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
|
@@ -1,293 +0,0 @@
|
|
|
1
|
-
// React component for submitting evaluation results
|
|
2
|
-
// Allows users to submit their agent's results to the leaderboard
|
|
3
|
-
|
|
4
|
-
import { useState } from 'react';
|
|
5
|
-
|
|
6
|
-
export interface SubmitFormProps {
|
|
7
|
-
apiUrl?: string;
|
|
8
|
-
onSubmit?: (submission: SubmissionData) => void;
|
|
9
|
-
onSuccess?: (submissionId: string) => void;
|
|
10
|
-
onError?: (error: string) => void;
|
|
11
|
-
}
|
|
12
|
-
|
|
13
|
-
export interface SubmissionData {
|
|
14
|
-
agentName: string;
|
|
15
|
-
agentVersion: string;
|
|
16
|
-
repositoryUrl?: string;
|
|
17
|
-
taskId: string;
|
|
18
|
-
scores: {
|
|
19
|
-
functional: number;
|
|
20
|
-
visual: number;
|
|
21
|
-
quality: number;
|
|
22
|
-
security: number;
|
|
23
|
-
cost: number;
|
|
24
|
-
speed: number;
|
|
25
|
-
overall: number;
|
|
26
|
-
};
|
|
27
|
-
metrics: {
|
|
28
|
-
tokensUsed: number;
|
|
29
|
-
executionTimeMs: number;
|
|
30
|
-
filesChanged: number;
|
|
31
|
-
};
|
|
32
|
-
notes?: string;
|
|
33
|
-
}
|
|
34
|
-
|
|
35
|
-
const AVAILABLE_TASKS = [
|
|
36
|
-
{ id: 'saas-core/auth/supabase-oauth', name: 'Supabase Google OAuth' },
|
|
37
|
-
{ id: 'glue-code/data-transform/excel-to-json', name: 'Excel to JSON Transformer' },
|
|
38
|
-
{ id: 'ai-integration/rag-chatbot/pdf-qa', name: 'PDF Q&A RAG Chatbot' },
|
|
39
|
-
{ id: 'frontend/figma-to-code/pricing-card', name: 'Pricing Card Component' },
|
|
40
|
-
{ id: 'api-integrations/stripe/payment-webhook', name: 'Stripe Payment Webhook' },
|
|
41
|
-
{ id: 'code-evolution/legacy-migration/express-to-fastify', name: 'Express to Fastify Migration' },
|
|
42
|
-
];
|
|
43
|
-
|
|
44
|
-
export function SubmitForm({
|
|
45
|
-
apiUrl = '/api/submissions',
|
|
46
|
-
onSubmit,
|
|
47
|
-
onSuccess,
|
|
48
|
-
onError,
|
|
49
|
-
}: SubmitFormProps) {
|
|
50
|
-
const [isSubmitting, setIsSubmitting] = useState(false);
|
|
51
|
-
const [formData, setFormData] = useState<Partial<SubmissionData>>({
|
|
52
|
-
agentName: '',
|
|
53
|
-
agentVersion: '',
|
|
54
|
-
repositoryUrl: '',
|
|
55
|
-
taskId: '',
|
|
56
|
-
scores: {
|
|
57
|
-
functional: 0,
|
|
58
|
-
visual: 0,
|
|
59
|
-
quality: 0,
|
|
60
|
-
security: 0,
|
|
61
|
-
cost: 0,
|
|
62
|
-
speed: 0,
|
|
63
|
-
overall: 0,
|
|
64
|
-
},
|
|
65
|
-
metrics: {
|
|
66
|
-
tokensUsed: 0,
|
|
67
|
-
executionTimeMs: 0,
|
|
68
|
-
filesChanged: 0,
|
|
69
|
-
},
|
|
70
|
-
notes: '',
|
|
71
|
-
});
|
|
72
|
-
|
|
73
|
-
const handleChange = (
|
|
74
|
-
e: React.ChangeEvent<HTMLInputElement | HTMLSelectElement | HTMLTextAreaElement>
|
|
75
|
-
) => {
|
|
76
|
-
const { name, value, type } = e.target;
|
|
77
|
-
|
|
78
|
-
if (name.startsWith('scores.')) {
|
|
79
|
-
const field = name.replace('scores.', '');
|
|
80
|
-
setFormData((prev) => ({
|
|
81
|
-
...prev,
|
|
82
|
-
scores: {
|
|
83
|
-
...prev.scores!,
|
|
84
|
-
[field]: type === 'number' ? parseFloat(value) : value,
|
|
85
|
-
},
|
|
86
|
-
}));
|
|
87
|
-
} else if (name.startsWith('metrics.')) {
