LICENSE
NOTICE
README.md
pyproject.toml
evalview/__init__.py
evalview/__main__.py
evalview/api.py
evalview/chat.py
evalview/chat_runtime.py
evalview/chat_slash.py
evalview/cli.py
evalview/compare.py
evalview/expander.py
evalview/mcp_server.py
evalview/openclaw.py
evalview/pytest_plugin.py
evalview/recorder.py
evalview/test_generation.py
evalview/version_check.py
evalview.egg-info/PKG-INFO
evalview.egg-info/SOURCES.txt
evalview.egg-info/dependency_links.txt
evalview.egg-info/entry_points.txt
evalview.egg-info/requires.txt
evalview.egg-info/top_level.txt
evalview/adapters/__init__.py
evalview/adapters/aider_adapter.py
evalview/adapters/anthropic_adapter.py
evalview/adapters/base.py
evalview/adapters/cohere_adapter.py
evalview/adapters/crewai_adapter.py
evalview/adapters/crewai_native_adapter.py
evalview/adapters/goose_adapter.py
evalview/adapters/http_adapter.py
evalview/adapters/huggingface_adapter.py
evalview/adapters/langgraph_adapter.py
evalview/adapters/mcp_adapter.py
evalview/adapters/mistral_adapter.py
evalview/adapters/ollama_adapter.py
evalview/adapters/openai_assistants_adapter.py
evalview/adapters/openclaw_adapter.py
evalview/adapters/opencode_adapter.py
evalview/adapters/pydantic_ai_adapter.py
evalview/adapters/registry.py
evalview/adapters/tapescope_adapter.py
evalview/benchmarks/__init__.py
evalview/benchmarks/canary/README.md
evalview/benchmarks/canary/__init__.py
evalview/benchmarks/canary/suite.v1.held-out.yaml
evalview/benchmarks/canary/suite.v1.public.yaml
evalview/ci/__init__.py
evalview/ci/comment.py
evalview/cloud/__init__.py
evalview/cloud/auth.py
evalview/cloud/client.py
evalview/cloud/push.py
evalview/commands/__init__.py
evalview/commands/add_cmd.py
evalview/commands/assertion_wizard.py
evalview/commands/autopr_cmd.py
evalview/commands/badge_cmd.py
evalview/commands/baseline_cmd.py
evalview/commands/benchmark_cmd.py
evalview/commands/capture_cmd.py
evalview/commands/chat_cmd.py
evalview/commands/check_cmd.py
evalview/commands/check_display.py
evalview/commands/ci_cmd.py
evalview/commands/cloud_cmd.py
evalview/commands/demo_cmd.py
evalview/commands/drift_cmd.py
evalview/commands/expand_cmd.py
evalview/commands/feedback_cmd.py
evalview/commands/generate_cmd.py
evalview/commands/golden_cmd.py
evalview/commands/gym_cmd.py
evalview/commands/hooks_cmd.py
evalview/commands/import_cmd.py
evalview/commands/init_cmd.py
evalview/commands/judge_cmd.py
evalview/commands/listing_cmd.py
evalview/commands/log_cmd.py
evalview/commands/mcp_cmd.py
evalview/commands/model_check_cmd.py
evalview/commands/model_check_render.py
evalview/commands/monitor_cmd.py
evalview/commands/openclaw_cmd.py
evalview/commands/progress_cmd.py
evalview/commands/quarantine_cmd.py
evalview/commands/replay_trace_cmd.py
evalview/commands/shared.py
evalview/commands/simulate_cmd.py
evalview/commands/since_cmd.py
evalview/commands/skill_agent_runner.py
evalview/commands/skill_cmd.py
evalview/commands/slack_digest_cmd.py
evalview/commands/snapshot_cmd.py
evalview/commands/telemetry_cmd.py
evalview/commands/traces_cmd.py
evalview/commands/trends_cmd.py
evalview/commands/visual_cmd.py
evalview/commands/watch_cmd.py
evalview/commands/run/__init__.py
evalview/commands/run/_adapters.py
evalview/commands/run/_cmd.py
evalview/commands/run/_executor.py
