-events/task.yaml +0 -24
- package/refs/vbenchmark/tasks/api-integrations/analytics/segment-tracking/PROMPT.md +0 -42
- package/refs/vbenchmark/tasks/api-integrations/analytics/segment-tracking/task.yaml +0 -24
- package/refs/vbenchmark/tasks/api-integrations/auth-provider/oauth2-github/PROMPT.md +0 -42
- package/refs/vbenchmark/tasks/api-integrations/auth-provider/oauth2-github/task.yaml +0 -24
- package/refs/vbenchmark/tasks/api-integrations/auth-provider/okta-integration/PROMPT.md +0 -44
- package/refs/vbenchmark/tasks/api-integrations/auth-provider/okta-integration/task.yaml +0 -24
- package/refs/vbenchmark/tasks/api-integrations/auth-provider/saml-sso/PROMPT.md +0 -42
- package/refs/vbenchmark/tasks/api-integrations/auth-provider/saml-sso/task.yaml +0 -24
- package/refs/vbenchmark/tasks/api-integrations/communication/discord-webhook/PROMPT.md +0 -44
- package/refs/vbenchmark/tasks/api-integrations/communication/discord-webhook/task.yaml +0 -24
- package/refs/vbenchmark/tasks/api-integrations/communication/slack-bot/PROMPT.md +0 -42
- package/refs/vbenchmark/tasks/api-integrations/communication/slack-bot/task.yaml +0 -24
- package/refs/vbenchmark/tasks/api-integrations/communication/twilio-sms/PROMPT.md +0 -42
- package/refs/vbenchmark/tasks/api-integrations/communication/twilio-sms/task.yaml +0 -24
- package/refs/vbenchmark/tasks/api-integrations/email/transactional/PROMPT.md +0 -82
- package/refs/vbenchmark/tasks/api-integrations/email/transactional/task.yaml +0 -27
- package/refs/vbenchmark/tasks/api-integrations/maps/google-maps-geocoding/PROMPT.md +0 -41
- package/refs/vbenchmark/tasks/api-integrations/maps/google-maps-geocoding/task.yaml +0 -24
- package/refs/vbenchmark/tasks/api-integrations/maps/mapbox-directions/PROMPT.md +0 -41
- package/refs/vbenchmark/tasks/api-integrations/maps/mapbox-directions/task.yaml +0 -24
- package/refs/vbenchmark/tasks/api-integrations/payment/crypto-payments/PROMPT.md +0 -43
- package/refs/vbenchmark/tasks/api-integrations/payment/crypto-payments/task.yaml +0 -24
- package/refs/vbenchmark/tasks/api-integrations/payment/paypal-integration/PROMPT.md +0 -41
- package/refs/vbenchmark/tasks/api-integrations/payment/paypal-integration/task.yaml +0 -24
- package/refs/vbenchmark/tasks/api-integrations/social/twitter-api/PROMPT.md +0 -41
- package/refs/vbenchmark/tasks/api-integrations/social/twitter-api/task.yaml +0 -24
- package/refs/vbenchmark/tasks/api-integrations/storage/cloudinary-upload/PROMPT.md +0 -43
- package/refs/vbenchmark/tasks/api-integrations/storage/cloudinary-upload/task.yaml +0 -24
- package/refs/vbenchmark/tasks/api-integrations/storage/gcs-streaming/PROMPT.md +0 -43
- package/refs/vbenchmark/tasks/api-integrations/storage/gcs-streaming/task.yaml +0 -24
- package/refs/vbenchmark/tasks/api-integrations/storage/s3-presigned-urls/PROMPT.md +0 -41
- package/refs/vbenchmark/tasks/api-integrations/storage/s3-presigned-urls/task.yaml +0 -24
- package/refs/vbenchmark/tasks/api-integrations/stripe/checkout-session/PROMPT.md +0 -41
- package/refs/vbenchmark/tasks/api-integrations/stripe/checkout-session/task.yaml +0 -24
- package/refs/vbenchmark/tasks/api-integrations/stripe/payment-webhook/PROMPT.md +0 -60
- package/refs/vbenchmark/tasks/api-integrations/stripe/payment-webhook/docker-compose.yaml +0 -38
- package/refs/vbenchmark/tasks/api-integrations/stripe/payment-webhook/task.yaml +0 -31
- package/refs/vbenchmark/tasks/api-integrations/stripe/payment-webhook/tests/webhook.test.ts +0 -193
- package/refs/vbenchmark/tasks/api-integrations/stripe/subscription-portal/PROMPT.md +0 -41
- package/refs/vbenchmark/tasks/api-integrations/stripe/subscription-portal/task.yaml +0 -24
- package/refs/vbenchmark/tasks/code-evolution/advanced/api-deprecation/PROMPT.md +0 -15
- package/refs/vbenchmark/tasks/code-evolution/advanced/api-deprecation/task.yaml +0 -16
- package/refs/vbenchmark/tasks/code-evolution/advanced/ast-refactoring/PROMPT.md +0 -15
- package/refs/vbenchmark/tasks/code-evolution/advanced/ast-refactoring/task.yaml +0 -16
- package/refs/vbenchmark/tasks/code-evolution/advanced/concurrency-fix/PROMPT.md +0 -15
- package/refs/vbenchmark/tasks/code-evolution/advanced/concurrency-fix/task.yaml +0 -16
- package/refs/vbenchmark/tasks/code-evolution/advanced/database-schema-migration/PROMPT.md +0 -15
- package/refs/vbenchmark/tasks/code-evolution/advanced/database-schema-migration/task.yaml +0 -16
- package/refs/vbenchmark/tasks/code-evolution/advanced/dead-code-elimination/PROMPT.md +0 -15
- package/refs/vbenchmark/tasks/code-evolution/advanced/dead-code-elimination/task.yaml +0 -16
- package/refs/vbenchmark/tasks/code-evolution/advanced/dependency-upgrade/PROMPT.md +0 -15
- package/refs/vbenchmark/tasks/code-evolution/advanced/dependency-upgrade/task.yaml +0 -16
- package/refs/vbenchmark/tasks/code-evolution/advanced/memory-optimization/PROMPT.md +0 -15