|
|
88
|
-
const field = name.replace('metrics.', '');
|
|
89
|
-
setFormData((prev) => ({
|
|
90
|
-
...prev,
|
|
91
|
-
metrics: {
|
|
92
|
-
...prev.metrics!,
|
|
93
|
-
[field]: parseInt(value, 10),
|
|
94
|
-
},
|
|
95
|
-
}));
|
|
96
|
-
} else {
|
|
97
|
-
setFormData((prev) => ({
|
|
98
|
-
...prev,
|
|
99
|
-
[name]: value,
|
|
100
|
-
}));
|
|
101
|
-
}
|
|
102
|
-
};
|
|
103
|
-
|
|
104
|
-
const handleSubmit = async (e: React.FormEvent) => {
|
|
105
|
-
e.preventDefault();
|
|
106
|
-
setIsSubmitting(true);
|
|
107
|
-
|
|
108
|
-
try {
|
|
109
|
-
const submission = formData as SubmissionData;
|
|
110
|
-
onSubmit?.(submission);
|
|
111
|
-
|
|
112
|
-
const response = await fetch(apiUrl, {
|
|
113
|
-
method: 'POST',
|
|
114
|
-
headers: { 'Content-Type': 'application/json' },
|
|
115
|
-
body: JSON.stringify(submission),
|
|
116
|
-
});
|
|
117
|
-
|
|
118
|
-
if (!response.ok) {
|
|
119
|
-
throw new Error('Submission failed');
|
|
120
|
-
}
|
|
121
|
-
|
|
122
|
-
const result = await response.json();
|
|
123
|
-
onSuccess?.(result.id);
|
|
124
|
-
} catch (error) {
|
|
125
|
-
onError?.(error instanceof Error ? error.message : 'Unknown error');
|
|
126
|
-
} finally {
|
|
127
|
-
setIsSubmitting(false);
|
|
128
|
-
}
|
|
129
|
-
};
|
|
130
|
-
|
|
131
|
-
return (
|
|
132
|
-
<form onSubmit={handleSubmit} className="space-y-6">
|
|
133
|
-
{/* Agent Information */}
|
|
134
|
-
<div className="bg-white shadow rounded-lg p-6">
|
|
135
|
-
<h3 className="text-lg font-medium text-gray-900 mb-4">Agent Information</h3>
|
|
136
|
-
<div className="grid grid-cols-2 gap-4">
|
|
137
|
-
<div>
|
|
138
|
-
<label className="block text-sm font-medium text-gray-700">Agent Name</label>
|
|
139
|
-
<input
|
|
140
|
-
type="text"
|
|
141
|
-
name="agentName"
|
|
142
|
-
value={formData.agentName}
|
|
143
|
-
onChange={handleChange}
|
|
144
|
-
required
|
|
145
|
-
className="mt-1 block w-full rounded-md border-gray-300 shadow-sm focus:border-indigo-500 focus:ring-indigo-500"
|
|
146
|
-
placeholder="e.g., Claude Code"
|
|
147
|
-
/>
|
|
148
|
-
</div>
|
|
149
|
-
<div>
|
|
150
|
-
<label className="block text-sm font-medium text-gray-700">Version</label>
|
|
151
|
-
<input
|
|
152
|
-
type="text"
|
|
153
|
-
name="agentVersion"
|
|
154
|
-
value={formData.agentVersion}
|
|
155
|
-
onChange={handleChange}
|
|
156
|
-
required
|
|
157
|
-
className="mt-1 block w-full rounded-md border-gray-300 shadow-sm focus:border-indigo-500 focus:ring-indigo-500"
|
|
158
|
-
placeholder="e.g., 1.0.0"
|
|
159
|
-
/>
|
|
160
|
-
</div>
|
|
161
|
-
<div className="col-span-2">
|
|
162
|
-
<label className="block text-sm font-medium text-gray-700">
|
|
163
|
-
Repository URL (optional)
|
|
164
|
-
</label>
|
|
165
|
-
<input
|
|
166
|
-
type="url"
|
|
167
|
-
name="repositoryUrl"
|
|
168
|
-
value={formData.repositoryUrl}
|
|
169
|
-
onChange={handleChange}
|
|
170
|
-
className="mt-1 block w-full rounded-md border-gray-300 shadow-sm focus:border-indigo-500 focus:ring-indigo-500"
|
|
171
|
-
placeholder="https://github.com/..."
