CHANGELOG.md
LICENSE
MANIFEST.in
README.md
__init__.py
__main__.py
action.yml
agents.yaml
cli.py
compat.py
pyproject.toml
requirements-dev.txt
requirements.txt
./__init__.py
./__main__.py
./agents.yaml
./cli.py
./compat.py
./adapters/__init__.py
./adapters/_utils.py
./adapters/agentic_data_analyst.py
./adapters/autogen.py
./adapters/base.py
./adapters/contract_shield.py
./adapters/crewai.py
./adapters/data_analyst.py
./adapters/langgraph.py
./adapters/openai_agents.py
./adapters/scheme_saathi.py
./baselines/data_analyst.json
./core/__init__.py
./core/_fsutil.py
./core/alerts.py
./core/audit.py
./core/calibration.py
./core/ci_matrix.py
./core/ci_preflight.py
./core/compare.py
./core/config.py
./core/conversation.py
./core/dataset_import.py
./core/flakiness.py
./core/generator.py
./core/history.py
./core/init.py
./core/judge.py
./core/metrics.py
./core/model_compare.py
./core/pricing.py
./core/provenance.py
./core/rag_metrics.py
./core/rbac.py
./core/redteam.py
./core/registry.py
./core/report.py
./core/runner.py
./core/schema.py
./core/server.py
./core/significance.py
./core/store.py
./core/template_catalog.py
./core/tool_efficiency.py
./core/trace.py
./core/trace_view.py
./core/trajectory.py
./core/trajectory_diff.py
./dashboard/__init__.py
./dashboard/app.py
./evaluators/__init__.py
./evaluators/_registry.py
./failure_memory/__init__.py
./failure_memory/cancel.py
./failure_memory/ci_gate.py
./failure_memory/cli.py
./failure_memory/clustering.py
./failure_memory/export.py
./failure_memory/fingerprint.py
./failure_memory/migrations.py
./failure_memory/minimize.py
./failure_memory/otel_compat.py
./failure_memory/recorder.py
./failure_memory/recurrence.py
./failure_memory/redaction.py
./failure_memory/replay.py
./failure_memory/review.py
./failure_memory/schema.py
./failure_memory/service.py
./failure_memory/store.py
./failure_memory/taxonomy.py
./sql/__init__.py
./sql/cli.py
./sql/diff.py
./sql/execution.py
./sql/hashutil.py
./sql/importer.py
./sql/normalize.py
./sql/parser.py
./sql/policy.py
./sql/qualify.py
./sql/report.py
./sql/scanner.py
./sql/semantic.py
./sql/session.py
./sql/rules/__init__.py
./sql/rules/policy.py
./sql/rules/structural.py
./templates/__init__.py
./templates/catalog/__init__.py
./templates/catalog/coding-agent/README.md
./templates/catalog/coding-agent/agents.yaml
./templates/catalog/coding-agent/cases.yaml
./templates/catalog/coding-agent/template.json
./templates/catalog/customer-support/README.md
./templates/catalog/customer-support/agents.yaml
./templates/catalog/customer-support/cases.yaml
./templates/catalog/customer-support/template.json
./templates/catalog/rag-assistant/README.md
./templates/catalog/rag-assistant/agents.yaml
./templates/catalog/rag-assistant/cases.yaml
./templates/catalog/rag-assistant/template.json
./tests/golden/analyst_cases.yaml
./tests/golden/calibration_example.yaml
adapters/__init__.py
adapters/_utils.py
adapters/agentic_data_analyst.py
adapters/autogen.py
adapters/base.py
adapters/contract_shield.py
adapters/crewai.py
adapters/data_analyst.py
adapters/langgraph.py
adapters/openai_agents.py
adapters/scheme_saathi.py
baselines/data_analyst.json
core/__init__.py
core/_fsutil.py
core/alerts.py
core/audit.py
core/calibration.py
core/ci_matrix.py
core/ci_preflight.py
core/compare.py
core/config.py
core/conversation.py
core/dataset_import.py
core/flakiness.py
core/generator.py
core/history.py
core/init.py
core/judge.py
core/metrics.py
core/model_compare.py
core/pricing.py
core/provenance.py
core/rag_metrics.py
core/rbac.py
core/redteam.py
core/registry.py
core/report.py
core/runner.py
core/schema.py
core/server.py
core/significance.py
core/store.py
core/template_catalog.py
core/tool_efficiency.py
core/trace.py
core/trace_view.py
core/trajectory.py
core/trajectory_diff.py
dashboard/__init__.py
dashboard/app.py
docs/compatibility.md
docs/failure-memory.md
docs/multi-turn-evaluation.md
docs/plugins.md
docs/redteam-generation.md
docs/sql-scanner.md
docs/templates.md
docs/tool-efficiency.md
docs/v1-readiness.md
evaluators/__init__.py
evaluators/_registry.py
examples/__init__.py
examples/action_demo/__init__.py
examples/action_demo/adapter.py
examples/action_demo/agents.yaml
examples/action_demo/baseline.json
examples/action_demo/cases.yaml
examples/failure_memory_demo/README.md
examples/failure_memory_demo/run_demo.py
examples/failure_memory_demo_v21/README.md
examples/failure_memory_demo_v21/run_demo.py
examples/github-actions/agenteval.yml
examples/mock_agent/README.md
examples/mock_agent/__init__.py
examples/mock_agent/adapter.py
examples/mock_agent/agents.yaml
examples/mock_agent/baseline.json
examples/mock_agent/cases.yaml
examples/plugins/README.md
examples/plugins/_smoke_plugins.py
examples/plugins/agenteval-json-schema-evaluator/README.md
