CHANGELOG.md
LICENSE
README.md
pyproject.toml
src/tool_eval_bench/__init__.py
src/tool_eval_bench/__main__.py
src/tool_eval_bench/_version.py
src/tool_eval_bench/api.py
src/tool_eval_bench/py.typed
src/tool_eval_bench/schema.py
src/tool_eval_bench.egg-info/PKG-INFO
src/tool_eval_bench.egg-info/SOURCES.txt
src/tool_eval_bench.egg-info/dependency_links.txt
src/tool_eval_bench.egg-info/entry_points.txt
src/tool_eval_bench.egg-info/requires.txt
src/tool_eval_bench.egg-info/scm_file_list.json
src/tool_eval_bench.egg-info/scm_version.json
src/tool_eval_bench.egg-info/top_level.txt
src/tool_eval_bench/adapters/__init__.py
src/tool_eval_bench/adapters/anthropic.py
src/tool_eval_bench/adapters/base.py
src/tool_eval_bench/adapters/factory.py
src/tool_eval_bench/adapters/gemini.py
src/tool_eval_bench/adapters/http_retry.py
src/tool_eval_bench/adapters/measurement.py
src/tool_eval_bench/adapters/openai_compat.py
src/tool_eval_bench/adapters/requests.py
src/tool_eval_bench/adapters/systemone.py
src/tool_eval_bench/adapters/wire_format.py
src/tool_eval_bench/application/__init__.py
src/tool_eval_bench/application/decision_audit.py
src/tool_eval_bench/application/finalization.py
src/tool_eval_bench/application/mode_runs.py
src/tool_eval_bench/application/run_config.py
src/tool_eval_bench/application/run_context.py
src/tool_eval_bench/application/run_queries.py
src/tool_eval_bench/application/service.py
src/tool_eval_bench/cli/__init__.py
src/tool_eval_bench/cli/bench.py
src/tool_eval_bench/cli/command_registry.py
src/tool_eval_bench/cli/commands.py
src/tool_eval_bench/cli/compare_report.py
src/tool_eval_bench/cli/decision_live_display.py
src/tool_eval_bench/cli/dispatch.py
src/tool_eval_bench/cli/display.py
src/tool_eval_bench/cli/headless.py
src/tool_eval_bench/cli/held_out.py
src/tool_eval_bench/cli/helpers.py
src/tool_eval_bench/cli/history.py
src/tool_eval_bench/cli/leaderboard.py
src/tool_eval_bench/cli/legacy_parser.py
src/tool_eval_bench/cli/local_commands.py
src/tool_eval_bench/cli/model_probe.py
src/tool_eval_bench/cli/modes.py
src/tool_eval_bench/cli/parser.py
src/tool_eval_bench/cli/perf.py
src/tool_eval_bench/cli/plugin_datasets.py
src/tool_eval_bench/cli/plugin_lifecycle.py
src/tool_eval_bench/cli/plugin_progress.py
src/tool_eval_bench/cli/plugin_runners.py
src/tool_eval_bench/cli/pressure.py
src/tool_eval_bench/cli/probe.py
src/tool_eval_bench/cli/provider_env.py
src/tool_eval_bench/cli/resolve.py
src/tool_eval_bench/cli/run_io.py
src/tool_eval_bench/cli/scored_run.py
src/tool_eval_bench/cli/server.py
src/tool_eval_bench/cli/spec_bench.py
src/tool_eval_bench/cli/spec_live_display.py
src/tool_eval_bench/cli/spec_live_rendering.py
src/tool_eval_bench/cli/timeout_advice.py
src/tool_eval_bench/compare_reports/__init__.py
src/tool_eval_bench/compare_reports/_common.py
src/tool_eval_bench/compare_reports/summary.py
src/tool_eval_bench/compare_reports/tool_eval.py
src/tool_eval_bench/domain/__init__.py
src/tool_eval_bench/domain/adapters.py
src/tool_eval_bench/domain/decision.py
src/tool_eval_bench/domain/engines.py
src/tool_eval_bench/domain/errors.py
src/tool_eval_bench/domain/filler.py
src/tool_eval_bench/domain/measurement.py
src/tool_eval_bench/domain/models.py
src/tool_eval_bench/domain/plugin.py
src/tool_eval_bench/domain/redaction.py
src/tool_eval_bench/domain/scenarios.py
src/tool_eval_bench/domain/spec_decode.py