|
|
172
|
-
/>
|
|
173
|
-
</div>
|
|
174
|
-
</div>
|
|
175
|
-
</div>
|
|
176
|
-
|
|
177
|
-
{/* Task Selection */}
|
|
178
|
-
<div className="bg-white shadow rounded-lg p-6">
|
|
179
|
-
<h3 className="text-lg font-medium text-gray-900 mb-4">Task</h3>
|
|
180
|
-
<select
|
|
181
|
-
name="taskId"
|
|
182
|
-
value={formData.taskId}
|
|
183
|
-
onChange={handleChange}
|
|
184
|
-
required
|
|
185
|
-
className="block w-full rounded-md border-gray-300 shadow-sm focus:border-indigo-500 focus:ring-indigo-500"
|
|
186
|
-
>
|
|
187
|
-
<option value="">Select a task...</option>
|
|
188
|
-
{AVAILABLE_TASKS.map((task) => (
|
|
189
|
-
<option key={task.id} value={task.id}>
|
|
190
|
-
{task.name}
|
|
191
|
-
</option>
|
|
192
|
-
))}
|
|
193
|
-
</select>
|
|
194
|
-
</div>
|
|
195
|
-
|
|
196
|
-
{/* Scores */}
|
|
197
|
-
<div className="bg-white shadow rounded-lg p-6">
|
|
198
|
-
<h3 className="text-lg font-medium text-gray-900 mb-4">Scores (0-100)</h3>
|
|
199
|
-
<div className="grid grid-cols-3 gap-4">
|
|
200
|
-
{['functional', 'visual', 'quality', 'security', 'cost', 'speed', 'overall'].map(
|
|
201
|
-
(field) => (
|
|
202
|
-
<div key={field}>
|
|
203
|
-
<label className="block text-sm font-medium text-gray-700 capitalize">
|
|
204
|
-
{field}
|
|
205
|
-
</label>
|
|
206
|
-
<input
|
|
207
|
-
type="number"
|
|
208
|
-
name={`scores.${field}`}
|
|
209
|
-
value={(formData.scores as Record<string, number>)?.[field] || 0}
|
|
210
|
-
onChange={handleChange}
|
|
211
|
-
min="0"
|
|
212
|
-
max="100"
|
|
213
|
-
step="0.1"
|
|
214
|
-
required
|
|
215
|
-
className="mt-1 block w-full rounded-md border-gray-300 shadow-sm focus:border-indigo-500 focus:ring-indigo-500"
|
|
216
|
-
/>
|
|
217
|
-
</div>
|
|
218
|
-
)
|
|
219
|
-
)}
|
|
220
|
-
</div>
|
|
221
|
-
</div>
|
|
222
|
-
|
|
223
|
-
{/* Metrics */}
|
|
224
|
-
<div className="bg-white shadow rounded-lg p-6">
|
|
225
|
-
<h3 className="text-lg font-medium text-gray-900 mb-4">Metrics</h3>
|
|
226
|
-
<div className="grid grid-cols-3 gap-4">
|
|
227
|
-
<div>
|
|
228
|
-
<label className="block text-sm font-medium text-gray-700">Tokens Used</label>
|
|
229
|
-
<input
|
|
230
|
-
type="number"
|
|
231
|
-
name="metrics.tokensUsed"
|
|
232
|
-
value={formData.metrics?.tokensUsed || 0}
|
|
233
|
-
onChange={handleChange}
|
|
234
|
-
min="0"
|
|
235
|
-
required
|
|
236
|
-
className="mt-1 block w-full rounded-md border-gray-300 shadow-sm focus:border-indigo-500 focus:ring-indigo-500"
|
|
237
|
-
/>
|
|
238
|
-
</div>
|
|
239
|
-
<div>
|
|
240
|
-
<label className="block text-sm font-medium text-gray-700">
|
|
241
|
-
Execution Time (ms)
|
|
242
|
-
</label>
|
|