evalview/commands/run/_reporter.py
evalview/commands/run/_runner.py
evalview/core/__init__.py
evalview/core/adapter_factory.py
evalview/core/behavioral_anomalies.py
evalview/core/benchmark_hardening.py
evalview/core/budget.py
evalview/core/canary_suite.py
evalview/core/celebrations.py
evalview/core/config.py
evalview/core/contract_diff.py
evalview/core/dashboard.py
evalview/core/diff.py
evalview/core/discord_notifier.py
evalview/core/drift_classifier.py
evalview/core/drift_kind.py
evalview/core/drift_tracker.py
evalview/core/eval_profiles.py
evalview/core/golden.py
evalview/core/healing.py
evalview/core/judge_cache.py
evalview/core/llm_configs.py
evalview/core/llm_provider.py
evalview/core/loader.py
evalview/core/mcp_contract.py
evalview/core/messages.py
evalview/core/model_check_scoring.py
evalview/core/model_provider_runner.py
evalview/core/model_runtime_detector.py
evalview/core/model_snapshots.py
evalview/core/noise_tracker.py
evalview/core/observability.py
evalview/core/parallel.py
evalview/core/pricing.py
evalview/core/project_state.py
evalview/core/quarantine.py
evalview/core/rationale.py
evalview/core/recommendations.py
evalview/core/regression_synth.py
evalview/core/replay_pipeline.py
evalview/core/retry.py
evalview/core/root_cause.py
evalview/core/runner.py
evalview/core/security.py
evalview/core/semantic_diff.py
evalview/core/simulation.py
evalview/core/slack_notifier.py
evalview/core/test_quality.py
evalview/core/tool_categories.py
evalview/core/tracing.py
evalview/core/turn_coherence.py
evalview/core/types.py
evalview/core/variant_clusterer.py
evalview/core/verdict.py
evalview/core/watcher.py
evalview/evaluators/__init__.py
evalview/evaluators/cost_evaluator.py
evalview/evaluators/evaluator.py
evalview/evaluators/hallucination_evaluator.py
evalview/evaluators/latency_evaluator.py
evalview/evaluators/output_evaluator.py
evalview/evaluators/pii_evaluator.py
evalview/evaluators/safety_evaluator.py
evalview/evaluators/sequence_evaluator.py
evalview/evaluators/statistical_evaluator.py
evalview/evaluators/tool_call_evaluator.py
evalview/exporters/__init__.py
evalview/exporters/html_exporter.py
evalview/importers/__init__.py
evalview/importers/log_importer.py
evalview/reporters/__init__.py
evalview/reporters/console_reporter.py
evalview/reporters/html_reporter.py
evalview/reporters/json_reporter.py
evalview/reporters/trace_live_reporter.py
evalview/reporters/trace_reporter.py
evalview/skills/__init__.py
evalview/skills/agent_runner.py
evalview/skills/agent_types.py
evalview/skills/constants.py
evalview/skills/parser.py
evalview/skills/runner.py
evalview/skills/security_scanner.py
evalview/skills/test_generator.py
evalview/skills/test_helpers.py
evalview/skills/types.py
evalview/skills/ui_utils.py
evalview/skills/validator.py
evalview/skills/adapters/__init__.py
evalview/skills/adapters/base.py
evalview/skills/adapters/claude_code_adapter.py
evalview/skills/adapters/codex_adapter.py
evalview/skills/adapters/crewai_adapter.py
evalview/skills/adapters/custom_adapter.py
evalview/skills/adapters/langgraph_adapter.py
evalview/skills/adapters/openai_assistants_adapter.py
evalview/skills/adapters/openclaw_adapter.py
evalview/skills/adapters/registry.py
evalview/skills/evaluators/__init__.py