src/tool_eval_bench/domain/tools.py
src/tool_eval_bench/domain/tools_large.py
src/tool_eval_bench/evals/__init__.py
src/tool_eval_bench/evals/helpers.py
src/tool_eval_bench/evals/milestones.py
src/tool_eval_bench/evals/noise.py
src/tool_eval_bench/evals/packs.py
src/tool_eval_bench/evals/variants.py
src/tool_eval_bench/evals/yaml_loader.py
src/tool_eval_bench/evals/scenarios/__init__.py
src/tool_eval_bench/evals/scenarios/_registry.py
src/tool_eval_bench/evals/scenarios/adversarial/__init__.py
src/tool_eval_bench/evals/scenarios/adversarial/_shared.py
src/tool_eval_bench/evals/scenarios/adversarial/tc57.py
src/tool_eval_bench/evals/scenarios/adversarial/tc58.py
src/tool_eval_bench/evals/scenarios/adversarial/tc59.py
src/tool_eval_bench/evals/scenarios/adversarial/tc60.py
src/tool_eval_bench/evals/scenarios/agentic/__init__.py
src/tool_eval_bench/evals/scenarios/agentic/tc22.py
src/tool_eval_bench/evals/scenarios/agentic/tc23.py
src/tool_eval_bench/evals/scenarios/agentic/tc24.py
src/tool_eval_bench/evals/scenarios/agentic/tc25.py
src/tool_eval_bench/evals/scenarios/agentic/tc26.py
src/tool_eval_bench/evals/scenarios/agentic/tc27.py
src/tool_eval_bench/evals/scenarios/agentic/tc28.py
src/tool_eval_bench/evals/scenarios/agentic/tc29.py
src/tool_eval_bench/evals/scenarios/agentic/tc30.py
src/tool_eval_bench/evals/scenarios/agentic/tc31.py
src/tool_eval_bench/evals/scenarios/agentic/tc32.py
src/tool_eval_bench/evals/scenarios/agentic/tc33.py
src/tool_eval_bench/evals/scenarios/agentic/tc34.py
src/tool_eval_bench/evals/scenarios/agentic/tc35.py
src/tool_eval_bench/evals/scenarios/agentic/tc36.py
src/tool_eval_bench/evals/scenarios/agentic/tc41.py
src/tool_eval_bench/evals/scenarios/agentic/tc42.py
src/tool_eval_bench/evals/scenarios/agentic/tc43.py
src/tool_eval_bench/evals/scenarios/agentic/tc44.py
src/tool_eval_bench/evals/scenarios/agentic/tc45.py
src/tool_eval_bench/evals/scenarios/agentic/tc46.py
src/tool_eval_bench/evals/scenarios/agentic/tc47.py
src/tool_eval_bench/evals/scenarios/agentic/tc48.py
src/tool_eval_bench/evals/scenarios/agentic/tc49.py
src/tool_eval_bench/evals/scenarios/agentic/tc50.py
src/tool_eval_bench/evals/scenarios/core/__init__.py
src/tool_eval_bench/evals/scenarios/core/_shared.py
src/tool_eval_bench/evals/scenarios/core/tc01.py
src/tool_eval_bench/evals/scenarios/core/tc02.py
src/tool_eval_bench/evals/scenarios/core/tc03.py
src/tool_eval_bench/evals/scenarios/core/tc04.py
src/tool_eval_bench/evals/scenarios/core/tc05.py
src/tool_eval_bench/evals/scenarios/core/tc06.py
src/tool_eval_bench/evals/scenarios/core/tc07.py
src/tool_eval_bench/evals/scenarios/core/tc08.py
src/tool_eval_bench/evals/scenarios/core/tc09.py
src/tool_eval_bench/evals/scenarios/core/tc10.py
src/tool_eval_bench/evals/scenarios/core/tc11.py
src/tool_eval_bench/evals/scenarios/core/tc12.py
src/tool_eval_bench/evals/scenarios/core/tc13.py
src/tool_eval_bench/evals/scenarios/core/tc14.py
src/tool_eval_bench/evals/scenarios/core/tc15.py
src/tool_eval_bench/evals/scenarios/extended/__init__.py
src/tool_eval_bench/evals/scenarios/extended/_shared.py
src/tool_eval_bench/evals/scenarios/extended/tc16.py
src/tool_eval_bench/evals/scenarios/extended/tc17.py
src/tool_eval_bench/evals/scenarios/extended/tc18.py
src/tool_eval_bench/evals/scenarios/extended/tc19.py
src/tool_eval_bench/evals/scenarios/extended/tc20.py
src/tool_eval_bench/evals/scenarios/extended/tc21.py