243
|
-
<input
|
|
244
|
-
type="number"
|
|
245
|
-
name="metrics.executionTimeMs"
|
|
246
|
-
value={formData.metrics?.executionTimeMs || 0}
|
|
247
|
-
onChange={handleChange}
|
|
248
|
-
min="0"
|
|
249
|
-
required
|
|
250
|
-
className="mt-1 block w-full rounded-md border-gray-300 shadow-sm focus:border-indigo-500 focus:ring-indigo-500"
|
|
251
|
-
/>
|
|
252
|
-
</div>
|
|
253
|
-
<div>
|
|
254
|
-
<label className="block text-sm font-medium text-gray-700">Files Changed</label>
|
|
255
|
-
<input
|
|
256
|
-
type="number"
|
|
257
|
-
name="metrics.filesChanged"
|
|
258
|
-
value={formData.metrics?.filesChanged || 0}
|
|
259
|
-
onChange={handleChange}
|
|
260
|
-
min="0"
|
|
261
|
-
required
|
|
262
|
-
className="mt-1 block w-full rounded-md border-gray-300 shadow-sm focus:border-indigo-500 focus:ring-indigo-500"
|
|
263
|
-
/>
|
|
264
|
-
</div>
|
|
265
|
-
</div>
|
|
266
|
-
</div>
|
|
267
|
-
|
|
268
|
-
{/* Notes */}
|
|
269
|
-
<div className="bg-white shadow rounded-lg p-6">
|
|
270
|
-
<h3 className="text-lg font-medium text-gray-900 mb-4">Notes (optional)</h3>
|
|
271
|
-
<textarea
|
|
272
|
-
name="notes"
|
|
273
|
-
value={formData.notes}
|
|
274
|
-
onChange={handleChange}
|
|
275
|
-
rows={3}
|
|
276
|
-
className="block w-full rounded-md border-gray-300 shadow-sm focus:border-indigo-500 focus:ring-indigo-500"
|
|
277
|
-
placeholder="Any additional information about this submission..."
|
|
278
|
-
/>
|
|
279
|
-
</div>
|
|
280
|
-
|
|
281
|
-
{/* Submit Button */}
|
|
282
|
-
<div className="flex justify-end">
|
|
283
|
-
<button
|
|
284
|
-
type="submit"
|
|
285
|
-
disabled={isSubmitting}
|
|
286
|
-
className="px-6 py-3 bg-indigo-600 text-white font-medium rounded-md hover:bg-indigo-700 focus:outline-none focus:ring-2 focus:ring-offset-2 focus:ring-indigo-500 disabled:opacity-50 disabled:cursor-not-allowed"
|
|
287
|
-
>
|
|
288
|
-
{isSubmitting ? 'Submitting...' : 'Submit Results'}
|
|
289
|
-
</button>
|
|
290
|
-
</div>
|
|
291
|
-
</form>
|
|
292
|
-
);
|
|
293
|
-
}
|
|
@@ -1,111 +0,0 @@
|
|
|
1
|
-
// React component for streaming terminal output
|
|
2
|
-
// Uses asciinema-player for rendering recorded terminal sessions
|
|
3
|
-
|
|
4
|
-
import { useEffect, useRef, useState } from 'react';
|
|
5
|
-
|
|
6
|
-
export interface TerminalStreamProps {
|
|
7
|
-
runId: string;
|
|
8
|
-
apiUrl?: string;
|
|
9
|
-
}
|
|
10
|
-
|
|
11
|
-
export interface LogEntry {
|
|
12
|
-
timestamp: string;
|
|
13
|
-
message: string;
|
|
14
|
-
}
|
|
15
|
-
|
|
16
|
-
export function TerminalStream({ runId, apiUrl = '/api/live' }: TerminalStreamProps) {
|
|
17
|
-
const terminalRef = useRef<HTMLDivElement>(null);