- package/refs/vbenchmark/tasks/code-evolution/advanced/memory-optimization/task.yaml +0 -16
- package/refs/vbenchmark/tasks/code-evolution/advanced/monorepo-extraction/PROMPT.md +0 -15
- package/refs/vbenchmark/tasks/code-evolution/advanced/monorepo-extraction/task.yaml +0 -16
- package/refs/vbenchmark/tasks/code-evolution/advanced/performance-profiling/PROMPT.md +0 -15
- package/refs/vbenchmark/tasks/code-evolution/advanced/performance-profiling/task.yaml +0 -16
- package/refs/vbenchmark/tasks/code-evolution/advanced/type-migration/PROMPT.md +0 -15
- package/refs/vbenchmark/tasks/code-evolution/advanced/type-migration/task.yaml +0 -16
- package/refs/vbenchmark/tasks/code-evolution/legacy-migration/callback-to-async/PROMPT.md +0 -47
- package/refs/vbenchmark/tasks/code-evolution/legacy-migration/callback-to-async/task.yaml +0 -24
- package/refs/vbenchmark/tasks/code-evolution/legacy-migration/express-to-fastify/PROMPT.md +0 -49
- package/refs/vbenchmark/tasks/code-evolution/legacy-migration/express-to-fastify/base-code/src/app.ts +0 -22
- package/refs/vbenchmark/tasks/code-evolution/legacy-migration/express-to-fastify/task.yaml +0 -37
- package/refs/vbenchmark/tasks/code-evolution/legacy-migration/express-to-fastify/tests/api.test.ts +0 -70
- package/refs/vbenchmark/tasks/code-evolution/legacy-migration/flask-to-fastapi/PROMPT.md +0 -46
- package/refs/vbenchmark/tasks/code-evolution/legacy-migration/flask-to-fastapi/task.yaml +0 -24
- package/refs/vbenchmark/tasks/code-evolution/legacy-migration/java-to-kotlin/PROMPT.md +0 -45
- package/refs/vbenchmark/tasks/code-evolution/legacy-migration/java-to-kotlin/task.yaml +0 -24
- package/refs/vbenchmark/tasks/code-evolution/legacy-migration/jquery-to-react/PROMPT.md +0 -47
- package/refs/vbenchmark/tasks/code-evolution/legacy-migration/jquery-to-react/task.yaml +0 -24
- package/refs/vbenchmark/tasks/code-evolution/legacy-migration/rest-to-grpc/PROMPT.md +0 -47
- package/refs/vbenchmark/tasks/code-evolution/legacy-migration/rest-to-grpc/task.yaml +0 -24
- package/refs/vbenchmark/tasks/code-evolution/performance/async-refactor/PROMPT.md +0 -47
- package/refs/vbenchmark/tasks/code-evolution/performance/async-refactor/task.yaml +0 -24
- package/refs/vbenchmark/tasks/code-evolution/performance/memory-leak-fix/PROMPT.md +0 -47
- package/refs/vbenchmark/tasks/code-evolution/performance/memory-leak-fix/task.yaml +0 -24
- package/refs/vbenchmark/tasks/code-evolution/performance/query-optimization/PROMPT.md +0 -49
- package/refs/vbenchmark/tasks/code-evolution/performance/query-optimization/task.yaml +0 -24
- package/refs/vbenchmark/tasks/code-evolution/refactoring/class-to-hooks/PROMPT.md +0 -96
- package/refs/vbenchmark/tasks/code-evolution/refactoring/class-to-hooks/task.yaml +0 -27
- package/refs/vbenchmark/tasks/code-evolution/refactoring/dependency-injection/PROMPT.md +0 -47
- package/refs/vbenchmark/tasks/code-evolution/refactoring/dependency-injection/task.yaml +0 -24
- package/refs/vbenchmark/tasks/code-evolution/refactoring/error-handling/PROMPT.md +0 -48
- package/refs/vbenchmark/tasks/code-evolution/refactoring/error-handling/task.yaml +0 -24
- package/refs/vbenchmark/tasks/code-evolution/refactoring/monolith-to-modules/PROMPT.md +0 -50
- package/refs/vbenchmark/tasks/code-evolution/refactoring/monolith-to-modules/task.yaml +0 -24
- package/refs/vbenchmark/tasks/code-evolution/refactoring/orm-migration/PROMPT.md +0 -47
- package/refs/vbenchmark/tasks/code-evolution/refactoring/orm-migration/task.yaml +0 -24
- package/refs/vbenchmark/tasks/code-evolution/security/secrets-rotation/PROMPT.md +0 -49
- package/refs/vbenchmark/tasks/code-evolution/security/secrets-rotation/task.yaml +0 -24
- package/refs/vbenchmark/tasks/code-evolution/security/sql-injection-fix/PROMPT.md +0 -50
- package/refs/vbenchmark/tasks/code-evolution/security/sql-injection-fix/task.yaml +0 -24
- package/refs/vbenchmark/tasks/code-evolution/security/xss-prevention/PROMPT.md +0 -47
- package/refs/vbenchmark/tasks/code-evolution/security/xss-prevention/task.yaml +0 -24
- package/refs/vbenchmark/tasks/code-evolution/testing/add-unit-tests/PROMPT.md +0 -48
- package/refs/vbenchmark/tasks/code-evolution/testing/add-unit-tests/task.yaml +0 -24
- package/refs/vbenchmark/tasks/code-evolution/testing/e2e-playwright/PROMPT.md +0 -50
- package/refs/vbenchmark/tasks/code-evolution/testing/e2e-playwright/task.yaml +0 -24
- package/refs/vbenchmark/tasks/code-evolution/testing/pytest-fixtures/PROMPT.md +0 -47
- package/refs/vbenchmark/tasks/code-evolution/testing/pytest-fixtures/task.yaml +0 -24
- package/refs/vbenchmark/tasks/frontend/accessibility/keyboard-shortcuts/PROMPT.md +0 -44
- package/refs/vbenchmark/tasks/frontend/accessibility/keyboard-shortcuts/task.yaml +0 -24
- package/refs/vbenchmark/tasks/frontend/accessibility/screen-reader-nav/PROMPT.md +0 -44