src/tool_eval_bench/evals/scenarios/hardmode/__init__.py
src/tool_eval_bench/evals/scenarios/hardmode/_shared.py
src/tool_eval_bench/evals/scenarios/hardmode/tc70.py
src/tool_eval_bench/evals/scenarios/hardmode/tc71.py
src/tool_eval_bench/evals/scenarios/hardmode/tc72.py
src/tool_eval_bench/evals/scenarios/hardmode/tc73.py
src/tool_eval_bench/evals/scenarios/hardmode/tc74.py
src/tool_eval_bench/evals/scenarios/hardmode_documents/__init__.py
src/tool_eval_bench/evals/scenarios/hardmode_documents/_shared.py
src/tool_eval_bench/evals/scenarios/hardmode_documents/tc93.py
src/tool_eval_bench/evals/scenarios/hardmode_documents/tc94.py
src/tool_eval_bench/evals/scenarios/hardmode_documents/tc95.py
src/tool_eval_bench/evals/scenarios/hardmode_documents/tc96.py
src/tool_eval_bench/evals/scenarios/hardmode_documents/tc97.py
src/tool_eval_bench/evals/scenarios/hardmode_expanded/__init__.py
src/tool_eval_bench/evals/scenarios/hardmode_expanded/_shared.py
src/tool_eval_bench/evals/scenarios/hardmode_expanded/tc75.py
src/tool_eval_bench/evals/scenarios/hardmode_expanded/tc76.py
src/tool_eval_bench/evals/scenarios/hardmode_expanded/tc77.py
src/tool_eval_bench/evals/scenarios/hardmode_expanded/tc78.py
src/tool_eval_bench/evals/scenarios/hardmode_expanded/tc79.py
src/tool_eval_bench/evals/scenarios/hardmode_expanded/tc80.py
src/tool_eval_bench/evals/scenarios/hardmode_expanded/tc81.py
src/tool_eval_bench/evals/scenarios/hardmode_expanded/tc82.py
src/tool_eval_bench/evals/scenarios/hardmode_expanded/tc83.py
src/tool_eval_bench/evals/scenarios/hardmode_expanded/tc84.py
src/tool_eval_bench/evals/scenarios/hardmode_governance/__init__.py
src/tool_eval_bench/evals/scenarios/hardmode_governance/_shared.py
src/tool_eval_bench/evals/scenarios/hardmode_governance/tc90.py
src/tool_eval_bench/evals/scenarios/hardmode_governance/tc91.py
src/tool_eval_bench/evals/scenarios/hardmode_governance/tc92.py
src/tool_eval_bench/evals/scenarios/hardmode_transactional/__init__.py
src/tool_eval_bench/evals/scenarios/hardmode_transactional/_shared.py
src/tool_eval_bench/evals/scenarios/hardmode_transactional/tc85.py
src/tool_eval_bench/evals/scenarios/hardmode_transactional/tc86.py
src/tool_eval_bench/evals/scenarios/hardmode_transactional/tc87.py
src/tool_eval_bench/evals/scenarios/hardmode_transactional/tc88.py
src/tool_eval_bench/evals/scenarios/hardmode_transactional/tc89.py
src/tool_eval_bench/evals/scenarios/large_toolset/__init__.py
src/tool_eval_bench/evals/scenarios/large_toolset/_shared.py
src/tool_eval_bench/evals/scenarios/large_toolset/tc37.py
src/tool_eval_bench/evals/scenarios/large_toolset/tc38.py
src/tool_eval_bench/evals/scenarios/large_toolset/tc39.py
src/tool_eval_bench/evals/scenarios/large_toolset/tc40.py
src/tool_eval_bench/evals/scenarios/planning/__init__.py
src/tool_eval_bench/evals/scenarios/planning/_shared.py
src/tool_eval_bench/evals/scenarios/planning/tc51.py
src/tool_eval_bench/evals/scenarios/planning/tc52.py
src/tool_eval_bench/evals/scenarios/planning/tc53.py
src/tool_eval_bench/evals/scenarios/planning/tc54.py
src/tool_eval_bench/evals/scenarios/planning/tc55.py
src/tool_eval_bench/evals/scenarios/planning/tc56.py
src/tool_eval_bench/evals/scenarios/planning/tc61.py
src/tool_eval_bench/evals/scenarios/planning/tc62.py
src/tool_eval_bench/evals/scenarios/planning/tc63.py
src/tool_eval_bench/evals/scenarios/structured/__init__.py
