.dockerignore
.env.keys.example
.gitignore
AGENTS.md
ARCHITECTURE.md
CLAUDE.md
CODE_OF_CONDUCT.md
CONTRIBUTING.md
Dockerfile
LICENSE
Makefile
NOTICE
README.md
ROADMAP.md
THIRD_PARTY
buildspec-deploy.yml
buildspec.yml
deploy.sh
destroy.sh
manage-users.sh
package-lock.json
package.json
pyproject.toml
stress_test.py
uv.lock
verify_chat.py
verify_edge.py
verify_lifecycle.py
verify_migration.py
verify_reconnect.py
verify_results.py
verify_tenant_isolation.py
.claude/skills/aws-architecture/.gitignore
.claude/skills/aws-architecture/SKILL.md
.claude/skills/aws-architecture/scripts/fetch_icons.sh
.claude/skills/aws-architecture/scripts/find_icon.py
.claude/skills/aws-architecture/scripts/render.py
.claude/skills/ship-it/SKILL.md
.github/workflows/publish.yml
backend/__init__.py
backend/api/__init__.py
backend/api/compare.py
backend/api/main.py
backend/api/optimizations.py
backend/core/__init__.py
backend/core/agent.py
backend/core/bedrock_pricing.json
backend/core/chat.py
backend/core/database.py
backend/core/inspect_viewer.py
backend/core/judge_prompt_builder.py
backend/core/judge_tools.py
backend/core/jury_scoring.py
backend/core/mcp_client.py
backend/judge_prompts/reference_comparison.md
buildspec-scripts/deploy.sh
buildspec-scripts/destroy-data.sh
buildspec-scripts/destroy.sh
docker/backend.Dockerfile
docs/DEVELOPMENT.md
docs/SELF_HOSTING.md
docs/architecture-diagram.html
docs/image.png
eval_mcp/INSTALL.md
eval_mcp/__init__.py
eval_mcp/__main__.py
eval_mcp/_agent_launcher.py
eval_mcp/agent_detect.py
eval_mcp/bedrock_capture.py
eval_mcp/canary.py
eval_mcp/cli.py
eval_mcp/config.py
eval_mcp/judge_config.py
eval_mcp/otlp_receiver.py
eval_mcp/pricing.py
eval_mcp/provider_pricing.json
eval_mcp/s3_sync.py
eval_mcp/server.py
eval_mcp/storage.py
eval_mcp/subprocess_runner.py
eval_mcp/viewer.py
eval_mcp/core/__init__.py
eval_mcp/core/bedrock_client.py
eval_mcp/core/document_chunking.py
eval_mcp/core/eval_results.py
eval_mcp/core/judge_config.py
eval_mcp/core/logging_utils.py
eval_mcp/core/pdf_report.py
eval_mcp/core/pipeline_stages.py
eval_mcp/core/pricing.py
eval_mcp/core/provider_pricing.json
eval_mcp/core/s3_client.py
eval_mcp/core/user_storage.py
eval_mcp/installers/__init__.py
eval_mcp/installers/_json_merge.py
eval_mcp/installers/_toml_merge.py
eval_mcp/installers/base.py
eval_mcp/installers/claude_code.py
eval_mcp/installers/codex.py
eval_mcp/installers/cursor.py
eval_mcp/installers/detect.py
eval_mcp/installers/kiro.py
eval_mcp/installers/vscode.py
eval_mcp/scorers/__init__.py
eval_mcp/scorers/rag.py
eval_mcp/solvers/__init__.py
eval_mcp/solvers/static_output.py
eval_mcp/tools/__init__.py
eval_mcp/tools/agent.py
eval_mcp/tools/analyze_agent_image.py
eval_mcp/tools/analyze_agent_path.py
eval_mcp/tools/analyze_dataset.py
eval_mcp/tools/bedrock_models.py
eval_mcp/tools/benchmarks.py
eval_mcp/tools/create_agent_eval_config.py
eval_mcp/tools/create_config.py
eval_mcp/tools/create_pipeline_eval_config.py
eval_mcp/tools/external_providers.py
eval_mcp/tools/generate_judge.py
eval_mcp/tools/generate_qa.py
eval_mcp/tools/generate_report.py