examples/plugins/agenteval-json-schema-evaluator/pyproject.toml
examples/plugins/agenteval-json-schema-evaluator/src/agenteval_json_schema_evaluator/__init__.py
examples/plugins/agenteval-keyword-evaluator/README.md
examples/plugins/agenteval-keyword-evaluator/pyproject.toml
examples/plugins/agenteval-keyword-evaluator/src/agenteval_keyword_evaluator/__init__.py
examples/plugins/agenteval-pattern-presence-evaluator/README.md
examples/plugins/agenteval-pattern-presence-evaluator/pyproject.toml
examples/plugins/agenteval-pattern-presence-evaluator/src/agenteval_pattern_presence_evaluator/__init__.py
examples/trajectory_diff/README.md
examples/trajectory_diff/traj_a.json
examples/trajectory_diff/traj_b.json
failure_memory/__init__.py
failure_memory/cancel.py
failure_memory/ci_gate.py
failure_memory/cli.py
failure_memory/clustering.py
failure_memory/export.py
failure_memory/fingerprint.py
failure_memory/migrations.py
failure_memory/minimize.py
failure_memory/otel_compat.py
failure_memory/recorder.py
failure_memory/recurrence.py
failure_memory/redaction.py
failure_memory/replay.py
failure_memory/review.py
failure_memory/schema.py
failure_memory/service.py
failure_memory/store.py
failure_memory/taxonomy.py
nishanttyagi_agenteval.egg-info/PKG-INFO
nishanttyagi_agenteval.egg-info/SOURCES.txt
nishanttyagi_agenteval.egg-info/dependency_links.txt
nishanttyagi_agenteval.egg-info/entry_points.txt
nishanttyagi_agenteval.egg-info/requires.txt
nishanttyagi_agenteval.egg-info/top_level.txt
sql/__init__.py
sql/cli.py
sql/diff.py
sql/execution.py
sql/hashutil.py
sql/importer.py
sql/normalize.py
sql/parser.py
sql/policy.py
sql/qualify.py
sql/report.py
sql/scanner.py
sql/semantic.py
sql/session.py
sql/rules/__init__.py
sql/rules/policy.py
sql/rules/structural.py
templates/__init__.py
templates/catalog/__init__.py
templates/catalog/coding-agent/README.md
templates/catalog/coding-agent/agents.yaml
templates/catalog/coding-agent/cases.yaml
templates/catalog/coding-agent/template.json
templates/catalog/customer-support/README.md
templates/catalog/customer-support/agents.yaml
templates/catalog/customer-support/cases.yaml
templates/catalog/customer-support/template.json
templates/catalog/rag-assistant/README.md
templates/catalog/rag-assistant/agents.yaml
templates/catalog/rag-assistant/cases.yaml
templates/catalog/rag-assistant/template.json
tests/test_adapter_contract.py
tests/test_adapter_usage.py
tests/test_agentic_data_analyst_trajectory.py
tests/test_alert_config.py
tests/test_alerts.py
tests/test_audit.py
tests/test_audit_config.py
tests/test_autogen_adapter.py
tests/test_calibration.py
tests/test_ci_matrix.py
tests/test_ci_workflow.py
tests/test_cli_agents.py
tests/test_cli_audit_hooks.py
tests/test_cli_audit_log.py
tests/test_cli_calibrate.py
tests/test_cli_compare_alerts.py
tests/test_cli_compare_gates.py
tests/test_cli_encoding.py
tests/test_cli_generate_adversarial.py
tests/test_cli_generate_cases_failures.py
tests/test_cli_help.py
tests/test_cli_history.py
tests/test_cli_plugins.py
tests/test_cli_report.py
tests/test_cli_serve.py
tests/test_cli_templates.py
tests/test_cli_trace.py
tests/test_compare.py
tests/test_compare_significance.py
tests/test_config.py
tests/test_conversation.py
tests/test_cost_attribution.py
tests/test_cost_provenance.py
tests/test_crewai_adapter.py
tests/test_dashboard_flakiness.py
tests/test_dashboard_run_selection.py
tests/test_dashboard_trajectory.py
tests/test_dataset_import.py
tests/test_docker.py
tests/test_evaluator_plugins.py
tests/test_example_evaluator_plugins.py
tests/test_flakiness.py
tests/test_flakiness_store.py
tests/test_generate_cases.py
tests/test_generator.py
tests/test_github_action.py
tests/test_history.py
tests/test_init.py
tests/test_langgraph_adapter.py
tests/test_metrics_integrity.py
tests/test_mock_agent_demo.py
tests/test_model_compare.py
tests/test_observability_gates.py
tests/test_openai_agents_adapter.py
tests/test_packaging.py
tests/test_pricing.py
tests/test_provenance.py
tests/test_public_api.py
tests/test_rag_metrics.py
tests/test_rag_schema.py
tests/test_rbac.py
tests/test_redteam_generation.py
tests/test_registry.py
tests/test_regression_from_failures.py
tests/test_repeat_cli.py
tests/test_report.py
tests/test_runner_trajectory.py
tests/test_schema_trajectory.py
tests/test_server.py
tests/test_significance.py
tests/test_sql_diff.py
tests/test_sql_execution.py
tests/test_sql_import.py
tests/test_sql_policy.py
tests/test_sql_semantic.py
tests/test_sql_session.py
tests/test_sql_structural.py
tests/test_store_git_sha.py
tests/test_strict_bool.py
tests/test_template_catalog.py
tests/test_tool_efficiency.py
tests/test_trace.py
tests/test_trace_view.py
tests/test_trajectory.py
tests/test_trajectory_diff.py
tests/golden/analyst_cases.yaml
tests/golden/calibration_example.yaml