.cursorindexingignore
.env.example
.gitignore
CLAUDE.md
LICENSE.md
README.md
pyproject.toml
requirements-docs.txt
uv.lock
.claude/skills/code-review/SKILL.md
.cursor/hooks.json
.cursor/hooks/update-context.js
.cursor/rules/app-details.md
.cursor/rules/context-first.md
.cursor/skills/changelog-generator/SKILL.md
.githooks/pre-commit
.github/workflows/claude-code-review.yml
.github/workflows/claude.yml
.github/workflows/publish.yml
.github/workflows/sync-api-spec.yml
.github/workflows/tests.yml
calibrate_agent/__init__.py
calibrate_agent/_env.py
calibrate_agent/cli.py
calibrate_agent/connections.py
calibrate_agent/judges.py
calibrate_agent/langfuse.py
calibrate_agent/rate_limit.py
calibrate_agent/status.py
calibrate_agent/utils.py
calibrate_agent.egg-info/PKG-INFO
calibrate_agent.egg-info/SOURCES.txt
calibrate_agent.egg-info/dependency_links.txt
calibrate_agent.egg-info/entry_points.txt
calibrate_agent.egg-info/requires.txt
calibrate_agent.egg-info/scm_file_list.json
calibrate_agent.egg-info/scm_version.json
calibrate_agent.egg-info/top_level.txt
calibrate_agent/agent/__init__.py
calibrate_agent/agent/bot.py
calibrate_agent/agent/run_simulation.py
calibrate_agent/agent/test.py
calibrate_agent/general/__init__.py
calibrate_agent/general/eval.py
calibrate_agent/general/metrics.py
calibrate_agent/llm/__init__.py
calibrate_agent/llm/_metrics_utils.py
calibrate_agent/llm/_output.py
calibrate_agent/llm/benchmark.py
calibrate_agent/llm/metrics.py
calibrate_agent/llm/run_simulation.py
calibrate_agent/llm/run_tests.py
calibrate_agent/llm/simulation_leaderboard.py
calibrate_agent/llm/tests_leaderboard.py
calibrate_agent/stt/__init__.py
calibrate_agent/stt/benchmark.py
calibrate_agent/stt/eval.py
calibrate_agent/stt/leaderboard.py
calibrate_agent/stt/metrics.py
calibrate_agent/stt/sarvam_intent_entity/__init__.py
calibrate_agent/stt/sarvam_intent_entity/judge.py
calibrate_agent/stt/sarvam_intent_entity/main.py
calibrate_agent/stt/sarvam_intent_entity/prompt_template.txt
calibrate_agent/stt/sarvam_intent_entity/utilities.py
calibrate_agent/stt/sarvam_llm_wer/__init__.py
calibrate_agent/stt/sarvam_llm_wer/judge.py
calibrate_agent/stt/sarvam_llm_wer/main.py
calibrate_agent/stt/sarvam_llm_wer/prompt_template.txt
calibrate_agent/stt/semantic_wer/__init__.py
calibrate_agent/stt/semantic_wer/judge.py
calibrate_agent/stt/semantic_wer/main.py
calibrate_agent/stt/semantic_wer/prompt_template.txt
calibrate_agent/tts/__init__.py
calibrate_agent/tts/benchmark.py
calibrate_agent/tts/eval.py
calibrate_agent/tts/leaderboard.py
calibrate_agent/tts/metrics.py
calibrate_agent/ui/__init__.py
calibrate_agent/ui/cli.bundle.mjs
docs/README.md
docs/development.mdx
docs/docs.json
docs/favicon.svg
docs/agents/onboarding.mdx
docs/agents/overview.mdx
docs/agents/skills.mdx
docs/ai-tools/claude-code.mdx
docs/ai-tools/cursor.mdx
docs/ai-tools/windsurf.mdx
docs/api-reference/introduction.mdx
docs/api-reference/openapi.json
docs/audio/hello_world.wav
docs/cli/calibrate-agent.mdx
docs/cli/overview.mdx
docs/cli/simulations.mdx
docs/cli/speech-to-text.mdx
docs/cli/text-to-speech.mdx
docs/cli/text-to-text.mdx