eval_mcp/tools/get_evaluation_details.py
eval_mcp/tools/get_optimization_details.py
eval_mcp/tools/list_datasets.py
eval_mcp/tools/list_eval_configs.py
eval_mcp/tools/list_evaluations.py
eval_mcp/tools/list_judges.py
eval_mcp/tools/list_optimizations.py
eval_mcp/tools/optimize_prompt.py
eval_mcp/tools/run_eval.py
eval_mcp/tools/save_dataset.py
eval_mcp/viewer_static/index.html
eval_mcp/viewer_static/assets/Geist-Variable-CrgPqtmy.woff2
eval_mcp/viewer_static/assets/GeistMono-Variable-BNLlm6Cd.woff2
eval_mcp/viewer_static/assets/InstrumentSerif-Italic-DakeqbAP.woff2
eval_mcp/viewer_static/assets/InstrumentSerif-Regular-Cyjo-q7q.woff2
eval_mcp/viewer_static/assets/index-3H0Vbyag.css
eval_mcp/viewer_static/assets/index-84y7Xk_P.js
examples/run_all_tests.sh
examples/datasets/simple_healthcare_config.yaml
examples/langchain_bedrock_agent/agent.py
examples/langchain_bedrock_agent/requirements.txt
examples/local_agent/agent.py
examples/local_agent/requirements.txt
examples/local_agent/task.py
examples/strands_agent/agent-as-tools.ipynb
examples/strands_agent/agent.py
examples/strands_agent/requirements.txt
examples/test_agent/Dockerfile
examples/test_agent/agent.py
examples/test_agent/compose.yaml
examples/test_agent/task.py
frontend/.gitignore
frontend/eslint.config.mjs
frontend/index.html
frontend/package-lock.json
frontend/package.json
frontend/postcss.config.mjs
frontend/tailwind.config.ts
frontend/tsconfig.json
frontend/vite.config.ts
frontend/src/globals.css
frontend/src/main.tsx
frontend/src/providers.tsx
frontend/src/router.tsx
frontend/src/components/ChatInterface.tsx
frontend/src/components/Header.tsx
frontend/src/components/MessageInput.tsx
frontend/src/components/MessageList.tsx
frontend/src/components/data/DatasetDetail.tsx
frontend/src/components/data/DatasetList.tsx
frontend/src/components/data/DocumentsView.tsx
frontend/src/components/data/JudgesView.tsx
frontend/src/components/data/SubToggle.tsx
frontend/src/components/optimizations/OptimizationDetail.tsx
frontend/src/components/optimizations/OptimizationRail.tsx
frontend/src/components/results/AggregateMetrics.tsx
frontend/src/components/results/ComparisonGrid.tsx
frontend/src/components/results/ComparisonView.tsx
frontend/src/components/results/ResultsHeader.tsx
frontend/src/components/results/RunRail.tsx
frontend/src/components/results/SampleDetailPanel.tsx
frontend/src/components/results/scorers.ts
frontend/src/contexts/AuthContext.tsx
frontend/src/contexts/ChatContext.tsx
frontend/src/fonts/Geist-Variable.woff2
frontend/src/fonts/GeistMono-Variable.woff2
frontend/src/fonts/InstrumentSerif-Italic.woff2
frontend/src/fonts/InstrumentSerif-Regular.woff2
frontend/src/fonts/OFL.txt
frontend/src/fonts/SHA256SUMS
frontend/src/lib/data-api.ts
frontend/src/lib/data-types.ts
frontend/src/pages/Chat.tsx
frontend/src/pages/Data.tsx
frontend/src/pages/History.tsx
frontend/src/pages/Home.tsx
frontend/src/pages/Optimizations.tsx
frontend/src/pages/Results.tsx
helm/eval/Chart.lock
helm/eval/Chart.yaml
helm/eval/values-aws.yaml
helm/eval/values.yaml
helm/eval/charts/oauth2-proxy-7.18.0.tgz