|
|
18
|
-
const [logs, setLogs] = useState<LogEntry[]>([]);
|
|
19
|
-
const [isConnected, setIsConnected] = useState(false);
|
|
20
|
-
|
|
21
|
-
useEffect(() => {
|
|
22
|
-
const eventSource = new EventSource(`${apiUrl}/stream/${runId}`);
|
|
23
|
-
|
|
24
|
-
eventSource.addEventListener('update', (event) => {
|
|
25
|
-
const data = JSON.parse(event.data);
|
|
26
|
-
if (data.logs) {
|
|
27
|
-
setLogs((prev) => [...prev, ...data.logs].slice(-100));
|
|
28
|
-
}
|
|
29
|
-
});
|
|
30
|
-
|
|
31
|
-
eventSource.addEventListener('open', () => {
|
|
32
|
-
setIsConnected(true);
|
|
33
|
-
});
|
|
34
|
-
|
|
35
|
-
eventSource.addEventListener('error', () => {
|
|
36
|
-
setIsConnected(false);
|
|
37
|
-
});
|
|
38
|
-
|
|
39
|
-
eventSource.addEventListener('end', () => {
|
|
40
|
-
eventSource.close();
|
|
41
|
-
setIsConnected(false);
|
|
42
|
-
});
|
|
43
|
-
|
|
44
|
-
return () => {
|
|
45
|
-
eventSource.close();
|
|
46
|
-
};
|
|
47
|
-
}, [runId, apiUrl]);
|
|
48
|
-
|
|
49
|
-
useEffect(() => {
|
|
50
|
-
// Auto-scroll to bottom
|
|
51
|
-
if (terminalRef.current) {
|
|
52
|
-
terminalRef.current.scrollTop = terminalRef.current.scrollHeight;
|
|
53
|
-
}
|
|
54
|
-
}, [logs]);
|
|
55
|
-
|
|
56
|
-
const formatTimestamp = (ts: string) => {
|
|
57
|
-
const date = new Date(ts);
|
|
58
|
-
return date.toLocaleTimeString('en-US', {
|
|
59
|
-
hour: '2-digit',
|
|
60
|
-
minute: '2-digit',
|
|
61
|
-
second: '2-digit',
|
|
62
|
-
hour12: false,
|
|
63
|
-
});
|
|
64
|
-
};
|
|
65
|
-
|
|
66
|
-
return (
|
|
67
|
-
<div className="bg-gray-900 rounded-lg overflow-hidden">
|
|
68
|
-
{/* Terminal Header */}
|
|
69
|
-
<div className="bg-gray-800 px-4 py-2 flex items-center justify-between">
|
|
70
|
-
<div className="flex items-center space-x-2">
|
|
71
|
-
<div className="flex space-x-1.5">
|
|
72
|
-
<div className="w-3 h-3 rounded-full bg-red-500" />
|
|
73
|
-
<div className="w-3 h-3 rounded-full bg-yellow-500" />
|
|
74
|
-
<div className="w-3 h-3 rounded-full bg-green-500" />
|
|
75
|
-
</div>
|
|
76
|
-
<span className="text-gray-400 text-sm ml-2">Terminal Output</span>
|
|
77
|
-
</div>
|
|
78
|
-
<div className="flex items-center space-x-2">
|
|
79
|
-
<span
|
|
80
|
-
className={`w-2 h-2 rounded-full ${isConnected ? 'bg-green-500' : 'bg-red-500'}`}
|
|
81
|
-
/>
|
|
82
|
-
<span className="text-gray-400 text-xs">
|
|
83
|
-
{isConnected ? 'Connected' : 'Disconnected'}
|
|
84
|
-
</span>
|
|
85
|
-
</div>
|
|
86
|
-
</div>
|
|
87
|
-
|
|
88
|
-
{/* Terminal Content */}
|
|
89
|
-
<div
|
|
90
|
-
ref={terminalRef}
|
|
91
|
-
className="p-4 h-96 overflow-y-auto font-mono text-sm"
|
|
92
|
-
