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
|
@@ -1,153 +0,0 @@
|
|
|
1
|
-
/**
|
|
2
|
-
* Task Variation System
|
|
3
|
-
*
|
|
4
|
-
* Generates dynamic parameters for each benchmark run to ensure
|
|
5
|
-
* test diversity and prevent overfitting to specific patterns.
|
|
6
|
-
*/
|
|
7
|
-
|
|
8
|
-
export interface TaskVariation {
|
|
9
|
-
seed: number;
|
|
10
|
-
entityNames: EntityNames;
|
|
11
|
-
apiEndpoints: ApiEndpoints;
|
|
12
|
-
dataSchemas: DataSchemas;
|
|
13
|
-
businessRules: BusinessRules;
|
|
14
|
-
}
|
|
15
|
-
|
|
16
|
-
export interface EntityNames {
|
|
17
|
-
user: string;
|
|
18
|
-
product: string;
|
|
19
|
-
order: string;
|
|
20
|
-
payment: string;
|
|
21
|
-
settings: string;
|
|
22
|
-
}
|
|
23
|
-
|
|
24
|
-
export interface ApiEndpoints {
|
|
25
|
-
prefix: string;
|
|
26
|
-
version: string;
|
|
27
|
-
}
|
|
28
|
-
|
|
29
|
-
export interface DataSchemas {
|
|
30
|
-
idType: 'uuid' | 'nanoid' | 'cuid' | 'incremental';
|
|
31
|
-
timestampFormat: 'iso' | 'unix' | 'epoch_ms';
|
|
32
|
-
currencyFormat: 'cents' | 'decimal';
|
|
33
|
-
}
|
|
34
|
-
|
|
35
|
-
export interface BusinessRules {
|
|
36
|
-
maxItemsPerPage: number;
|
|
37
|
-
sessionTimeout: number;
|
|
38
|
-
passwordMinLength: number;
|
|
39
|
-
otpExpiry: number;
|
|
40
|
-
}
|
|
41
|
-
|
|
42
|
-
// Name pools for entity variation
|
|
43
|
-
const USER_NAMES = ['User', 'Member', 'Account', 'Profile', 'Customer'];
|
|
44
|
-
const PRODUCT_NAMES = ['Product', 'Item', 'Listing', 'Article', 'Goods'];
|
|
45
|
-
const ORDER_NAMES = ['Order', 'Purchase', 'Transaction', 'Booking', 'Request'];
|
|
46
|
-
const PAYMENT_NAMES = ['Payment', 'Charge', 'Invoice', 'Bill', 'Receipt'];
|
|
47
|
-
const SETTINGS_NAMES = ['Settings', 'Preferences', 'Config', 'Options', 'Profile'];
|
|
48
|
-
|
|
49
|
-
const API_PREFIXES = ['api', 'v1', 'rest', 'service', 'backend'];
|
|
50
|
-
const API_VERSIONS = ['v1', 'v2', 'v3', '2024-01', '2025-01'];
|
|
51
|
-
|
|
52
|
-
/**
|
|
53
|
-
* Seeded random number generator for reproducibility
|
|
54
|
-
*/
|
|
55
|
-
class SeededRandom {
|
|
56
|
-
private seed: number;
|
|
57
|
-
|
|
58
|
-
constructor(seed: number) {
|
|
59
|
-
this.seed = seed;
|
|
60
|
-
}
|
|
61
|
-
|
|
62
|
-
next(): number {
|
|
63
|
-
this.seed = (this.seed * 1103515245 + 12345) & 0x7fffffff;
|
|
64
|
-
return this.seed / 0x7fffffff;
|
|
65
|
-
}
|
|
66
|
-
|
|
67
|
-
pick<T>(array: T[]): T {
|
|
68
|
-
return array[Math.floor(this.next() * array.length)];
|
|
69
|
-
}
|
|
70
|
-
|
|
71
|
-
range(min: number, max: number): number {
|
|
72
|
-
return Math.floor(this.next() * (max - min + 1)) + min;
|
|
73
|
-
}
|
|
74
|
-
}
|
|
75
|
-
|
|
76
|
-
/**
|
|
77
|
-
* Generate a task variation based on a seed
|
|
78
|
-
*/
|
|
79
|
-
export function generateVariation(seed?: number): TaskVariation {
|
|
80
|
-