- package/refs/vbenchmark/tasks/frontend/accessibility/screen-reader-nav/task.yaml +0 -24
- package/refs/vbenchmark/tasks/frontend/advanced/canvas-editor/PROMPT.md +0 -15
- package/refs/vbenchmark/tasks/frontend/advanced/canvas-editor/task.yaml +0 -16
- package/refs/vbenchmark/tasks/frontend/advanced/micro-frontend/PROMPT.md +0 -15
- package/refs/vbenchmark/tasks/frontend/advanced/micro-frontend/task.yaml +0 -16
- package/refs/vbenchmark/tasks/frontend/advanced/offline-first/PROMPT.md +0 -15
- package/refs/vbenchmark/tasks/frontend/advanced/offline-first/task.yaml +0 -16
- package/refs/vbenchmark/tasks/frontend/advanced/realtime-collab/PROMPT.md +0 -15
- package/refs/vbenchmark/tasks/frontend/advanced/realtime-collab/task.yaml +0 -16
- package/refs/vbenchmark/tasks/frontend/advanced/service-worker/PROMPT.md +0 -15
- package/refs/vbenchmark/tasks/frontend/advanced/service-worker/task.yaml +0 -16
- package/refs/vbenchmark/tasks/frontend/advanced/state-machine/PROMPT.md +0 -15
- package/refs/vbenchmark/tasks/frontend/advanced/state-machine/task.yaml +0 -16
- package/refs/vbenchmark/tasks/frontend/advanced/virtual-list/PROMPT.md +0 -15
- package/refs/vbenchmark/tasks/frontend/advanced/virtual-list/task.yaml +0 -16
- package/refs/vbenchmark/tasks/frontend/advanced/wasm-integration/PROMPT.md +0 -15
- package/refs/vbenchmark/tasks/frontend/advanced/wasm-integration/task.yaml +0 -16
- package/refs/vbenchmark/tasks/frontend/advanced/web-worker/PROMPT.md +0 -15
- package/refs/vbenchmark/tasks/frontend/advanced/web-worker/task.yaml +0 -16
- package/refs/vbenchmark/tasks/frontend/advanced/webgl-visualization/PROMPT.md +0 -15
- package/refs/vbenchmark/tasks/frontend/advanced/webgl-visualization/task.yaml +0 -16
- package/refs/vbenchmark/tasks/frontend/animation/page-transitions/PROMPT.md +0 -44
- package/refs/vbenchmark/tasks/frontend/animation/page-transitions/task.yaml +0 -24
- package/refs/vbenchmark/tasks/frontend/components/data-grid/PROMPT.md +0 -59
- package/refs/vbenchmark/tasks/frontend/components/data-grid/task.yaml +0 -24
- package/refs/vbenchmark/tasks/frontend/components/date-range-picker/PROMPT.md +0 -57
- package/refs/vbenchmark/tasks/frontend/components/date-range-picker/task.yaml +0 -24
- package/refs/vbenchmark/tasks/frontend/components/file-uploader/PROMPT.md +0 -55
- package/refs/vbenchmark/tasks/frontend/components/file-uploader/task.yaml +0 -24
- package/refs/vbenchmark/tasks/frontend/components/form-builder/PROMPT.md +0 -96
- package/refs/vbenchmark/tasks/frontend/components/form-builder/task.yaml +0 -28
- package/refs/vbenchmark/tasks/frontend/components/rich-text-editor/PROMPT.md +0 -45
- package/refs/vbenchmark/tasks/frontend/components/rich-text-editor/task.yaml +0 -24
- package/refs/vbenchmark/tasks/frontend/figma-to-code/dashboard-layout/PROMPT.md +0 -50
- package/refs/vbenchmark/tasks/frontend/figma-to-code/dashboard-layout/task.yaml +0 -25
- package/refs/vbenchmark/tasks/frontend/figma-to-code/landing-page/PROMPT.md +0 -49
- package/refs/vbenchmark/tasks/frontend/figma-to-code/landing-page/task.yaml +0 -25
- package/refs/vbenchmark/tasks/frontend/figma-to-code/mobile-app-screen/PROMPT.md +0 -51
- package/refs/vbenchmark/tasks/frontend/figma-to-code/mobile-app-screen/task.yaml +0 -24
- package/refs/vbenchmark/tasks/frontend/figma-to-code/pricing-card/PROMPT.md +0 -93
- package/refs/vbenchmark/tasks/frontend/figma-to-code/pricing-card/docker-compose.yaml +0 -23
- package/refs/vbenchmark/tasks/frontend/figma-to-code/pricing-card/task.yaml +0 -30
- package/refs/vbenchmark/tasks/frontend/figma-to-code/pricing-card/tests/visual/diff.test.ts +0 -107
- package/refs/vbenchmark/tasks/frontend/figma-to-code/pricing-card/tests/visual/interaction.test.ts +0 -88
- package/refs/vbenchmark/tasks/frontend/performance/image-lazy-load/PROMPT.md +0 -43
- package/refs/vbenchmark/tasks/frontend/performance/image-lazy-load/task.yaml +0 -24
- package/refs/vbenchmark/tasks/frontend/performance/infinite-scroll/PROMPT.md +0 -44
- package/refs/vbenchmark/tasks/frontend/performance/infinite-scroll/task.yaml +0 -24
- package/refs/vbenchmark/tasks/frontend/state-management/collaborative-editor/PROMPT.md +0 -44
- package/refs/vbenchmark/tasks/frontend/state-management/collaborative-editor/task.yaml +0 -24
- package/refs/vbenchmark/tasks/frontend/state-management/shopping-cart/PROMPT.md +0 -53
- package/refs/vbenchmark/tasks/frontend/state-management/shopping-cart/task.yaml +0 -24
- package/refs/vbenchmark/tasks/frontend/visualization/chart-dashboard/PROMPT.md +0 -83
- package/refs/vbenchmark/tasks/frontend/visualization/chart-dashboard/task.yaml +0 -28
- package/refs/vbenchmark/tasks/frontend/visualization/gantt-chart/PROMPT.md +0 -57
- package/refs/vbenchmark/tasks/frontend/visualization/gantt-chart/task.yaml +0 -24
- package/refs/vbenchmark/tasks/frontend/visualization/map-dashboard/PROMPT.md +0 -44