docs/cli/agent-connections/chat.mdx
docs/cli/agent-connections/outbound-voice.mdx
docs/cli/agent-connections/overview.mdx
docs/cli/calibrate/agent-mode.mdx
docs/cli/calibrate/agent-tests.mdx
docs/cli/calibrate/agents.mdx
docs/cli/calibrate/annotation-tasks.mdx
docs/cli/calibrate/evaluators.mdx
docs/cli/calibrate/overview.mdx
docs/cli/calibrate/tests.mdx
docs/cli/images/llm_leaderboard.png
docs/cli/images/llm_model_output_pass.png
docs/cli/images/simulation_eval.png
docs/cli/images/simulation_overview.png
docs/cli/images/simulation_transcript.png
docs/cli/images/stt_leaderboard.png
docs/cli/images/stt_output_provider.png
docs/cli/images/tts_leaderboard.png
docs/cli/images/tts_output_provider.png
docs/core-concepts/agent-connections.mdx
docs/core-concepts/agents.mdx
docs/core-concepts/metrics.mdx
docs/core-concepts/personas.mdx
docs/core-concepts/scenarios.mdx
docs/core-concepts/speech-to-text.mdx
docs/core-concepts/text-to-speech.mdx
docs/core-concepts/tools.mdx
docs/core-concepts/audios/dr_smith.wav
docs/core-concepts/audios/hello_world.wav
docs/core-concepts/audios/phone_number.wav
docs/core-concepts/images/agent-conn-1.png
docs/core-concepts/images/agent-conn-2.png
docs/core-concepts/images/agent-conn-3.png
docs/core-concepts/images/agent-conn-4.png
docs/core-concepts/images/agents-0.png
docs/core-concepts/images/agents-1.png
docs/core-concepts/images/agents-2.png
docs/core-concepts/images/agents-3.png
docs/core-concepts/images/agents-4.png
docs/core-concepts/images/agents-5.png
docs/core-concepts/images/agents-6.png
docs/core-concepts/images/agents-7.png
docs/core-concepts/images/metrics-1.png
docs/core-concepts/images/metrics-2.png
docs/core-concepts/images/personas-1.png
docs/core-concepts/images/personas-2.png
docs/core-concepts/images/scenarios-1.png
docs/core-concepts/images/scenarios-2.png
docs/core-concepts/images/stt_dataset_detail.png
docs/core-concepts/images/stt_datasets_tab.png
docs/core-concepts/images/stt_new_dataset_dialog.png
docs/core-concepts/images/tests-1.png
docs/core-concepts/images/tools-1.png
docs/core-concepts/images/tools-structured-1.png
docs/core-concepts/images/tools-structured-2.png
docs/core-concepts/images/tools-webhook-1.png
docs/core-concepts/images/tools-webhook-2.png
docs/core-concepts/images/tts_dataset_detail.png
docs/core-concepts/images/tts_datasets_tab.png
docs/core-concepts/images/tts_new_dataset_dialog.png
docs/essentials/code.mdx
docs/essentials/images.mdx
docs/essentials/markdown.mdx
docs/essentials/navigation.mdx
docs/essentials/reusable-snippets.mdx
docs/essentials/settings.mdx
docs/examples/overview.mdx
docs/getting-started/introduction.mdx
docs/guides/tools.mdx
docs/images/checks-passed.png
docs/images/hero-dark.png
docs/images/hero-light.png
docs/integrations/llm.mdx
docs/integrations/stt.mdx
docs/integrations/tts.mdx
docs/logo/dark.svg
docs/logo/light.svg
docs/mcp/beginners-guide.mdx
docs/mcp/installation.mdx
docs/mcp/overview.mdx
docs/mcp/tools.mdx
docs/mcp/troubleshooting.mdx
docs/quickstart/simulations.mdx
docs/quickstart/speech-to-text.mdx
docs/quickstart/text-to-speech.mdx
docs/quickstart/text-to-text.mdx
docs/quickstart/images/agent-choice.png