const actualSeed = seed ?? Date.now();
|
|
81
|
-
const rng = new SeededRandom(actualSeed);
|
|
82
|
-
|
|
83
|
-
return {
|
|
84
|
-
seed: actualSeed,
|
|
85
|
-
entityNames: {
|
|
86
|
-
user: rng.pick(USER_NAMES),
|
|
87
|
-
product: rng.pick(PRODUCT_NAMES),
|
|
88
|
-
order: rng.pick(ORDER_NAMES),
|
|
89
|
-
payment: rng.pick(PAYMENT_NAMES),
|
|
90
|
-
settings: rng.pick(SETTINGS_NAMES),
|
|
91
|
-
},
|
|
92
|
-
apiEndpoints: {
|
|
93
|
-
prefix: rng.pick(API_PREFIXES),
|
|
94
|
-
version: rng.pick(API_VERSIONS),
|
|
95
|
-
},
|
|
96
|
-
dataSchemas: {
|
|
97
|
-
idType: rng.pick(['uuid', 'nanoid', 'cuid', 'incremental'] as const),
|
|
98
|
-
timestampFormat: rng.pick(['iso', 'unix', 'epoch_ms'] as const),
|
|
99
|
-
currencyFormat: rng.pick(['cents', 'decimal'] as const),
|
|
100
|
-
},
|
|
101
|
-
businessRules: {
|
|
102
|
-
maxItemsPerPage: rng.pick([10, 20, 25, 50, 100]),
|
|
103
|
-
sessionTimeout: rng.pick([900, 1800, 3600, 7200]), // seconds
|
|
104
|
-
passwordMinLength: rng.pick([8, 10, 12, 14]),
|
|
105
|
-
otpExpiry: rng.pick([60, 120, 180, 300]), // seconds
|
|
106
|
-
},
|
|
107
|
-
};
|
|
108
|
-
}
|
|
109
|
-
|
|
110
|
-
/**
|
|
111
|
-
* Apply variation to a task prompt
|
|
112
|
-
*/
|
|
113
|
-
export function applyVariation(prompt: string, variation: TaskVariation): string {
|
|
114
|
-
let result = prompt;
|
|
115
|
-
|
|
116
|
-
// Replace entity names
|
|
117
|
-
result = result.replace(/\bUser\b/g, variation.entityNames.user);
|
|
118
|
-
result = result.replace(/\bProduct\b/g, variation.entityNames.product);
|
|
119
|
-
result = result.replace(/\bOrder\b/g, variation.entityNames.order);
|
|
120
|
-
result = result.replace(/\bPayment\b/g, variation.entityNames.payment);
|
|
121
|
-
result = result.replace(/\bSettings\b/g, variation.entityNames.settings);
|
|
122
|
-
|
|
123
|
-
// Replace API endpoints
|
|
124
|
-
result = result.replace(/\/api\//g, `/${variation.apiEndpoints.prefix}/`);
|
|
125
|
-
|
|
126
|
-
// Add variation context header
|
|
127
|
-
const variationHeader = `
|
|
128
|
-
<!-- Task Variation (Seed: ${variation.seed}) -->
|
|
129
|
-
<!-- Entity Naming: ${variation.entityNames.user}, ${variation.entityNames.product} -->
|
|
130
|
-
<!-- API: /${variation.apiEndpoints.prefix}/${variation.apiEndpoints.version} -->
|
|
131
|
-
<!-- ID Type: ${variation.dataSchemas.idType} -->
|
|
132
|
-
<!-- Pagination: ${variation.businessRules.maxItemsPerPage} items/page -->
|
|
133
|
-
|
|
134
|
-
`;
|
|
135
|
-
|
|
136
|
-
return variationHeader + result;
|
|
137
|
-
}
|
|
138
|
-
|
|
139
|
-
/**
|
|
140
|
-
* Generate variation metadata for result tracking
|
|
141
|
-
*/
|
|
142
|
-
export function variationMetadata(variation: TaskVariation): Record<string, string | number> {
|
|
143
|
-
return {
|
|
144
|
-
seed: variation.seed,
|
|
145
|
-
userEntity: variation.entityNames.user,