- package/refs/vbenchmark/tasks/frontend/visualization/map-dashboard/task.yaml +0 -24
- package/refs/vbenchmark/tasks/frontend/visualization/realtime-charts/PROMPT.md +0 -43
- package/refs/vbenchmark/tasks/frontend/visualization/realtime-charts/task.yaml +0 -24
- package/refs/vbenchmark/tasks/glue-code/advanced/blue-green-deploy/PROMPT.md +0 -15
- package/refs/vbenchmark/tasks/glue-code/advanced/blue-green-deploy/task.yaml +0 -16
- package/refs/vbenchmark/tasks/glue-code/advanced/canary-release/PROMPT.md +0 -15
- package/refs/vbenchmark/tasks/glue-code/advanced/canary-release/task.yaml +0 -16
- package/refs/vbenchmark/tasks/glue-code/advanced/change-data-capture/PROMPT.md +0 -15
- package/refs/vbenchmark/tasks/glue-code/advanced/change-data-capture/task.yaml +0 -16
- package/refs/vbenchmark/tasks/glue-code/advanced/config-management/PROMPT.md +0 -15
- package/refs/vbenchmark/tasks/glue-code/advanced/config-management/task.yaml +0 -16
- package/refs/vbenchmark/tasks/glue-code/advanced/data-pipeline/PROMPT.md +0 -15
- package/refs/vbenchmark/tasks/glue-code/advanced/data-pipeline/task.yaml +0 -16
- package/refs/vbenchmark/tasks/glue-code/advanced/distributed-tracing/PROMPT.md +0 -15
- package/refs/vbenchmark/tasks/glue-code/advanced/distributed-tracing/task.yaml +0 -16
- package/refs/vbenchmark/tasks/glue-code/advanced/log-aggregation/PROMPT.md +0 -15
- package/refs/vbenchmark/tasks/glue-code/advanced/log-aggregation/task.yaml +0 -16
- package/refs/vbenchmark/tasks/glue-code/advanced/schema-registry/PROMPT.md +0 -15
- package/refs/vbenchmark/tasks/glue-code/advanced/schema-registry/task.yaml +0 -16
- package/refs/vbenchmark/tasks/glue-code/advanced/secret-rotation/PROMPT.md +0 -15
- package/refs/vbenchmark/tasks/glue-code/advanced/secret-rotation/task.yaml +0 -16
- package/refs/vbenchmark/tasks/glue-code/advanced/stream-processing/PROMPT.md +0 -15
- package/refs/vbenchmark/tasks/glue-code/advanced/stream-processing/task.yaml +0 -16
- package/refs/vbenchmark/tasks/glue-code/api-sync/rest-to-graphql/PROMPT.md +0 -66
- package/refs/vbenchmark/tasks/glue-code/api-sync/rest-to-graphql/task.yaml +0 -27
- package/refs/vbenchmark/tasks/glue-code/caching/redis-cache/PROMPT.md +0 -82
- package/refs/vbenchmark/tasks/glue-code/caching/redis-cache/task.yaml +0 -27
- package/refs/vbenchmark/tasks/glue-code/data-transform/avro-schema-evolution/PROMPT.md +0 -51
- package/refs/vbenchmark/tasks/glue-code/data-transform/avro-schema-evolution/task.yaml +0 -24
- package/refs/vbenchmark/tasks/glue-code/data-transform/csv-normalizer/PROMPT.md +0 -49
- package/refs/vbenchmark/tasks/glue-code/data-transform/csv-normalizer/task.yaml +0 -24
- package/refs/vbenchmark/tasks/glue-code/data-transform/excel-to-json/PROMPT.md +0 -67
- package/refs/vbenchmark/tasks/glue-code/data-transform/excel-to-json/task.yaml +0 -28
- package/refs/vbenchmark/tasks/glue-code/data-transform/excel-to-json/tests/transform.test.py +0 -137
- package/refs/vbenchmark/tasks/glue-code/data-transform/json-to-xml/PROMPT.md +0 -45
- package/refs/vbenchmark/tasks/glue-code/data-transform/json-to-xml/task.yaml +0 -24
- package/refs/vbenchmark/tasks/glue-code/data-transform/protobuf-converter/PROMPT.md +0 -44
- package/refs/vbenchmark/tasks/glue-code/data-transform/protobuf-converter/task.yaml +0 -24
- package/refs/vbenchmark/tasks/glue-code/etl/cdc-pipeline/PROMPT.md +0 -52
- package/refs/vbenchmark/tasks/glue-code/etl/cdc-pipeline/task.yaml +0 -27
- package/refs/vbenchmark/tasks/glue-code/etl/database-sync/PROMPT.md +0 -51
- package/refs/vbenchmark/tasks/glue-code/etl/database-sync/task.yaml +0 -24
- package/refs/vbenchmark/tasks/glue-code/etl/s3-to-warehouse/PROMPT.md +0 -50
- package/refs/vbenchmark/tasks/glue-code/etl/s3-to-warehouse/task.yaml +0 -24
- package/refs/vbenchmark/tasks/glue-code/file-processing/image-resizer/PROMPT.md +0 -52
- package/refs/vbenchmark/tasks/glue-code/file-processing/image-resizer/task.yaml +0 -24
- package/refs/vbenchmark/tasks/glue-code/file-processing/pdf-merger/PROMPT.md +0 -50
- package/refs/vbenchmark/tasks/glue-code/file-processing/pdf-merger/task.yaml +0 -24
- package/refs/vbenchmark/tasks/glue-code/file-processing/video-transcoder/PROMPT.md +0 -50
- package/refs/vbenchmark/tasks/glue-code/file-processing/video-transcoder/task.yaml +0 -27
- package/refs/vbenchmark/tasks/glue-code/migration/data-backfill/PROMPT.md +0 -50
- package/refs/vbenchmark/tasks/glue-code/migration/data-backfill/task.yaml +0 -24
- package/refs/vbenchmark/tasks/glue-code/migration/database-versioning/PROMPT.md +0 -50
- package/refs/vbenchmark/tasks/glue-code/migration/database-versioning/task.yaml +0 -24
- package/refs/vbenchmark/tasks/glue-code/queue/kafka-producer/PROMPT.md +0 -49
- package/refs/vbenchmark/tasks/glue-code/queue/kafka-producer/task.yaml +0 -27
- package/refs/vbenchmark/tasks/glue-code/queue/rabbitmq-consumer/PROMPT.md +0 -50