docs/quickstart/images/agent-conn-benchmark-verify.png
docs/quickstart/images/agent-conn-verify-sample.png
docs/quickstart/images/llm-bench-public-preview-2.png
docs/quickstart/images/llm-bench-public-preview.png
docs/quickstart/images/llm-public-preview.png
docs/quickstart/images/llm-share-public.png
docs/quickstart/images/llm-shared-public.png
docs/quickstart/images/llm-test-bulk-upload-dialog.png
docs/quickstart/images/llm-test-bulk-upload-done.png
docs/quickstart/images/llm-test-bulk-upload-select-agent.png
docs/quickstart/images/llm-test-bulk-upload.png
docs/quickstart/images/sim_agent.png
docs/quickstart/images/sim_agent_tools.png
docs/quickstart/images/sim_config.png
docs/quickstart/images/sim_config_filled.png
docs/quickstart/images/sim_create.png
docs/quickstart/images/sim_launch_button.png
docs/quickstart/images/sim_launch_options.png
docs/quickstart/images/sim_metric_add.png
docs/quickstart/images/sim_metrics.png
docs/quickstart/images/sim_persona_add.png
docs/quickstart/images/sim_personas.png
docs/quickstart/images/sim_preview.png
docs/quickstart/images/sim_public.png
docs/quickstart/images/sim_public_preview.png
docs/quickstart/images/sim_scenario_add.png
docs/quickstart/images/sim_scenarios.png
docs/quickstart/images/sim_text_results.png
docs/quickstart/images/sim_text_running.png
docs/quickstart/images/sim_text_transcript.png
docs/quickstart/images/sim_voice_latency.png
docs/quickstart/images/sim_voice_results.png
docs/quickstart/images/sim_voice_running.png
docs/quickstart/images/sim_voice_transcript.png
docs/quickstart/images/sim_voice_transcript_complete.png
docs/quickstart/images/stt-dataset-upload.png
docs/quickstart/images/stt-existing-dataset.png
docs/quickstart/images/stt-setting.png
docs/quickstart/images/stt_leaderboard.png
docs/quickstart/images/stt_new.png
docs/quickstart/images/stt_new_dataset.png
docs/quickstart/images/stt_output.png
docs/quickstart/images/stt_overview.png
docs/quickstart/images/stt_preview.png
docs/quickstart/images/stt_public.png
docs/quickstart/images/stt_share.png
docs/quickstart/images/tests-all-1.png
docs/quickstart/images/tests-all-2.png
docs/quickstart/images/tests-all-3.png
docs/quickstart/images/tests-all.png
docs/quickstart/images/tests-benchmark-1.png
docs/quickstart/images/tests-benchmark-2.png
docs/quickstart/images/tests-benchmark-3.png
docs/quickstart/images/tests-new-1.png
docs/quickstart/images/tests-new-2.png
docs/quickstart/images/tests-one-test-1.png
docs/quickstart/images/tests-one-test-2.png
docs/quickstart/images/tests-one-test-3.png
docs/quickstart/images/tts_dataset_create.png
docs/quickstart/images/tts_existing_dataset.png
docs/quickstart/images/tts_leaderboard.png
docs/quickstart/images/tts_new.png
docs/quickstart/images/tts_new_dataset.png
docs/quickstart/images/tts_outputs.png
docs/quickstart/images/tts_preview.png
docs/quickstart/images/tts_public.png
docs/quickstart/images/tts_runs.png
docs/quickstart/images/tts_settings.png
docs/quickstart/images/tts_share.png
docs/reference/api-keys.mdx
docs/reference/github-actions.mdx
docs/sdk/overview.mdx
docs/sdk/agent-tests/benchmark.mdx