style={{ backgroundColor: '#1a1b26' }}
|
|
93
|
-
>
|
|
94
|
-
{logs.length === 0 ? (
|
|
95
|
-
<div className="text-gray-500 animate-pulse">Waiting for output...</div>
|
|
96
|
-
) : (
|
|
97
|
-
logs.map((log, index) => (
|
|
98
|
-
<div key={index} className="flex">
|
|
99
|
-
<span className="text-gray-500 mr-3 select-none">
|
|
100
|
-
[{formatTimestamp(log.timestamp)}]
|
|
101
|
-
</span>
|
|
102
|
-
<span className="text-gray-100 whitespace-pre-wrap break-all">
|
|
103
|
-
{log.message}
|
|
104
|
-
</span>
|
|
105
|
-
</div>
|
|
106
|
-
))
|
|
107
|
-
)}
|
|
108
|
-
</div>
|
|
109
|
-
</div>
|
|
110
|
-
);
|
|
111
|
-
}
|
|
@@ -1,206 +0,0 @@
|
|
|
1
|
-
/**
|
|
2
|
-
* Model Pricing Configuration
|
|
3
|
-
*
|
|
4
|
-
* Prices are per 1 million tokens, sourced from OpenRouter (2026-01-21)
|
|
5
|
-
* https://openrouter.ai/models
|
|
6
|
-
* https://pricepertoken.com/
|
|
7
|
-
*
|
|
8
|
-
* To update: Edit this file and rebuild the leaderboard service
|
|
9
|
-
*/
|
|
10
|
-
|
|
11
|
-
export interface ModelPricing {
|
|
12
|
-
input: number; // $ per 1M input tokens
|
|
13
|
-
output: number; // $ per 1M output tokens
|
|
14
|
-
model: string; // Display name
|
|
15
|
-
provider: string;
|
|
16
|
-
lastUpdated: string;
|
|
17
|
-
}
|
|
18
|
-
|
|
19
|
-
// Canonical pricing data - use this everywhere
|
|
20
|
-
export const MODEL_PRICING: Record<string, ModelPricing> = {
|
|
21
|
-
// Anthropic Claude
|
|
22
|
-
'Claude Opus': {
|
|
23
|
-
input: 5.00,
|
|
24
|
-
output: 25.00,
|
|
25
|
-
model: 'Claude Opus 4.5',
|
|
26
|
-
provider: 'Anthropic',
|
|
27
|
-
lastUpdated: '2026-01-21',
|
|
28
|
-
},
|
|
29
|
-
'Claude Sonnet': {
|
|
30
|
-
input: 3.00,
|
|
31
|
-
output: 15.00,
|
|
32
|
-
model: 'Claude Sonnet 4.5',
|
|
33
|
-
provider: 'Anthropic',
|
|
34
|
-
lastUpdated: '2026-01-21',
|
|
35
|
-
},
|
|
36
|
-
'Claude Haiku': {
|
|
37
|
-
input: 1.00,
|
|
38
|
-
output: 5.00,
|
|
39
|
-
model: 'Claude Haiku 4.5',
|
|
40
|
-
provider: 'Anthropic',
|
|
41
|
-
lastUpdated: '2026-01-21',
|
|
42
|
-
},
|
|
43
|
-
'Claude': {
|
|
44
|
-
input: 1.00,
|
|
45
|
-
output: 5.00,
|
|
46
|
-
model: 'Claude Haiku 4.5',
|
|
47
|
-
provider: 'Anthropic',
|
|
48
|
-
lastUpdated: '2026-01-21',
|
|
49
|
-
},
|
|
50
|
-
'Claude Code': {
|
|
51
|
-
input: 1.00,
|
|
52
|
-
output: 5.00,
|
|
53
|
-
model: 'Claude Haiku 4.5',
|
|
54
|
-
provider: 'Anthropic',
|
|
55
|
-
lastUpdated: '2026-01-21',
|
|
56
|
-
},
|
|
57
|
-
|
|
58
|
-
// OpenAI
|
|
59
|
-
'OpenAI': {
|
|
60
|
-
input: 1.75,
|
|
61
|
-
output: 14.00,
|
|
62
|
-
model: 'GPT-5.2',
|
|
63
|
-
provider: 'OpenAI',
|
|
64
|
-
lastUpdated: '2026-01-21',
|
|
65
|
-
},
|
|
66
|
-
