LICENSE
README.md
pyproject.toml
src/evalwarden/__init__.py
src/evalwarden/calibration.py
src/evalwarden/cli.py
src/evalwarden/coverage.py
src/evalwarden/dataset.py
src/evalwarden/engine.py
src/evalwarden/ensemble.py
src/evalwarden/model.py
src/evalwarden/noise.py
src/evalwarden/trajectory.py
src/evalwarden.egg-info/PKG-INFO
src/evalwarden.egg-info/SOURCES.txt
src/evalwarden.egg-info/dependency_links.txt
src/evalwarden.egg-info/entry_points.txt
src/evalwarden.egg-info/requires.txt
src/evalwarden.egg-info/top_level.txt
src/evalwarden/adapters/__init__.py
src/evalwarden/adapters/inspect_ai.py
src/evalwarden/adapters/promptfoo.py
src/evalwarden/checks/__init__.py
src/evalwarden/checks/base.py
src/evalwarden/checks/cost.py
src/evalwarden/checks/data.py
src/evalwarden/checks/env_leakage.py
src/evalwarden/checks/grader.py
src/evalwarden/checks/judge.py
src/evalwarden/checks/noise.py
src/evalwarden/checks/traj.py
src/evalwarden/demo/agent_loop/README.md
src/evalwarden/demo/agent_loop/dataset.json
src/evalwarden/demo/agent_loop/environment.json
src/evalwarden/demo/agent_loop/grader.json
src/evalwarden/demo/agent_loop/run.json
src/evalwarden/demo/agent_loop/trajectories.jsonl
src/evalwarden/demo/agent_ordinary/README.md
src/evalwarden/demo/agent_ordinary/dataset.json
src/evalwarden/demo/agent_ordinary/environment.json
src/evalwarden/demo/agent_ordinary/grader.json
src/evalwarden/demo/agent_ordinary/run.json
src/evalwarden/demo/agent_ordinary/trajectories.jsonl
src/evalwarden/demo/cost_clean/README.md
src/evalwarden/demo/cost_clean/dataset.json
src/evalwarden/demo/cost_clean/environment.json
src/evalwarden/demo/cost_clean/grader.json
src/evalwarden/demo/cost_clean/run.json
src/evalwarden/demo/cost_wasteful/README.md
src/evalwarden/demo/cost_wasteful/dataset.json
src/evalwarden/demo/cost_wasteful/environment.json
src/evalwarden/demo/cost_wasteful/grader.json
src/evalwarden/demo/cost_wasteful/run.json
src/evalwarden/demo/hardened/README.md
src/evalwarden/demo/hardened/dataset.json
src/evalwarden/demo/hardened/environment.json
src/evalwarden/demo/hardened/grader.json
src/evalwarden/demo/hardened/run.json
src/evalwarden/demo/hardened/run_cheat.json
src/evalwarden/demo/judge_bad/README.md
src/evalwarden/demo/judge_bad/dataset.json
src/evalwarden/demo/judge_bad/environment.json
src/evalwarden/demo/judge_bad/grader.json
src/evalwarden/demo/judge_bad/judge_run.json
src/evalwarden/demo/judge_bad/run.json
src/evalwarden/demo/judge_clean/README.md
src/evalwarden/demo/judge_clean/dataset.json
src/evalwarden/demo/judge_clean/environment.json
src/evalwarden/demo/judge_clean/grader.json
src/evalwarden/demo/judge_clean/judge_run.json
src/evalwarden/demo/judge_clean/run.json
src/evalwarden/demo/judge_panel/README.md
src/evalwarden/demo/judge_panel/dataset.json
src/evalwarden/demo/judge_panel/environment.json
src/evalwarden/demo/judge_panel/grader.json
src/evalwarden/demo/judge_panel/judge_run.json
src/evalwarden/demo/judge_panel/run.json
src/evalwarden/demo/leaky/README.md
src/evalwarden/demo/leaky/dataset.json
src/evalwarden/demo/leaky/environment.json
src/evalwarden/demo/leaky/gold_map.json
src/evalwarden/demo/leaky/grader.json
src/evalwarden/demo/leaky/run.json
src/evalwarden/demo/leaky/gold/patch-task-001.diff
src/evalwarden/demo/leaky/gold/patch-task-002.diff
src/evalwarden/demo/leaky/gold/patch-task-003.diff
src/evalwarden/demo/promptfoo_bad/README.md
src/evalwarden/demo/promptfoo_bad/promptfooconfig.yaml
src/evalwarden/demo/promptfoo_bad/results.json
src/evalwarden/demo/promptfoo_clean/README.md
src/evalwarden/demo/promptfoo_clean/promptfooconfig.yaml
src/evalwarden/demo/promptfoo_clean/results.json
src/evalwarden/reporters/__init__.py
src/evalwarden/reporters/html.py
src/evalwarden/reporters/json_report.py
src/evalwarden/reporters/records.py
src/evalwarden/reporters/report_card.py
src/evalwarden/reporters/sarif.py
src/evalwarden/reporters/terminal.py
tests/test_adapter.py
tests/test_adapter_wiring.py
tests/test_calibration.py
tests/test_cli.py
tests/test_cost.py
tests/test_coverage.py
tests/test_data.py
tests/test_engine.py
tests/test_ensemble.py
tests/test_env_leakage.py
tests/test_formats.py
tests/test_grader.py
tests/test_judge.py
tests/test_noise.py
tests/test_noise_checks.py
tests/test_panel_coverage.py
tests/test_promptfoo.py
tests/test_report_card.py
tests/test_traj.py
tests/test_trajectory.py