docs/sdk/agent-tests/get_benchmark.mdx
docs/sdk/agent-tests/get_run.mdx
docs/sdk/agent-tests/link.mdx
docs/sdk/agent-tests/list_for_agent.mdx
docs/sdk/agent-tests/list_runs_for_agent.mdx
docs/sdk/agent-tests/run.mdx
docs/sdk/agent-tests/run_batch.mdx
docs/sdk/agents/create.mdx
docs/sdk/agents/get.mdx
docs/sdk/agents/link_evaluators.mdx
docs/sdk/agents/list.mdx
docs/sdk/agents/list_evaluators.mdx
docs/sdk/agents/resolve.mdx
docs/sdk/agents/update.mdx
docs/sdk/agents/verify_connection.mdx
docs/sdk/annotation-tasks/add_items.mdx
docs/sdk/annotation-tasks/create.mdx
docs/sdk/annotation-tasks/create_evaluator_run.mdx
docs/sdk/annotation-tasks/get.mdx
docs/sdk/annotation-tasks/get_agreement.mdx
docs/sdk/annotation-tasks/get_evaluator_run.mdx
docs/sdk/annotation-tasks/get_summary.mdx
docs/sdk/annotation-tasks/list.mdx
docs/sdk/annotation-tasks/set_evaluators.mdx
docs/sdk/annotation-tasks/update_items.mdx
docs/sdk/evaluators/create.mdx
docs/sdk/evaluators/create_version.mdx
docs/sdk/evaluators/get.mdx
docs/sdk/evaluators/list.mdx
docs/sdk/tests/bulk_create.mdx
docs/sdk/tests/create.mdx
docs/sdk/tests/get.mdx
docs/sdk/tests/list.mdx
docs/sdk/tests/update.mdx
docs/snippets/snippet-intro.mdx
docs/templates/api-reference/introduction.mdx
docs/templates/cli/calibrate/agent-mode.mdx
docs/templates/cli/calibrate/overview.mdx
docs/templates/mcp/beginners-guide.mdx
docs/templates/mcp/installation.mdx
docs/templates/mcp/overview.mdx
docs/templates/mcp/troubleshooting.mdx
docs/templates/reference/api-keys.mdx
docs/templates/reference/github-actions.mdx
docs/templates/sdk/overview.mdx
examples/agent/simulation/sample_text_agent_connection.json
examples/agent/simulation/sample_text_dataset.json
examples/agent/simulation/sample_text_internal_agent.json
examples/agent/simulation/sample_voice.json
examples/agent/simulation/sample_voice_agent_connection.json
examples/agent/test/config.json
examples/agent/test/sample_output/audios/0_user.wav
examples/agent/test/sample_output/audios/10_user.wav
examples/agent/test/sample_output/audios/1_user.wav
examples/agent/test/sample_output/audios/2_bot.wav
examples/agent/test/sample_output/audios/3_user.wav
examples/agent/test/sample_output/audios/4_user.wav
examples/agent/test/sample_output/audios/5_user.wav
examples/agent/test/sample_output/audios/6_bot.wav
examples/agent/test/sample_output/audios/7_user.wav
examples/agent/test/sample_output/audios/8_user.wav
examples/agent/test/sample_output/audios/9_bot.wav
examples/general/config.json
examples/general/sample_dataset.json
examples/llm/config-conversation.json
examples/llm/config-external-agent.json
examples/llm/config-internal-agent.json
examples/llm/sample_dataset.json
examples/llm/sample_dataset_conversation.json
examples/llm/tool_call_scenarios/README.md
examples/llm/tool_call_scenarios/config.json
examples/llm/tool_call_scenarios/eval_only_dataset.json
examples/stt/config.json
examples/stt/sample_dataset.json
examples/stt/sample_dataset_sarvam.json
examples/stt/sample_input/stt.csv
examples/stt/sample_input/audios/1.wav
examples/stt/sample_input/audios/2.wav
examples/stt/sample_input/audios/3.wav