evalview/skills/evaluators/deterministic.py
evalview/skills/evaluators/orchestrator.py
evalview/skills/evaluators/rubric.py
evalview/storage/__init__.py
evalview/storage/database.py
evalview/telemetry/__init__.py
evalview/telemetry/client.py
evalview/telemetry/config.py
evalview/telemetry/decorators.py
evalview/telemetry/events.py
evalview/templates/patterns/code-generation.yaml
evalview/templates/patterns/cost-budget.yaml
evalview/templates/patterns/customer-support.yaml
evalview/templates/patterns/data-analysis.yaml
evalview/templates/patterns/latency-budget.yaml
evalview/templates/patterns/multi-turn-memory.yaml
evalview/templates/patterns/output-format.yaml
evalview/templates/patterns/rag-citation.yaml
evalview/templates/patterns/rag-grounding.yaml
evalview/templates/patterns/research-synthesis.yaml
evalview/templates/patterns/safety-refusal.yaml
evalview/templates/patterns/tool-error-handling.yaml
evalview/templates/patterns/tool-not-called.yaml
evalview/templates/patterns/tool-sequence.yaml
evalview/templates/patterns/wrong-tool-chosen.yaml
evalview/trace_cmd/__init__.py
evalview/trace_cmd/collector.py
evalview/trace_cmd/patcher.py
evalview/trace_cmd/runner.py
evalview/tracking/__init__.py
evalview/tracking/database.py
evalview/tracking/regression.py
evalview/visualization/__init__.py
evalview/visualization/generators.py
tests/test_adapters.py
tests/test_api.py
tests/test_autopr.py
tests/test_behavioral_anomalies.py
tests/test_benchmark_hardening.py
tests/test_canary_suite.py
tests/test_celebrations.py
tests/test_check_cmd.py
tests/test_check_pipeline.py
tests/test_ci_generate_comment.py
tests/test_config_models.py
tests/test_diff_engine.py
tests/test_dogfood_e2e.py
tests/test_drift_classifier.py
tests/test_drift_tracker.py
tests/test_e2e_snapshot_check.py
tests/test_endpoint_detection.py
tests/test_evaluator_accuracy.py
tests/test_evaluator_orchestrator.py
tests/test_evaluators.py
tests/test_forbidden_tools.py
tests/test_generate_cmd.py
tests/test_golden_store.py
tests/test_healing.py
tests/test_init_cmd.py
tests/test_judge_cache.py
tests/test_llm_provider.py
tests/test_loader.py
tests/test_main_evaluator.py
tests/test_mcp_contracts.py
tests/test_mcp_server.py
tests/test_messages.py
tests/test_model_check_cmd.py
tests/test_model_check_scoring.py
tests/test_model_runtime_detector.py
tests/test_model_snapshots.py
tests/test_monitor.py
tests/test_multi_turn_evaluation.py
tests/test_new_features.py
tests/test_noise_tracker.py
tests/test_observability_regressions.py
tests/test_pii_evaluator.py
tests/test_project_state.py
tests/test_pytest_plugin.py
tests/test_rationale.py
tests/test_replay_pipeline.py
tests/test_root_cause.py
tests/test_run_cmd_tags.py
tests/test_run_guidance.py
tests/test_runner.py
tests/test_security.py
tests/test_semantic_diff.py
tests/test_simulation.py
tests/test_snapshot_generated_workflow.py
tests/test_snapshot_json_output.py
tests/test_statistical_evaluator.py
tests/test_telemetry_client.py
tests/test_turn_coherence.py
tests/test_types.py
tests/test_verdict.py
tests/test_version_check.py
tests/test_visualization_generators.py
tests/test_week1_integration.py
tests/test_week2_quarantine.py
tests/test_week2_review_fixes.py
tests/test_week2_since_and_comment.py
tests/test_week3_progress_and_drift.py