|
|
146
|
-
productEntity: variation.entityNames.product,
|
|
147
|
-
apiPrefix: variation.apiEndpoints.prefix,
|
|
148
|
-
idType: variation.dataSchemas.idType,
|
|
149
|
-
pageSize: variation.businessRules.maxItemsPerPage,
|
|
150
|
-
};
|
|
151
|
-
}
|
|
152
|
-
|
|
153
|
-
export default { generateVariation, applyVariation, variationMetadata };
|
|
@@ -1,258 +0,0 @@
|
|
|
1
|
-
import * as fs from 'fs/promises';
|
|
2
|
-
import * as path from 'path';
|
|
3
|
-
import { watch } from 'fs';
|
|
4
|
-
import { parse as parseYaml } from 'yaml';
|
|
5
|
-
import Ajv from 'ajv';
|
|
6
|
-
// eslint-disable-next-line @typescript-eslint/no-require-imports
|
|
7
|
-
const taskSchema = require('./schema/task.schema.json');
|
|
8
|
-
import { EventEmitter } from 'events';
|
|
9
|
-
|
|
10
|
-
export interface Task {
|
|
11
|
-
id: string;
|
|
12
|
-
name: string;
|
|
13
|
-
category: string;
|
|
14
|
-
subcategory?: string;
|
|
15
|
-
description: string;
|
|
16
|
-
difficulty: 'easy' | 'medium' | 'hard';
|
|
17
|
-
stack?: string;
|
|
18
|
-
timeout: number;
|
|
19
|
-
tokenLimit: number;
|
|
20
|
-
template?: string;
|
|
21
|
-
promptFile: string;
|
|
22
|
-
tests: {
|
|
23
|
-
functional?: string;
|
|
24
|
-
visual?: string;
|
|
25
|
-
security?: string;
|
|
26
|
-
};
|
|
27
|
-
docker?: {
|
|
28
|
-
compose?: string;
|
|
29
|
-
image?: string;
|
|
30
|
-
};
|
|
31
|
-
weight: number;
|
|
32
|
-
tags: string[];
|
|
33
|
-
}
|
|
34
|
-
|
|
35
|
-
const ajv = new Ajv();
|
|
36
|
-
const validateTask = ajv.compile(taskSchema);
|
|
37
|
-
|
|
38
|
-
const TASKS_DIR = path.resolve(process.cwd(), 'tasks');
|
|
39
|
-
|
|
40
|
-
/**
|
|
41
|
-
* Load a single task by ID (e.g., "saas-core/auth/supabase-oauth")
|
|
42
|
-
*/
|
|
43
|
-
export async function loadTask(taskId: string): Promise<Task | null> {
|
|
44
|
-
const taskPath = path.join(TASKS_DIR, taskId, 'task.yaml');
|
|
45
|
-
|
|
46
|
-
try {
|
|
47
|
-
const content = await fs.readFile(taskPath, 'utf-8');
|
|
48
|
-
const raw = parseYaml(content);
|
|
49
|
-
|
|
50
|
-
if (!validateTask(raw)) {
|
|
51
|
-
console.error(`Invalid task.yaml at ${taskPath}:`, validateTask.errors);
|
|
52
|
-
return null;
|
|
53
|
-
}
|
|
54
|
-
|
|
55
|
-
const taskData = raw as Record<string, unknown>;
|
|
56
|
-
return {
|
|
57
|
-
id: taskId,
|
|
58
|
-
name: taskData.name as string,
|
|
59
|
-
category: taskData.category as string,
|
|
60
|
-
subcategory: taskData.subcategory as string | undefined,
|
|
61
|
-
description: taskData.description as string,
|
|
62
|
-
difficulty: taskData.difficulty as 'easy' | 'medium' | 'hard',
|
|
63
|
-
stack: taskData.stack as string | undefined,
|
|
64
|
-
timeout: (taskData.timeout as number) || 300,
|
|
65
|
-
tokenLimit: (taskData.tokenLimit as number) || 100000,
|
|
66
|
-
template: taskData.template as string | undefined,
|
|
67