examples/stt/sample_input/audios/4.wav
examples/tts/config.json
examples/tts/sample.csv
images/run_conversation.png
images/run_metrics.png
scripts/cli_reference.py
scripts/docs_mdx.py
scripts/docs_nav.py
scripts/fetch_public_openapi.py
scripts/generate_cli_docs.py
scripts/generate_mcp_docs.py
scripts/generate_sdk_docs.py
scripts/mcp_reference.py
scripts/request_examples.py
scripts/sdk_reference.py
tests/__init__.py
tests/cli_doc_samples.py
tests/mcp_tool_samples.py
tests/sdk_route_samples.py
tests/test_agent_init_extra.py
tests/test_benchmarks.py
tests/test_cli.py
tests/test_cli_main.py
tests/test_cli_reference.py
tests/test_connections.py
tests/test_connections_extra.py
tests/test_docs_nav.py
tests/test_env.py
tests/test_fetch_public_openapi.py
tests/test_generate_cli_docs.py
tests/test_generate_mcp_docs.py
tests/test_generate_sdk_docs.py
tests/test_judges.py
tests/test_judges_extra.py
tests/test_langfuse_extra.py
tests/test_leaderboards_extra.py
tests/test_llm_leaderboards_extra.py
tests/test_mcp_reference.py
tests/test_metrics_extra.py
tests/test_misc_extra.py
tests/test_rate_limit.py
tests/test_request_examples.py
tests/test_sdk_judge_regressions.py
tests/test_sdk_reference.py
tests/test_status.py
tests/test_utils.py
tests/test_utils_audio.py
tests/test_utils_factories.py
tests/agent/__init__.py
tests/agent/test_bot.py
tests/agent/test_bot_run_bot.py
tests/agent/test_rtvi_adapter.py
tests/agent/test_rtvi_function_call.py
tests/agent/test_run_bot.py
tests/agent/test_run_simulation_helpers.py
tests/agent/test_test_module.py
tests/fixtures/reference.md
tests/general/__init__.py
tests/general/test_eval.py
tests/general/test_metrics.py
tests/llm/__init__.py
tests/llm/test_benchmark.py
tests/llm/test_init_extra.py
tests/llm/test_output.py
tests/llm/test_run_simulation.py
tests/llm/test_run_simulation_classes.py
tests/llm/test_run_simulation_extra.py
tests/llm/test_run_simulation_full.py
tests/llm/test_run_simulation_inner_handlers.py
tests/llm/test_run_simulation_integration.py
tests/llm/test_run_simulation_processor.py
tests/llm/test_run_tests.py
tests/llm/test_run_tests_extra.py
tests/llm/test_tests_leaderboard.py
tests/stt/__init__.py
tests/stt/test_eval.py
tests/stt/test_eval_extra.py
tests/stt/test_eval_more.py
tests/stt/test_eval_providers.py
tests/stt/test_google_streaming.py
tests/stt/test_intent_entity.py
tests/stt/test_language_mapping.py
tests/stt/test_leaderboard.py
tests/stt/test_llm_wer.py
tests/stt/test_metrics.py
tests/stt/test_sarvam_intent_entity.py
tests/stt/test_semantic_wer.py
tests/tts/__init__.py
tests/tts/test_benchmark.py
tests/tts/test_eval.py
tests/tts/test_eval_extra.py
tests/tts/test_eval_providers.py
tests/tts/test_leaderboard.py
tests/tts/test_metrics.py
ui/.gitignore
ui/package-lock.json
ui/package.json
ui/tsconfig.json
ui/vitest.config.ts
ui/source/app.tsx
ui/source/cli.tsx
ui/source/components.tsx
ui/source/credentials.ts
ui/source/llm-app.tsx
ui/source/llm-types.ts
ui/source/providers.ts
ui/source/resource-app.tsx
ui/source/shared.ts
ui/source/sim-app.tsx
ui/source/storage.ts
ui/tests/llm-app.test.tsx
ui/tests/shared.test.ts
ui/tests/sim-app.test.tsx