'OpenAI Codex': {
|
|
67
|
-
input: 1.75,
|
|
68
|
-
output: 14.00,
|
|
69
|
-
model: 'GPT-5.2',
|
|
70
|
-
provider: 'OpenAI',
|
|
71
|
-
lastUpdated: '2026-01-21',
|
|
72
|
-
},
|
|
73
|
-
|
|
74
|
-
// xAI Grok
|
|
75
|
-
'Grok': {
|
|
76
|
-
input: 3.00,
|
|
77
|
-
output: 15.00,
|
|
78
|
-
model: 'Grok 4',
|
|
79
|
-
provider: 'xAI',
|
|
80
|
-
lastUpdated: '2026-01-21',
|
|
81
|
-
},
|
|
82
|
-
'Grok Fast': {
|
|
83
|
-
input: 0.20,
|
|
84
|
-
output: 0.50,
|
|
85
|
-
model: 'Grok 4 Fast',
|
|
86
|
-
provider: 'xAI',
|
|
87
|
-
lastUpdated: '2026-01-21',
|
|
88
|
-
},
|
|
89
|
-
'Grok 4.1': {
|
|
90
|
-
input: 0.20,
|
|
91
|
-
output: 0.50,
|
|
92
|
-
model: 'Grok 4.1 Fast',
|
|
93
|
-
provider: 'xAI',
|
|
94
|
-
lastUpdated: '2026-01-21',
|
|
95
|
-
},
|
|
96
|
-
|
|
97
|
-
// Zhipu AI GLM
|
|
98
|
-
'GLM-4': {
|
|
99
|
-
input: 0.40,
|
|
100
|
-
output: 1.50,
|
|
101
|
-
model: 'GLM 4-Plus / GLM-4.7',
|
|
102
|
-
provider: 'Zhipu AI',
|
|
103
|
-
lastUpdated: '2026-01-21',
|
|
104
|
-
},
|
|
105
|
-
'GLM': {
|
|
106
|
-
input: 0.07,
|
|
107
|
-
output: 0.40,
|
|
108
|
-
model: 'GLM 4.7 Flash',
|
|
109
|
-
provider: 'Zhipu AI',
|
|
110
|
-
lastUpdated: '2026-01-21',
|
|
111
|
-
},
|
|
112
|
-
|
|
113
|
-
// DeepSeek
|
|
114
|
-
'DeepSeek': {
|
|
115
|
-
input: 0.30,
|
|
116
|
-
output: 1.20,
|
|
117
|
-
model: 'DeepSeek v3',
|
|
118
|
-
provider: 'DeepSeek',
|
|
119
|
-
lastUpdated: '2026-01-21',
|
|
120
|
-
},
|
|
121
|
-
|
|
122
|
-
// Google Gemini
|
|
123
|
-
'Gemini': {
|
|
124
|
-
input: 0.50,
|
|
125
|
-
output: 3.00,
|
|
126
|
-
model: 'Gemini 3 Flash',
|
|
127
|
-
provider: 'Google',
|
|
128
|
-
lastUpdated: '2026-01-21',
|
|
129
|
-
},
|
|
130
|
-
'Gemini Flash': {
|
|
131
|
-
input: 0.50,
|
|
132
|
-
output: 3.00,
|
|
133
|
-
model: 'Gemini 3 Flash',
|
|
134
|
-
provider: 'Google',
|
|
135
|
-
lastUpdated: '2026-01-21',
|
|
136
|
-
},
|
|
137
|
-
'Gemini Pro': {
|
|
138
|
-
input: 2.00,
|
|
139
|
-
output: 12.00,
|
|
140
|
-
model: 'Gemini 3 Pro',
|
|
141
|
-
provider: 'Google',
|
|
142
|
-
lastUpdated: '2026-01-21',
|
|
143
|
-
},
|
|
144
|
-
|
|
145
|
-
// MiniMax
|
|
146
|
-
'MiniMax': {
|
|
147
|
-
input: 0.27,
|
|
148
|
-
output: 1.12,
|
|
149
|
-
model: 'MiniMax M2.1',
|
|
150
|
-
provider: 'MiniMax',
|
|
151
|
-
lastUpdated: '2026-01-21',
|
|
152
|
-
},
|
|
153
|
-
};
|
|
154
|
-
|
|
155
|
-
/**
|
|
156
|
-
* Calculate cost from tokens using pricing config
|
|
157
|
-
*/
|
|
158
|
-
export function calculateCost(agentName: string, inputTokens: number, outputTokens: number): number {
|
|
159
|
-
const pricing = MODEL_PRICING[agentName] || { input: 1, output: 5 };
|
|
160
|
-