- package/refs/vbenchmark/tasks/glue-code/queue/rabbitmq-consumer/task.yaml +0 -27
- package/refs/vbenchmark/tasks/glue-code/queue/sqs-batch-processor/PROMPT.md +0 -47
- package/refs/vbenchmark/tasks/glue-code/queue/sqs-batch-processor/task.yaml +0 -24
- package/refs/vbenchmark/tasks/glue-code/scheduler/cron-job-manager/PROMPT.md +0 -52
- package/refs/vbenchmark/tasks/glue-code/scheduler/cron-job-manager/task.yaml +0 -27
- package/refs/vbenchmark/tasks/glue-code/scheduler/delayed-tasks/PROMPT.md +0 -51
- package/refs/vbenchmark/tasks/glue-code/scheduler/delayed-tasks/task.yaml +0 -27
- package/refs/vbenchmark/tasks/saas-core/advanced/api-versioning/PROMPT.md +0 -15
- package/refs/vbenchmark/tasks/saas-core/advanced/api-versioning/task.yaml +0 -16
- package/refs/vbenchmark/tasks/saas-core/advanced/circuit-breaker/PROMPT.md +0 -13
- package/refs/vbenchmark/tasks/saas-core/advanced/circuit-breaker/task.yaml +0 -16
- package/refs/vbenchmark/tasks/saas-core/advanced/compliance-gdpr/PROMPT.md +0 -15
- package/refs/vbenchmark/tasks/saas-core/advanced/compliance-gdpr/task.yaml +0 -16
- package/refs/vbenchmark/tasks/saas-core/advanced/cqrs-pattern/PROMPT.md +0 -13
- package/refs/vbenchmark/tasks/saas-core/advanced/cqrs-pattern/task.yaml +0 -16
- package/refs/vbenchmark/tasks/saas-core/advanced/data-encryption/PROMPT.md +0 -15
- package/refs/vbenchmark/tasks/saas-core/advanced/data-encryption/task.yaml +0 -16
- package/refs/vbenchmark/tasks/saas-core/advanced/distributed-locking/PROMPT.md +0 -46
- package/refs/vbenchmark/tasks/saas-core/advanced/distributed-locking/task.yaml +0 -24
- package/refs/vbenchmark/tasks/saas-core/advanced/event-sourcing/PROMPT.md +0 -23
- package/refs/vbenchmark/tasks/saas-core/advanced/event-sourcing/task.yaml +0 -16
- package/refs/vbenchmark/tasks/saas-core/advanced/feature-flags-ab/PROMPT.md +0 -15
- package/refs/vbenchmark/tasks/saas-core/advanced/feature-flags-ab/task.yaml +0 -16
- package/refs/vbenchmark/tasks/saas-core/advanced/saga-orchestration/PROMPT.md +0 -13
- package/refs/vbenchmark/tasks/saas-core/advanced/saga-orchestration/task.yaml +0 -16
- package/refs/vbenchmark/tasks/saas-core/advanced/webhook-delivery/PROMPT.md +0 -15
- package/refs/vbenchmark/tasks/saas-core/advanced/webhook-delivery/task.yaml +0 -16
- package/refs/vbenchmark/tasks/saas-core/audit/activity-logging/PROMPT.md +0 -50
- package/refs/vbenchmark/tasks/saas-core/audit/activity-logging/task.yaml +0 -27
- package/refs/vbenchmark/tasks/saas-core/auth/jwt-refresh-tokens/PROMPT.md +0 -50
- package/refs/vbenchmark/tasks/saas-core/auth/jwt-refresh-tokens/task.yaml +0 -27
- package/refs/vbenchmark/tasks/saas-core/auth/magic-link-email/PROMPT.md +0 -53
- package/refs/vbenchmark/tasks/saas-core/auth/magic-link-email/task.yaml +0 -27
- package/refs/vbenchmark/tasks/saas-core/auth/mfa-totp/PROMPT.md +0 -79
- package/refs/vbenchmark/tasks/saas-core/auth/mfa-totp/task.yaml +0 -27
- package/refs/vbenchmark/tasks/saas-core/auth/rbac-permissions/PROMPT.md +0 -51
- package/refs/vbenchmark/tasks/saas-core/auth/rbac-permissions/task.yaml +0 -27
- package/refs/vbenchmark/tasks/saas-core/auth/session-management/PROMPT.md +0 -52
- package/refs/vbenchmark/tasks/saas-core/auth/session-management/task.yaml +0 -27
- package/refs/vbenchmark/tasks/saas-core/auth/supabase-oauth/PROMPT.md +0 -45
- package/refs/vbenchmark/tasks/saas-core/auth/supabase-oauth/docker-compose.yaml +0 -47
- package/refs/vbenchmark/tasks/saas-core/auth/supabase-oauth/task.yaml +0 -32
- package/refs/vbenchmark/tasks/saas-core/auth/supabase-oauth/tests/auth.test.ts +0 -59
- package/refs/vbenchmark/tasks/saas-core/billing/invoice-generation/PROMPT.md +0 -53
- package/refs/vbenchmark/tasks/saas-core/billing/invoice-generation/task.yaml +0 -27
- package/refs/vbenchmark/tasks/saas-core/billing/stripe-subscriptions/PROMPT.md +0 -51
- package/refs/vbenchmark/tasks/saas-core/billing/stripe-subscriptions/task.yaml +0 -27
- package/refs/vbenchmark/tasks/saas-core/billing/usage-metering/PROMPT.md +0 -52
- package/refs/vbenchmark/tasks/saas-core/billing/usage-metering/task.yaml +0 -27
- package/refs/vbenchmark/tasks/saas-core/crud/dashboard-table/PROMPT.md +0 -48
- package/refs/vbenchmark/tasks/saas-core/crud/dashboard-table/task.yaml +0 -28
- package/refs/vbenchmark/tasks/saas-core/multi-tenant/org-isolation/PROMPT.md +0 -50
- package/refs/vbenchmark/tasks/saas-core/multi-tenant/org-isolation/task.yaml +0 -27
- package/refs/vbenchmark/tasks/saas-core/multi-tenant/subdomain-routing/PROMPT.md +0 -50
- package/refs/vbenchmark/tasks/saas-core/multi-tenant/subdomain-routing/task.yaml +0 -27
- package/refs/vbenchmark/tasks/saas-core/notifications/email-queue/PROMPT.md +0 -53
- package/refs/vbenchmark/tasks/saas-core/notifications/email-queue/task.yaml +0 -27
- package/refs/vbenchmark/tasks/saas-core/notifications/in-app-alerts/PROMPT.md +0 -51