|
-
promptFile: path.join(TASKS_DIR, taskId, (taskData.promptFile as string) || 'PROMPT.md'),
|
|
68
|
-
tests: {
|
|
69
|
-
functional: (taskData.tests as Record<string, string>)?.functional
|
|
70
|
-
? path.join(TASKS_DIR, taskId, (taskData.tests as Record<string, string>).functional)
|
|
71
|
-
: undefined,
|
|
72
|
-
visual: (taskData.tests as Record<string, string>)?.visual
|
|
73
|
-
? path.join(TASKS_DIR, taskId, (taskData.tests as Record<string, string>).visual)
|
|
74
|
-
: undefined,
|
|
75
|
-
security: (taskData.tests as Record<string, string>)?.security
|
|
76
|
-
? path.join(TASKS_DIR, taskId, (taskData.tests as Record<string, string>).security)
|
|
77
|
-
: undefined,
|
|
78
|
-
},
|
|
79
|
-
docker: taskData.docker as { compose?: string; image?: string } | undefined,
|
|
80
|
-
weight: (taskData.weight as number) || 1.0,
|
|
81
|
-
tags: (taskData.tags as string[]) || []
|
|
82
|
-
};
|
|
83
|
-
} catch (error) {
|
|
84
|
-
if ((error as NodeJS.ErrnoException).code === 'ENOENT') {
|
|
85
|
-
return null;
|
|
86
|
-
}
|
|
87
|
-
throw error;
|
|
88
|
-
}
|
|
89
|
-
}
|
|
90
|
-
|
|
91
|
-
/**
|
|
92
|
-
* Discover and load all tasks from the tasks directory.
|
|
93
|
-
* Tasks are modular - just add a new folder with task.yaml to register.
|
|
94
|
-
*/
|
|
95
|
-
export async function loadAllTasks(): Promise<Task[]> {
|
|
96
|
-
const tasks: Task[] = [];
|
|
97
|
-
|
|
98
|
-
async function scanDirectory(dir: string, prefix: string = ''): Promise<void> {
|
|
99
|
-
const entries = await fs.readdir(dir, { withFileTypes: true });
|
|
100
|
-
|
|
101
|
-
for (const entry of entries) {
|
|
102
|
-
if (!entry.isDirectory()) continue;
|
|
103
|
-
|
|
104
|
-
const fullPath = path.join(dir, entry.name);
|
|
105
|
-
const taskId = prefix ? `${prefix}/${entry.name}` : entry.name;
|
|
106
|
-
const taskYaml = path.join(fullPath, 'task.yaml');
|
|
107
|
-
|
|
108
|
-
try {
|
|
109
|
-
await fs.access(taskYaml);
|
|
110
|
-
const task = await loadTask(taskId);
|
|
111
|
-
if (task) tasks.push(task);
|
|
112
|
-
} catch {
|
|
113
|
-
// No task.yaml, recurse into subdirectory
|
|
114
|
-
await scanDirectory(fullPath, taskId);
|
|
115
|
-
}
|
|
116
|
-
}
|
|
117
|
-
}
|
|
118
|
-
|
|
119
|
-
try {
|
|
120
|
-
await fs.access(TASKS_DIR);
|
|
121
|
-
await scanDirectory(TASKS_DIR);
|
|
122
|
-
} catch {
|
|
123
|
-
// tasks directory doesn't exist yet
|
|
124
|
-
}
|
|
125
|
-
|
|
126
|
-
return tasks.sort((a, b) => {
|
|
127
|
-
// Sort by category, then by difficulty
|
|
128
|
-
if (a.category !== b.category) return a.category.localeCompare(b.category);
|
|
129
|
-
const diffOrder = { easy: 0, medium: 1, hard: 2 };
|
|
130
|
-
return diffOrder[a.difficulty] - diffOrder[b.difficulty];
|
|
131
|
-
});
|
|
132
|
-
}
|
|
133
|
-
|
|
134
|
-
/**
|
|
135
|
-
* Get all unique categories from loaded tasks
|
|
136