src/tool_eval_bench/evals/scenarios/structured/_shared.py
src/tool_eval_bench/evals/scenarios/structured/tc64.py
src/tool_eval_bench/evals/scenarios/structured/tc65.py
src/tool_eval_bench/evals/scenarios/structured/tc66.py
src/tool_eval_bench/evals/scenarios/structured/tc67.py
src/tool_eval_bench/evals/scenarios/structured/tc68.py
src/tool_eval_bench/evals/scenarios/structured/tc69.py
src/tool_eval_bench/evals/yaml_scenarios/__init__.py
src/tool_eval_bench/evals/yaml_scenarios/chained_lookup.yaml
src/tool_eval_bench/evals/yaml_scenarios/no_tool_needed.yaml
src/tool_eval_bench/evals/yaml_scenarios/weather.yaml
src/tool_eval_bench/plugins/__init__.py
src/tool_eval_bench/plugins/hf_utils.py
src/tool_eval_bench/plugins/registry.py
src/tool_eval_bench/plugins/decision/__init__.py
src/tool_eval_bench/plugins/decision/evaluator.py
src/tool_eval_bench/plugins/decision/live.py
src/tool_eval_bench/plugins/decision/metrics.py
src/tool_eval_bench/plugins/decision/plugin.py
src/tool_eval_bench/plugins/decision/render.py
src/tool_eval_bench/plugins/decision/typed_decisions.py
src/tool_eval_bench/plugins/decision/vendor/typed_decisions/LICENSE
src/tool_eval_bench/plugins/decision/vendor/typed_decisions/NOTICE
src/tool_eval_bench/plugins/decision/vendor/typed_decisions/manifest.json
src/tool_eval_bench/plugins/decision/vendor/typed_decisions/test.jsonl.gz
src/tool_eval_bench/plugins/gsm8k/__init__.py
src/tool_eval_bench/plugins/gsm8k/dataset.py
src/tool_eval_bench/plugins/gsm8k/evaluator.py
src/tool_eval_bench/plugins/gsm8k/plugin.py
src/tool_eval_bench/plugins/gsm8k/prompts.py
src/tool_eval_bench/plugins/ifeval/__init__.py
src/tool_eval_bench/plugins/ifeval/checkers.py
src/tool_eval_bench/plugins/ifeval/dataset.py
src/tool_eval_bench/plugins/ifeval/evaluator.py
src/tool_eval_bench/plugins/ifeval/plugin.py
src/tool_eval_bench/plugins/mmlu/__init__.py
src/tool_eval_bench/plugins/mmlu/dataset.py
src/tool_eval_bench/plugins/mmlu/evaluator.py
src/tool_eval_bench/plugins/mmlu/plugin.py
src/tool_eval_bench/plugins/mmlu/prompts.py
src/tool_eval_bench/plugins/needle/__init__.py
src/tool_eval_bench/plugins/needle/haystack.py
src/tool_eval_bench/plugins/needle/plugin.py
src/tool_eval_bench/runner/__init__.py
src/tool_eval_bench/runner/context_pressure.py
src/tool_eval_bench/runner/llama_benchy.py
src/tool_eval_bench/runner/orchestrator.py
src/tool_eval_bench/runner/service.py
src/tool_eval_bench/runner/spec_detection.py
src/tool_eval_bench/runner/spec_live.py
src/tool_eval_bench/runner/speculative.py
src/tool_eval_bench/runner/throughput.py
src/tool_eval_bench/storage/__init__.py
src/tool_eval_bench/storage/db.py
src/tool_eval_bench/storage/reports/__init__.py
src/tool_eval_bench/storage/reports/_common.py
src/tool_eval_bench/storage/reports/mode.py
src/tool_eval_bench/storage/reports/pressure.py
src/tool_eval_bench/storage/reports/scenario.py
src/tool_eval_bench/storage/reports/spec_decode.py
src/tool_eval_bench/storage/reports/summary.py
src/tool_eval_bench/storage/reports/throughput.py
src/tool_eval_bench/utils/__init__.py
src/tool_eval_bench/utils/fingerprint.py
src/tool_eval_bench/utils/headers.py
src/tool_eval_bench/utils/ids.py
src/tool_eval_bench/utils/metadata.py
src/tool_eval_bench/utils/openai_compat.py
src/tool_eval_bench/utils/system_prompt.py
src/tool_eval_bench/utils/tokenizers.py
src/tool_eval_bench/utils/urls.py