- package/refs/vbenchmark/tasks/saas-core/notifications/in-app-alerts/task.yaml +0 -27
- package/refs/vbenchmark/tasks/saas-core/notifications/push-notifications/PROMPT.md +0 -51
- package/refs/vbenchmark/tasks/saas-core/notifications/push-notifications/task.yaml +0 -27
- package/refs/vbenchmark/tasks/saas-core/realtime/websocket-chat/PROMPT.md +0 -80
- package/refs/vbenchmark/tasks/saas-core/realtime/websocket-chat/task.yaml +0 -27
- package/refs/vbenchmark/tasks/saas-core/search/full-text-search/PROMPT.md +0 -51
- package/refs/vbenchmark/tasks/saas-core/search/full-text-search/task.yaml +0 -27
- package/refs/vbenchmark/tasks/saas-core/security/rate-limiter/PROMPT.md +0 -99
- package/refs/vbenchmark/tasks/saas-core/security/rate-limiter/task.yaml +0 -27
- package/refs/vbenchmark/tasks/saas-core/settings/user-preferences/PROMPT.md +0 -78
- package/refs/vbenchmark/tasks/saas-core/settings/user-preferences/task.yaml +0 -27
- package/refs/vbenchmark/templates/fastapi-postgres/docker-compose.yaml +0 -36
- package/refs/vbenchmark/templates/fastapi-postgres/pyproject.toml +0 -34
- package/refs/vbenchmark/templates/fastapi-postgres/src/__init__.py +0 -0
- package/refs/vbenchmark/templates/fastapi-postgres/src/config.py +0 -12
- package/refs/vbenchmark/templates/fastapi-postgres/src/database.py +0 -15
- package/refs/vbenchmark/templates/fastapi-postgres/src/main.py +0 -51
- package/refs/vbenchmark/templates/fastapi-postgres/src/models.py +0 -12
- package/refs/vbenchmark/templates/fastapi-postgres/src/schemas.py +0 -20
- package/refs/vbenchmark/templates/go-fiber/docker-compose.yaml +0 -34
- package/refs/vbenchmark/templates/go-fiber/go.mod +0 -33
- package/refs/vbenchmark/templates/go-fiber/go.sum +0 -68
- package/refs/vbenchmark/templates/go-fiber/main.go +0 -98
- package/refs/vbenchmark/templates/nextjs-supabase/.env.example +0 -3
- package/refs/vbenchmark/templates/nextjs-supabase/docker-compose.yaml +0 -68
- package/refs/vbenchmark/templates/nextjs-supabase/src/app/globals.css +0 -13
- package/refs/vbenchmark/templates/nextjs-supabase/src/app/layout.tsx +0 -19
- package/refs/vbenchmark/templates/nextjs-supabase/src/app/page.tsx +0 -38
- package/refs/vbenchmark/templates/nextjs-supabase/src/lib/supabase/client.ts +0 -8
- package/refs/vbenchmark/templates/nextjs-supabase/src/lib/supabase/server.ts +0 -32
- package/refs/vbenchmark/templates/rust-axum/Cargo.lock +0 -2371
- package/refs/vbenchmark/templates/rust-axum/Cargo.toml +0 -16
- package/refs/vbenchmark/templates/rust-axum/docker-compose.yaml +0 -34
- package/refs/vbenchmark/templates/rust-axum/migrations/20240101000000_init.sql +0 -20
- package/refs/vbenchmark/templates/rust-axum/src/main.rs +0 -121
- package/refs/vbenchmark/tsconfig.base.json +0 -18
- package/refs/vbenchmark/turbo.json +0 -23
- package/refs/vbenchmark/vercel.json +0 -10
|
@@ -1,125 +0,0 @@
|
|
|
1
|
-
import { pgTable, uuid, varchar, integer, real, timestamp, jsonb, text } from 'drizzle-orm/pg-core';
|
|
2
|
-
|
|
3
|
-
// Agents table - stores registered agents
|
|
4
|
-
export const agents = pgTable('agents', {
|
|
5
|
-
id: uuid('id').primaryKey().defaultRandom(),
|
|
6
|
-
name: varchar('name', { length: 255 }).notNull(),
|
|
7
|
-
version: varchar('version', { length: 50 }).notNull(),
|
|
8
|
-
provider: varchar('provider', { length: 100 }), // anthropic, openai, glm, minimax
|
|
9
|
-
config: jsonb('config'), // API configuration (not secrets)
|
|
10
|
-
createdAt: timestamp('created_at').defaultNow().notNull(),
|
|
11
|
-
updatedAt: timestamp('updated_at').defaultNow().notNull(),
|
|
12
|
-
});
|
|
13
|
-
|
|
14
|
-
// Tasks table - stores benchmark tasks
|
|
15
|
-
export const tasks = pgTable('tasks', {
|
|
16
|
-
id: varchar('id', { length: 255 }).primaryKey(), // e.g., saas-core/auth/supabase-oauth
|
|
17
|
-
name: varchar('name', { length: 255 }).notNull(),
|
|
18
|
-
category: varchar('category', { length: 100 }).notNull(),
|
|
19
|
-
subcategory: varchar('subcategory', { length: 100 }),
|
|
20
|
-
difficulty: varchar('difficulty', { length: 20 }).notNull(), // easy, medium, hard
|
|
21
|
-
stack: varchar('stack', { length: 100 }),
|
|
22
|
-
tags: jsonb('tags').$type<string[]>(),
|
|
23
|
-
weights: jsonb('weights').$type<{
|
|
24
|
-
functional: number;
|
|
25
|
-
visual: number;
|
|
26
|
-
quality: number;
|
|
27
|
-
cost: number;
|
|
28
|
-
speed: number;
|
|
29
|
-
}>(),
|
|
30
|
-
createdAt: timestamp('created_at').defaultNow().notNull(),
|
|
31
|
-
});
|
|
32
|
-
|
|
33
|
-
// Benchmark runs table - stores each benchmark execution
|
|
34
|
-
export const benchmarkRuns = pgTable('benchmark_runs', {
|
|
35
|
-
id: uuid('id').primaryKey().defaultRandom(),
|
|
36
|
-
agentId: uuid('agent_id').references(() => agents.id),
|
|
37
|
-
agentName: varchar('agent_name', { length: 255 }).notNull(),
|
|
38
|
-