|
-
*/
|
|
137
|
-
export async function getCategories(): Promise<string[]> {
|
|
138
|
-
const tasks = await loadAllTasks();
|
|
139
|
-
return [...new Set(tasks.map(t => t.category))].sort();
|
|
140
|
-
}
|
|
141
|
-
|
|
142
|
-
/**
|
|
143
|
-
* Load tasks filtered by options (for composable benchmark subsets)
|
|
144
|
-
*/
|
|
145
|
-
export async function loadTasksFiltered(options: {
|
|
146
|
-
categories?: string[];
|
|
147
|
-
difficulties?: ('easy' | 'medium' | 'hard')[];
|
|
148
|
-
tags?: string[];
|
|
149
|
-
limit?: number;
|
|
150
|
-
}): Promise<Task[]> {
|
|
151
|
-
let tasks = await loadAllTasks();
|
|
152
|
-
|
|
153
|
-
if (options.categories?.length) {
|
|
154
|
-
tasks = tasks.filter(t => options.categories!.includes(t.category));
|
|
155
|
-
}
|
|
156
|
-
|
|
157
|
-
if (options.difficulties?.length) {
|
|
158
|
-
tasks = tasks.filter(t => options.difficulties!.includes(t.difficulty));
|
|
159
|
-
}
|
|
160
|
-
|
|
161
|
-
if (options.tags?.length) {
|
|
162
|
-
tasks = tasks.filter(t => options.tags!.some(tag => t.tags.includes(tag)));
|
|
163
|
-
}
|
|
164
|
-
|
|
165
|
-
if (options.limit) {
|
|
166
|
-
tasks = tasks.slice(0, options.limit);
|
|
167
|
-
}
|
|
168
|
-
|
|
169
|
-
return tasks;
|
|
170
|
-
}
|
|
171
|
-
|
|
172
|
-
/**
|
|
173
|
-
* Hot-reload task watcher for development.
|
|
174
|
-
* Watches the tasks directory and emits events when tasks change.
|
|
175
|
-
*/
|
|
176
|
-
export class TaskWatcher extends EventEmitter {
|
|
177
|
-
private watchers: ReturnType<typeof watch>[] = [];
|
|
178
|
-
private taskCache = new Map<string, Task>();
|
|
179
|
-
private debounceTimers = new Map<string, NodeJS.Timeout>();
|
|
180
|
-
|
|
181
|
-
async start(): Promise<void> {
|
|
182
|
-
try {
|
|
183
|
-
await fs.access(TASKS_DIR);
|
|
184
|
-
} catch {
|
|
185
|
-
await fs.mkdir(TASKS_DIR, { recursive: true });
|
|
186
|
-
}
|
|
187
|
-
|
|
188
|
-
// Initial load
|
|
189
|
-
const tasks = await loadAllTasks();
|
|
190
|
-
for (const task of tasks) {
|
|
191
|
-
this.taskCache.set(task.id, task);
|
|
192
|
-
}
|
|
193
|
-
|
|
194
|
-
// Watch for changes
|
|
195
|
-
this.watchDirectory(TASKS_DIR);
|
|
196
|
-
this.emit('ready', { taskCount: tasks.length });
|
|
197
|
-
}
|
|
198
|
-
|
|
199
|
-
private watchDirectory(dir: string): void {
|
|
200
|
-
const watcher = watch(dir, { recursive: true }, async (eventType, filename) => {
|
|
201
|
-
if (!filename) return;
|
|
202
|
-
|
|
203
|
-
// Debounce rapid changes
|
|
204
|
-
const key = filename;
|
|
205
|
-
const existing = this.debounceTimers.get(key);
|
|
206
|
-
if (existing) clearTimeout(existing);
|
|
207
|
-
|
|
208
|
-
this.debounceTimers.set(key, setTimeout(async () => {
|
|
209
|
-
await this.handleChange(filename);
|
|
210
|
-
this.debounceTimers.delete(key);
|
|
211
|
-
}, 100));
|
|
212
|
-
});
|
|
213
|
-
|
|