helm/eval/templates/deployment.yaml
helm/eval/templates/hpa.yaml
helm/eval/templates/pdb.yaml
helm/eval/templates/pvc.yaml
helm/eval/templates/rbac.yaml
helm/eval/templates/service.yaml
helm/external-secrets-config/Chart.yaml
helm/external-secrets-config/values.yaml
helm/external-secrets-config/templates/external-secrets.yaml
helm/external-secrets-config/templates/secret-store.yaml
infra/.gitignore
infra/.terraform.lock.hcl
infra/terraform.tfvars.example
infra/data/.terraform.lock.hcl
infra/data/cognito.tf
infra/data/main.tf
infra/data/outputs.tf
infra/data/rds.tf
infra/data/storage.tf
infra/data/variables.tf
infra/data/vpc.tf
infra/eval-logs-bucket/.terraform.lock.hcl
infra/eval-logs-bucket/create-bucket.sh
infra/eval-logs-bucket/main.tf
infra/eval-logs-bucket/outputs.tf
infra/eval-logs-bucket/variables.tf
infra/platform/.terraform.lock.hcl
infra/platform/alb.tf
infra/platform/cicd.tf
infra/platform/cloudfront.tf
infra/platform/cognito.tf
infra/platform/eks.tf
infra/platform/kubernetes.tf
infra/platform/main.tf
infra/platform/outputs.tf
infra/platform/sandbox-security.tf
infra/platform/spa_bucket_policy.tf
infra/platform/storage.tf
infra/platform/variables.tf
llm_evaluation_system.egg-info/PKG-INFO
llm_evaluation_system.egg-info/SOURCES.txt
llm_evaluation_system.egg-info/dependency_links.txt
llm_evaluation_system.egg-info/entry_points.txt
llm_evaluation_system.egg-info/requires.txt
llm_evaluation_system.egg-info/top_level.txt
local/Dockerfile.python
local/README.md
local/compose.yaml
local/entrypoint.py
local/nginx-compose.conf
scripts/populate-pricing.py
scripts/verify_optimizer_improves.py
tests/test_agent_cancel_recovery.py
tests/test_agent_cancellation_timing.py
tests/test_agent_detect.py
tests/test_bedrock_capture_adapter.py
tests/test_bedrock_models.py
tests/test_benchmarks.py
tests/test_canary.py
tests/test_chat_cancel_eks.py
tests/test_chat_history_xpod.py
tests/test_create_config.py
tests/test_data_api.py
tests/test_eval_results_headline.py
tests/test_generate_judge_iter.py
tests/test_generate_qa_rag.py
tests/test_http_server.py
tests/test_install_claude_code.py
tests/test_install_codex.py
tests/test_install_cursor.py
tests/test_install_dispatcher.py
tests/test_install_json_merge.py
tests/test_install_kiro.py
tests/test_install_toml_merge.py
tests/test_install_vscode.py
tests/test_langchain_subprocess_e2e.py
tests/test_mcp_eval.py
tests/test_mcp_reconnect_lifespan_owner.py
tests/test_mcp_schema.py
tests/test_model_usage_dedupe.py
tests/test_optimize_multiscorer.py
tests/test_optimize_prompt.py
tests/test_otlp_receiver.py
tests/test_qa_allocation.py
tests/test_rag_scorers.py
tests/test_raw_otel_persistence.py
tests/test_run_eval_fail_loud.py
tests/test_save_dataset_rag.py
tests/test_save_dataset_score_only.py
tests/test_static_output_solver.py
tests/test_subprocess_mode_wiring.py
tests/test_subprocess_otlp_integration.py
tests/test_subprocess_runner.py
tests/mcp_eval/__init__.py
tests/mcp_eval/questions.xml
tests/mcp_eval/runner.py
tests/parity/.gitignore
tests/parity/README.md
tests/parity/reference_dataset.json
tests/parity/run_parity.py