agentVersion: varchar('agent_version', { length: 50 }).notNull(),
|
|
39
|
-
seed: integer('seed'), // For reproducibility with task variations
|
|
40
|
-
status: varchar('status', { length: 20 }).notNull().default('pending'), // pending, running, completed, failed
|
|
41
|
-
startedAt: timestamp('started_at').defaultNow().notNull(),
|
|
42
|
-
completedAt: timestamp('completed_at'),
|
|
43
|
-
totalTasks: integer('total_tasks').notNull().default(0),
|
|
44
|
-
passedTasks: integer('passed_tasks').notNull().default(0),
|
|
45
|
-
failedTasks: integer('failed_tasks').notNull().default(0),
|
|
46
|
-
avgScore: real('avg_score'),
|
|
47
|
-
totalCost: real('total_cost').default(0),
|
|
48
|
-
totalTokens: integer('total_tokens').default(0),
|
|
49
|
-
totalDurationMs: integer('total_duration_ms'),
|
|
50
|
-
metadata: jsonb('metadata'), // Additional run metadata
|
|
51
|
-
});
|
|
52
|
-
|
|
53
|
-
// Task results table - stores individual task results within a run
|
|
54
|
-
export const taskResults = pgTable('task_results', {
|
|
55
|
-
id: uuid('id').primaryKey().defaultRandom(),
|
|
56
|
-
runId: uuid('run_id').references(() => benchmarkRuns.id).notNull(),
|
|
57
|
-
taskId: varchar('task_id', { length: 255 }).references(() => tasks.id).notNull(),
|
|
58
|
-
status: varchar('status', { length: 20 }).notNull(), // passed, failed, error, skipped
|
|
59
|
-
|
|
60
|
-
// Scores (0-100)
|
|
61
|
-
functionalScore: real('functional_score'),
|
|
62
|
-
visualScore: real('visual_score'),
|
|
63
|
-
qualityScore: real('quality_score'),
|
|
64
|
-
securityScore: real('security_score'),
|
|
65
|
-
costScore: real('cost_score'),
|
|
66
|
-
speedScore: real('speed_score'),
|
|
67
|
-
overallScore: real('overall_score'),
|
|
68
|
-
|
|
69
|
-
// Metrics
|
|
70
|
-
tokensUsed: integer('tokens_used').default(0),
|
|
71
|
-
inputTokens: integer('input_tokens').default(0),
|
|
72
|
-
outputTokens: integer('output_tokens').default(0),
|
|
73
|
-
cost: real('cost').default(0),
|
|
74
|
-
durationMs: integer('duration_ms'),
|
|
75
|
-
|
|
76
|
-
// Code metrics
|
|
77
|
-
filesCreated: integer('files_created').default(0),
|
|
78
|
-
filesModified: integer('files_modified').default(0),
|
|
79
|
-
linesAdded: integer('lines_added').default(0),
|
|
80
|
-
linesRemoved: integer('lines_removed').default(0),
|
|
81
|
-
|
|
82
|
-
// Test results
|
|
83
|
-
testsPassed: integer('tests_passed').default(0),
|
|
84
|
-
testsFailed: integer('tests_failed').default(0),
|
|
85
|
-
testsSkipped: integer('tests_skipped').default(0),
|
|
86
|
-
|
|
87
|
-
// Error info
|
|
88
|
-
errorMessage: text('error_message'),
|
|
89
|
-
errorStack: text('error_stack'),
|
|
90
|
-
|
|
91
|
-
// Full output (for debugging)
|
|
92
|
-
agentOutput: text('agent_output'),
|
|
93
|
-
|
|
94
|
-
startedAt: timestamp('started_at').defaultNow().notNull(),
|
|
95
|
-
completedAt: timestamp('completed_at'),
|
|
96
|
-
});
|
|
97
|
-
|
|
98
|
-
// Leaderboard snapshot table - periodic snapshots for historical tracking
|
|
99
|
-
export const leaderboardSnapshots = pgTable('leaderboard_snapshots', {
|
|
100
|
-
id: uuid('id').primaryKey().defaultRandom(),
|
|
101
|
-
snapshotDate: timestamp('snapshot_date').defaultNow().notNull(),
|
|
102
|
-
agentName: varchar('agent_name', { length: 255 }).notNull(),
|
|
103
|
-
agentVersion: varchar('agent_version', { length: 50 }).notNull(),
|
|
104
|
-
rank: integer('rank').notNull(),
|
|
105
|
-
totalRuns: integer('total_runs').notNull(),
|
|
106
|
-
avgScore: real('avg_score').notNull(),
|
|
107
|
-
avgFunctional: real('avg_functional'),
|
|
108
|
-
avgVisual: real('avg_visual'),
|
|
109
|
-
avgQuality: real('avg_quality'),
|
|
110
|
-
avgCost: real('avg_cost'),
|
|
111
|
-
avgSpeed: real('avg_speed'),
|
|
112
|
-
passRate: real('pass_rate'),
|
|
113
|
-
totalCost: real('total_cost'),
|
|
114
|
-
});
|
|
115
|
-
|
|
116
|
-
// Type exports for use in application code
|
|
117
|
-
export type Agent = typeof agents.$inferSelect;
|
|
118
|
-
export type NewAgent = typeof agents.$inferInsert;
|
|
119
|
-
export type Task = typeof tasks.$inferSelect;
|
|
120
|
-
export type NewTask = typeof tasks.$inferInsert;
|
|
121
|
-
export type BenchmarkRun = typeof benchmarkRuns.$inferSelect;
|
|
122
|
-
export type NewBenchmarkRun = typeof benchmarkRuns.$inferInsert;
|
|
123
|
-
export type TaskResult = typeof taskResults.$inferSelect;
|
|
124
|
-
export type NewTaskResult = typeof taskResults.$inferInsert;
|
|
125
|
-
export type LeaderboardSnapshot = typeof leaderboardSnapshots.$inferSelect;
|
|
@@ -1,13 +0,0 @@
|
|
|
1
|
-
import { serve } from '@hono/node-server';
|
|
2
|
-
import { app } from './app.js';
|
|
3
|
-
|
|
4
|
-
const port = parseInt(process.env.PORT || '3001', 10);
|
|
5
|
-
|
|
6
|
-
console.log(`Leaderboard service starting on port ${port}`);
|
|
7
|
-
|
|
8
|
-
serve({
|
|
9
|
-
fetch: app.fetch,
|
|
10
|