214
|
-
this.watchers.push(watcher);
|
|
215
|
-
}
|
|
216
|
-
|
|
217
|
-
private async handleChange(filename: string): Promise<void> {
|
|
218
|
-
// Extract task ID from path
|
|
219
|
-
const parts = filename.split(path.sep);
|
|
220
|
-
if (!parts.includes('task.yaml') && !filename.endsWith('task.yaml')) {
|
|
221
|
-
return;
|
|
222
|
-
}
|
|
223
|
-
|
|
224
|
-
const taskId = parts.slice(0, -1).join('/');
|
|
225
|
-
|
|
226
|
-
try {
|
|
227
|
-
const task = await loadTask(taskId);
|
|
228
|
-
if (task) {
|
|
229
|
-
const isNew = !this.taskCache.has(taskId);
|
|
230
|
-
this.taskCache.set(taskId, task);
|
|
231
|
-
this.emit(isNew ? 'added' : 'changed', task);
|
|
232
|
-
}
|
|
233
|
-
} catch {
|
|
234
|
-
if (this.taskCache.has(taskId)) {
|
|
235
|
-
const task = this.taskCache.get(taskId);
|
|
236
|
-
this.taskCache.delete(taskId);
|
|
237
|
-
this.emit('removed', task);
|
|
238
|
-
}
|
|
239
|
-
}
|
|
240
|
-
}
|
|
241
|
-
|
|
242
|
-
getTasks(): Task[] {
|
|
243
|
-
return [...this.taskCache.values()];
|
|
244
|
-
}
|
|
245
|
-
|
|
246
|
-
getTask(id: string): Task | undefined {
|
|
247
|
-
return this.taskCache.get(id);
|
|
248
|
-
}
|
|
249
|
-
|
|
250
|
-
stop(): void {
|
|
251
|
-
for (const watcher of this.watchers) {
|
|
252
|
-
watcher.close();
|
|
253
|
-
}
|
|
254
|
-
this.watchers = [];
|
|
255
|
-
this.debounceTimers.forEach(timer => clearTimeout(timer));
|
|
256
|
-
this.debounceTimers.clear();
|
|
257
|
-
}
|
|
258
|
-
}
|
|
@@ -1,222 +0,0 @@
|
|
|
1
|
-
/**
|
|
2
|
-
* Reporter module for sending live updates to the leaderboard service.
|
|
3
|
-
* Streams progress metrics during task execution.
|
|
4
|
-
*/
|
|
5
|
-
|
|
6
|
-
export interface ReporterConfig {
|
|
7
|
-
apiUrl: string;
|
|
8
|
-
enabled: boolean;
|
|
9
|
-
updateInterval?: number;
|
|
10
|
-
}
|
|
11
|
-
|
|
12
|
-
export interface RunMetrics {
|
|
13
|
-
tokensUsed: number;
|
|
14
|
-
filesRead: number;
|
|
15
|
-
filesWritten: number;
|
|
16
|
-
testsPass: number;
|
|
17
|
-
testsFail: number;
|
|
18
|
-
elapsedMs: number;
|
|
19
|
-
}
|
|
20
|
-
|
|
21
|
-
export interface RunUpdate {
|
|
22
|
-
status?: 'initializing' | 'running' | 'evaluating' | 'completed' | 'failed';
|
|
23
|
-
progress?: number;
|
|
24
|
-
currentStep?: string;
|
|
25
|
-
metrics?: Partial<RunMetrics>;
|
|
26
|
-
logs?: Array<{ timestamp: string; message: string }>;
|
|
27
|
-
}
|
|
28
|
-
|
|
29
|
-
export class LiveReporter {
|
|
30
|
-
private runId: string | null = null;
|
|
31
|
-
private intervalId: ReturnType<typeof setInterval> | null = null;
|
|
32
|
-
private metrics: RunMetrics = {
|
|
33
|
-
tokensUsed: 0,
|
|
34
|
-
filesRead: 0,
|
|
35
|
-
filesWritten: 0,
|
|
36
|
-
testsPass: 0,
|
|
37
|
-
testsFail: 0,
|
|
38
|
-
elapsedMs: 0,
|
|
39
|
-
};
|
|
40
|
-
private startTime: number = 0;
|
|
41
|
-