return (inputTokens / 1_000_000) * pricing.input + (outputTokens / 1_000_000) * pricing.output;
|
|
161
|
-
}
|
|
162
|
-
|
|
163
|
-
/**
|
|
164
|
-
* Get pricing for a model by name (fuzzy match)
|
|
165
|
-
*/
|
|
166
|
-
export function getPricing(modelName: string): ModelPricing | null {
|
|
167
|
-
// Exact match
|
|
168
|
-
if (MODEL_PRICING[modelName]) {
|
|
169
|
-
return MODEL_PRICING[modelName];
|
|
170
|
-
}
|
|
171
|
-
|
|
172
|
-
// Partial match
|
|
173
|
-
const key = Object.keys(MODEL_PRICING).find(k =>
|
|
174
|
-
modelName.toLowerCase().includes(k.toLowerCase()) ||
|
|
175
|
-
k.toLowerCase().includes(modelName.toLowerCase())
|
|
176
|
-
);
|
|
177
|
-
|
|
178
|
-
return key ? MODEL_PRICING[key] : null;
|
|
179
|
-
}
|
|
180
|
-
|
|
181
|
-
/**
|
|
182
|
-
* Get all pricing as a formatted table for display
|
|
183
|
-
*/
|
|
184
|
-
export function getPricingTable(): Array<{
|
|
185
|
-
provider: string;
|
|
186
|
-
model: string;
|
|
187
|
-
input: string;
|
|
188
|
-
output: string;
|
|
189
|
-
lastUpdated: string;
|
|
190
|
-
}> {
|
|
191
|
-
const seen = new Set<string>();
|
|
192
|
-
return Object.values(MODEL_PRICING)
|
|
193
|
-
.filter(p => {
|
|
194
|
-
if (seen.has(p.model)) return false;
|
|
195
|
-
seen.add(p.model);
|
|
196
|
-
return true;
|
|
197
|
-
})
|
|
198
|
-
.sort((a, b) => a.provider.localeCompare(b.provider))
|
|
199
|
-
.map(p => ({
|
|
200
|
-
provider: p.provider,
|
|
201
|
-
model: p.model,
|
|
202
|
-
input: `$${p.input.toFixed(2)}`,
|
|
203
|
-
output: `$${p.output.toFixed(2)}`,
|
|
204
|
-
lastUpdated: p.lastUpdated,
|
|
205
|
-
}));
|
|
206
|
-
}
|
|
@@ -1,31 +0,0 @@
|
|
|
1
|
-
import { drizzle } from 'drizzle-orm/postgres-js';
|
|
2
|
-
import postgres from 'postgres';
|
|
3
|
-
import * as schema from './schema.js';
|
|
4
|
-
|
|
5
|
-
const connectionString = process.env.DATABASE_URL;
|
|
6
|
-
|
|
7
|
-
if (!connectionString) {
|
|
8
|
-
console.warn('DATABASE_URL not set, using in-memory fallback');
|
|
9
|
-
}
|
|
10
|
-
|
|
11
|
-
// Create postgres client
|
|
12
|
-
const client = connectionString
|
|
13
|
-
? postgres(connectionString, { prepare: false })
|
|
14
|
-
: null;
|
|
15
|
-
|
|
16
|
-
// Create drizzle instance
|
|
17
|
-
export const db = client ? drizzle(client, { schema }) : null;
|
|
18
|
-
|
|
19
|
-
// Export schema for use elsewhere
|
|
20
|
-
export * from './schema.js';
|
|
21
|
-
|
|
22
|
-
// Health check
|
|
23
|
-
export async function checkDatabaseConnection(): Promise<boolean> {
|
|
24
|
-
if (!db) return false;
|
|
25
|
-
try {
|
|
26
|
-
await client!`SELECT 1`;
|
|
27
|
-
return true;
|
|
28
|
-
} catch {
|
|
29
|
-
return false;
|
|
30
|
-
}
|
|
31
|
-
}
|