-
port,
|
|
11
|
-
});
|
|
12
|
-
|
|
13
|
-
console.log(`Leaderboard service running at http://localhost:${port}`);
|
|
@@ -1,124 +0,0 @@
|
|
|
1
|
-
// WebSocket client utilities for real-time updates
|
|
2
|
-
|
|
3
|
-
export interface LiveUpdate {
|
|
4
|
-
type: 'run_update' | 'run_complete' | 'run_failed' | 'metrics_update';
|
|
5
|
-
runId: string;
|
|
6
|
-
data: unknown;
|
|
7
|
-
timestamp: string;
|
|
8
|
-
}
|
|
9
|
-
|
|
10
|
-
export type UpdateCallback = (update: LiveUpdate) => void;
|
|
11
|
-
|
|
12
|
-
export class LiveConnection {
|
|
13
|
-
private eventSource: EventSource | null = null;
|
|
14
|
-
private callbacks: Map<string, UpdateCallback[]> = new Map();
|
|
15
|
-
private reconnectAttempts = 0;
|
|
16
|
-
private maxReconnectAttempts = 5;
|
|
17
|
-
private reconnectDelay = 1000;
|
|
18
|
-
|
|
19
|
-
constructor(private baseUrl: string = '/api/live') {}
|
|
20
|
-
|
|
21
|
-
connect(runId?: string): void {
|
|
22
|
-
const url = runId ? `${this.baseUrl}/stream/${runId}` : `${this.baseUrl}/stream`;
|
|
23
|
-
|
|
24
|
-
this.eventSource = new EventSource(url);
|
|
25
|
-
|
|
26
|
-
this.eventSource.onopen = () => {
|
|
27
|
-
this.reconnectAttempts = 0;
|
|
28
|
-
this.emit('connected', { type: 'run_update', runId: '', data: null, timestamp: new Date().toISOString() });
|
|
29
|
-
};
|
|
30
|
-
|
|
31
|
-
this.eventSource.addEventListener('update', (event) => {
|
|
32
|
-
const messageEvent = event as MessageEvent;
|
|
33
|
-
const data = JSON.parse(messageEvent.data);
|
|
34
|
-
this.emit('update', {
|
|
35
|
-
type: 'run_update',
|
|
36
|
-
runId: data.id || runId || '',
|
|
37
|
-
data,
|
|
38
|
-
timestamp: new Date().toISOString(),
|
|
39
|
-
});
|
|
40
|
-
});
|
|
41
|
-
|
|
42
|
-
this.eventSource.addEventListener('end', (event) => {
|
|
43
|
-
const messageEvent = event as MessageEvent;
|
|
44
|
-
const data = JSON.parse(messageEvent.data);
|
|
45
|
-
this.emit('end', {
|
|
46
|
-
type: data.status === 'completed' ? 'run_complete' : 'run_failed',
|
|
47
|
-
runId: data.id || runId || '',
|
|
48
|
-
data,
|
|
49
|
-
timestamp: new Date().toISOString(),
|
|
50
|
-
});
|
|
51
|
-
this.disconnect();
|
|
52
|
-
});
|
|
53
|
-
|
|
54
|
-
this.eventSource.onerror = () => {
|
|
55
|
-
this.emit('error', { type: 'run_failed', runId: '', data: { error: 'Connection error' }, timestamp: new Date().toISOString() });
|
|
56
|
-
this.handleReconnect(runId);
|
|
57
|
-
};
|
|
58
|
-
}
|
|
59
|
-
|
|
60
|
-
private handleReconnect(runId?: string): void {
|
|
61
|
-
if (this.reconnectAttempts >= this.maxReconnectAttempts) {
|
|
62
|
-
this.emit('disconnected', { type: 'run_failed', runId: '', data: { error: 'Max reconnect attempts reached' }, timestamp: new Date().toISOString() });
|
|
63
|
-
return;
|
|
64
|
-
}
|
|
65
|
-
|
|
66
|
-
this.reconnectAttempts++;
|
|
67
|
-
const delay = this.reconnectDelay * Math.pow(2, this.reconnectAttempts - 1);
|
|
68
|
-
|
|
69
|
-
setTimeout(() => {
|
|
70
|
-
this.connect(runId);
|
|
71
|
-
}, delay);
|
|
72
|
-
}
|
|
73
|
-
|
|
74
|
-
disconnect(): void {
|
|
75
|
-
if (this.eventSource) {
|
|
76
|
-
this.eventSource.close();
|
|
77
|
-
this.eventSource = null;
|
|
78
|
-
}
|
|
79
|
-
}
|
|
80
|
-
|
|
81
|
-
on(event: string, callback: UpdateCallback): () => void {
|
|
82
|
-
if (!this.callbacks.has(event)) {
|
|
83
|
-
this.callbacks.set(event, []);
|
|
84
|
-
}
|
|
85
|
-
this.callbacks.get(event)!.push(callback);
|
|
86
|
-
|
|
87
|
-
// Return unsubscribe function
|
|
88
|
-
return () => {
|
|
89
|
-
const callbacks = this.callbacks.get(event);
|
|
90
|
-
if (callbacks) {
|
|
91
|
-
const index = callbacks.indexOf(callback);
|
|
92
|
-
if (index > -1) {
|
|
93
|
-
callbacks.splice(index, 1);
|
|
94
|
-
}
|
|
95
|
-
}
|
|
96
|
-
};
|
|
97
|
-
}
|
|
98
|
-
|
|
99
|
-
private emit(event: string, update: LiveUpdate): void {
|
|
100
|
-
const callbacks = this.callbacks.get(event);
|
|
101
|
-
if (callbacks) {
|
|
102
|
-
callbacks.forEach((cb) => cb(update));
|
|
103
|
-
}
|
|
104
|
-
|
|
105
|
-
// Also emit to 'all' listeners
|
|
106
|
-
const allCallbacks = this.callbacks.get('all');
|
|
107
|
-
if (allCallbacks) {
|
|
108
|
-
allCallbacks.forEach((cb) => cb(update));
|
|
109
|
-
}
|
|
110
|
-
}
|
|
111
|
-
}
|
|
112
|
-
|
|
113
|
-
// React hook for live updates
|
|
114
|
-
export function useLiveUpdates(runId?: string, apiUrl?: string) {
|
|
115
|
-
const connection = new LiveConnection(apiUrl);
|
|
116
|
-
|
|
117
|
-
return {
|
|
118
|
-
connect: () => connection.connect(runId),
|
|
119
|
-
disconnect: () => connection.disconnect(),
|
|
120
|
-
onUpdate: (callback: UpdateCallback) => connection.on('update', callback),
|
|
121
|
-
onComplete: (callback: UpdateCallback) => connection.on('end', callback),
|
|
122
|
-
onError: (callback: UpdateCallback) => connection.on('error', callback),
|
|
123
|
-
};
|
|
124
|
-
}
|