private logs: Array<{ timestamp: string; message: string }> = [];
|
|
42
|
-
|
|
43
|
-
constructor(private config: ReporterConfig) {
|
|
44
|
-
if (!config.updateInterval) {
|
|
45
|
-
this.config.updateInterval = 5000; // Default 5 seconds
|
|
46
|
-
}
|
|
47
|
-
}
|
|
48
|
-
|
|
49
|
-
async start(agentName: string, taskId: string): Promise<string | null> {
|
|
50
|
-
if (!this.config.enabled) {
|
|
51
|
-
return null;
|
|
52
|
-
}
|
|
53
|
-
|
|
54
|
-
try {
|
|
55
|
-
const response = await fetch(`${this.config.apiUrl}/runs`, {
|
|
56
|
-
method: 'POST',
|
|
57
|
-
headers: { 'Content-Type': 'application/json' },
|
|
58
|
-
body: JSON.stringify({ agentName, taskId }),
|
|
59
|
-
});
|
|
60
|
-
|
|
61
|
-
if (!response.ok) {
|
|
62
|
-
console.error('Failed to start live reporting');
|
|
63
|
-
return null;
|
|
64
|
-
}
|
|
65
|
-
|
|
66
|
-
const data = await response.json() as { id: string };
|
|
67
|
-
this.runId = data.id;
|
|
68
|
-
this.startTime = Date.now();
|
|
69
|
-
this.metrics = {
|
|
70
|
-
tokensUsed: 0,
|
|
71
|
-
filesRead: 0,
|
|
72
|
-
filesWritten: 0,
|
|
73
|
-
testsPass: 0,
|
|
74
|
-
testsFail: 0,
|
|
75
|
-
elapsedMs: 0,
|
|
76
|
-
};
|
|
77
|
-
|
|
78
|
-
// Start periodic updates
|
|
79
|
-
this.intervalId = setInterval(() => {
|
|
80
|
-
this.sendUpdate({
|
|
81
|
-
metrics: {
|
|
82
|
-
...this.metrics,
|
|
83
|
-
elapsedMs: Date.now() - this.startTime,
|
|
84
|
-
},
|
|
85
|
-
});
|
|
86
|
-
}, this.config.updateInterval);
|
|
87
|
-
|
|
88
|
-
return this.runId;
|
|
89
|
-
} catch (error) {
|
|
90
|
-
console.error('Error starting live reporter:', error);
|
|
91
|
-
return null;
|
|
92
|
-
}
|
|
93
|
-
}
|
|
94
|
-
|
|
95
|
-
async sendUpdate(update: RunUpdate): Promise<void> {
|
|
96
|
-
if (!this.config.enabled || !this.runId) {
|
|
97
|
-
return;
|
|
98
|
-
}
|
|
99
|
-
|
|
100
|
-
try {
|
|
101
|
-
// Send any pending logs
|
|
102
|
-
if (this.logs.length > 0) {
|
|
103
|
-
update.logs = [...this.logs];
|
|
104
|
-
this.logs = [];
|
|
105
|
-
}
|
|
106
|
-
|
|
107
|
-
await fetch(`${this.config.apiUrl}/runs/${this.runId}`, {
|
|
108
|
-
method: 'PATCH',
|
|
109
|
-
headers: { 'Content-Type': 'application/json' },
|
|
110
|
-
body: JSON.stringify(update),
|
|
111
|
-
});
|
|
112
|
-
} catch (error) {
|
|
113
|
-
// Silently fail - don't interrupt task execution
|
|
114
|
-
console.error('Error sending update:', error);
|
|
115
|
-
}
|
|
116
|
-
}
|
|
117
|
-
|
|
118
|
-
log(message: string): void {
|
|
119
|
-
this.logs.push({
|
|
120
|
-
timestamp: new Date().toISOString(),
|
|
121
|
-
message,
|
|
122
|
-
});
|
|
123
|
-
}
|
|
124
|
-
|
|
125
|
-
updateMetrics(updates: Partial<RunMetrics>): void {
|
|
126
|
-
this.metrics = { ...this.metrics, ...updates };
|
|
127
|
-
}
|
|
128
|
-
|
|
129
|
-
incrementTokens(count: number): void {
|
|
130
|
-
this.metrics.tokensUsed += count;
|
|
131
|
-
}
|
|
132
|
-
|
|
133
|
-
incrementFilesRead(): void {
|
|
134
|
-
this.metrics.filesRead++;
|
|
135
|
-
}
|
|
136
|
-
|
|
137
|
-
incrementFilesWritten(): void {
|
|
138
|
-
this.metrics.filesWritten++;
|
|
139
|
-
}
|
|
140
|
-
|
|
141
|
-
setTestResults(pass: number, fail: number): void {
|
|
142
|
-
this.metrics.testsPass = pass;
|
|
143
|
-
this.metrics.testsFail = fail;
|
|
144
|
-
}
|
|
145
|
-
|
|
146
|
-
async setStatus(
|
|
147
|
-
status: 'initializing' | 'running' | 'evaluating' | 'completed' | 'failed',
|
|
148
|
-
progress?: number,
|
|
149
|
-
currentStep?: string
|
|
150
|
-
): Promise<void> {
|
|
151
|
-
await this.sendUpdate({ status, progress, currentStep });
|
|
152
|
-
}
|
|
153
|
-
|
|
154
|
-
async complete(finalMetrics?: Partial<RunMetrics>): Promise<void> {
|
|
155
|
-
if (this.intervalId) {
|
|
156
|
-
clearInterval(this.intervalId);
|
|
157
|
-
this.intervalId = null;
|
|
158
|
-
}
|
|
159
|
-
|
|
160
|
-
if (finalMetrics) {
|
|
161
|
-
this.metrics = { ...this.metrics, ...finalMetrics };
|
|
162
|
-
}
|
|
163
|
-
|
|
164
|
-
await this.sendUpdate({
|
|
165
|
-
status: 'completed',
|
|
166
|
-
progress: 100,
|
|
167
|
-
currentStep: 'Complete',
|
|
168
|
-
metrics: {
|
|
169
|
-
...this.metrics,
|
|
170
|
-
elapsedMs: Date.now() - this.startTime,
|
|
171
|
-
},
|
|
172
|
-
});
|
|
173
|
-
}
|
|
174
|
-
|
|
175
|
-
async fail(error: string): Promise<void> {
|
|
176
|
-
if (this.intervalId) {
|
|
177
|
-
clearInterval(this.intervalId);
|
|
178
|
-
this.intervalId = null;
|
|
179
|
-
}
|
|
180
|
-
|
|
181
|
-
this.log(`Error: ${error}`);
|
|
182
|
-
|
|
183
|
-
await this.sendUpdate({
|
|
184
|
-
status: 'failed',
|
|
185
|
-
currentStep: 'Failed',
|
|
186
|
-
metrics: {
|
|
187
|
-
...this.metrics,
|
|
188
|
-
elapsedMs: Date.now() - this.startTime,
|
|
189
|
-
},
|
|
190
|
-
});
|
|
191
|
-
}
|
|
192
|
-
|
|
193
|
-
async cleanup(): Promise<void> {
|
|
194
|
-
if (this.intervalId) {
|
|
195
|
-
clearInterval(this.intervalId);
|
|
196
|
-
this.intervalId = null;
|
|
197
|
-
}
|
|
198
|
-
|
|
199
|
-
if (this.runId && this.config.enabled) {
|
|
200
|
-
try {
|
|
201
|
-
await fetch(`${this.config.apiUrl}/runs/${this.runId}`, {
|
|
202
|
-
method: 'DELETE',
|
|
203
|
-
});
|
|
204
|
-
} catch {
|
|
205
|
-
// Ignore cleanup errors
|
|
206
|
-
}
|
|
207
|
-
}
|
|
208
|
-
|
|
209
|
-
this.runId = null;
|
|
210
|
-
}
|
|
211
|
-
}
|
|
212
|
-
|
|
213
|
-
// Factory function for creating reporter
|
|
214
|
-
export function createReporter(options?: {
|
|
215
|
-
apiUrl?: string;
|
|
216
|
-
enabled?: boolean;
|
|
217
|
-
}): LiveReporter {
|
|
218
|
-
return new LiveReporter({
|
|
219
|
-
apiUrl: options?.apiUrl || process.env.LEADERBOARD_API_URL || 'http://localhost:3001/api/live',
|
|
220
|
-
enabled: options?.enabled ?? (process.env.LIVE_REPORTING === 'true'),
|
|
221
|
-
});
|
|
222
|
-
}
|