verifiers 0.3.2.dev70__tar.gz → 0.3.2.dev71__tar.gz
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/PKG-INFO +1 -1
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/tasksets/harbor/taskset.py +22 -15
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/.gitignore +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/LICENSE +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/README.md +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/pyproject.toml +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/tests/v1/conftest.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/tests/v1/fixtures/counter_tool_v1.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/tests/v1/fixtures/duet_v1.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/tests/v1/fixtures/echo_acp_resume_v1.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/tests/v1/fixtures/echo_agentic_v1.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/tests/v1/fixtures/echo_tool_v1.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/tests/v1/fixtures/echo_user_sim_v1.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/tests/v1/fixtures/echo_v1.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/tests/v1/fixtures/pyproject.toml +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/tests/v1/fixtures/tool_response_image_v1.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/tests/v1/test_color_codeword_tasks.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/tests/v1/test_configs.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/tests/v1/test_e2e.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/tests/v1/test_envs.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/tests/v1/test_graph.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/tests/v1/test_judges.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/tests/v1/test_scoring.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/tests/v1/test_taskset.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/tests/v1/test_trace.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/__init__.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/cli/commands/init.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/__init__.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/acp/__init__.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/acp/runner.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/agent.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/cli/__init__.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/cli/dashboard/__init__.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/cli/dashboard/base.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/cli/dashboard/eval.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/cli/dashboard/replay.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/cli/dashboard/validate.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/cli/debug.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/cli/eval/__init__.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/cli/eval/main.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/cli/eval/resume.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/cli/eval/runner.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/cli/gepa.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/cli/init.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/cli/output.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/cli/replay.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/cli/resolve.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/cli/resume.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/cli/validate.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/clients/__init__.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/clients/base.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/clients/client.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/clients/eval.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/clients/train.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/configs/__init__.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/configs/agent.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/configs/cli/__init__.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/configs/cli/debug.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/configs/cli/env.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/configs/cli/eval.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/configs/cli/init.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/configs/cli/replay.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/configs/cli/validate.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/configs/client.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/configs/env.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/configs/harness.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/configs/judge.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/configs/retries.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/configs/runtime.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/configs/serve.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/configs/task.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/configs/taskset.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/dialects/__init__.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/dialects/anthropic.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/dialects/base.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/dialects/chat.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/dialects/responses.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/env.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/envs/__init__.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/envs/agentic_judge/__init__.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/envs/agentic_judge/env.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/envs/best_of_n/__init__.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/envs/best_of_n/env.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/envs/isolated_verifier/__init__.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/envs/isolated_verifier/env.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/envs/shared_agentic_judge/__init__.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/envs/single_agent/__init__.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/envs/single_agent/env.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/envs/user_sim/__init__.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/envs/user_sim/env.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/episode.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/errors.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/gepa/__init__.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/gepa/adapter.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/gepa/config.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/gepa/dataset.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/gepa/reflection.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/gepa/runner.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/graph.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/harness.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/harnesses/__init__.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/harnesses/bash/__init__.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/harnesses/bash/harness.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/harnesses/browser_use/__init__.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/harnesses/browser_use/harness.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/harnesses/browser_use/program.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/harnesses/claude_code/__init__.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/harnesses/claude_code/harness.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/harnesses/codex/__init__.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/harnesses/codex/harness.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/harnesses/hermes_agent/__init__.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/harnesses/hermes_agent/harness.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/harnesses/hermes_agent/program.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/harnesses/kimi_code/__init__.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/harnesses/kimi_code/harness.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/harnesses/mini_swe_agent/__init__.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/harnesses/mini_swe_agent/harness.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/harnesses/mini_swe_agent/program.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/harnesses/node.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/harnesses/null/__init__.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/harnesses/null/harness.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/harnesses/openclaw/__init__.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/harnesses/openclaw/harness.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/harnesses/pi/__init__.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/harnesses/pi/harness.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/harnesses/pool/__init__.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/harnesses/pool/harness.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/harnesses/prime_agent/__init__.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/harnesses/prime_agent/harness.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/harnesses/rlm/__init__.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/harnesses/rlm/harness.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/harnesses/terminus_2/__init__.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/harnesses/terminus_2/harness.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/harnesses/terminus_2/program.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/harnesses/utils/__init__.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/harnesses/utils/compaction.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/harnesses/utils/core.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/harnesses/utils/install.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/harnesses/utils/launch.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/harnesses/utils/mcp.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/interception/__init__.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/interception/base.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/interception/pool.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/interception/server.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/interception/tool.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/interception/tunnel/__init__.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/interception/tunnel/base.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/interception/tunnel/custom.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/interception/tunnel/prime.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/judge.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/judges/__init__.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/judges/reference.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/judges/reference.txt +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/judges/rubric.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/judges/rubric.txt +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/mcp/__init__.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/mcp/launch.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/mcp/server.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/mcp/toolset.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/rollout.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/runtimes/__init__.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/runtimes/base.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/runtimes/docker/__init__.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/runtimes/docker/egress.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/runtimes/limiters.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/runtimes/modal.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/runtimes/prime.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/runtimes/subprocess.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/semantic.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/serve/__init__.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/serve/client.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/serve/encoding.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/serve/pool.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/serve/server.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/serve/types.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/session.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/state.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/task.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/taskset.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/tasksets/__init__.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/tasksets/harbor/__init__.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/tasksets/harbor/env.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/tasksets/lean/__init__.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/tasksets/lean/scoring.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/tasksets/lean/taskset.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/tasksets/nemo_gym/__init__.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/tasksets/nemo_gym/response.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/tasksets/nemo_gym/server.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/tasksets/nemo_gym/taskset.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/tasksets/nemo_gym/toolset.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/tasksets/openenv/__init__.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/tasksets/openenv/taskset.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/tasksets/textarena/__init__.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/tasksets/textarena/taskset.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/trace.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/types.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/utils/__init__.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/utils/aio.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/utils/artifacts.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/utils/compile.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/utils/decorators.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/utils/format.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/utils/generic.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/utils/git.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/utils/image.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/utils/interrupt.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/utils/loaders.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/utils/logging.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/utils/memory.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/utils/paths.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/utils/platform.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/utils/prime.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/utils/retries.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/utils/score.py +0 -0
- {verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/utils/version.py +0 -0
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
Metadata-Version: 2.5
|
|
2
2
|
Name: verifiers
|
|
3
|
-
Version: 0.3.2.
|
|
3
|
+
Version: 0.3.2.dev71
|
|
4
4
|
Summary: Verifiers: Environments for LLM Reinforcement Learning
|
|
5
5
|
Project-URL: Homepage, https://github.com/primeintellect-ai/verifiers
|
|
6
6
|
Project-URL: Documentation, https://github.com/primeintellect-ai/verifiers
|
|
@@ -27,7 +27,7 @@ import tempfile
|
|
|
27
27
|
import time
|
|
28
28
|
from collections.abc import Iterator
|
|
29
29
|
from functools import lru_cache
|
|
30
|
-
from pathlib import Path
|
|
30
|
+
from pathlib import Path, PurePosixPath
|
|
31
31
|
from typing import Annotated
|
|
32
32
|
|
|
33
33
|
from pydantic import BaseModel, ConfigDict, Field, TypeAdapter, ValidationError
|
|
@@ -250,31 +250,38 @@ class HarborTask(Task[HarborData]):
|
|
|
250
250
|
if not self.scoring_deferred:
|
|
251
251
|
trace.state.artifacts = await collect(runtime, self.data.artifacts)
|
|
252
252
|
|
|
253
|
-
async def stage_verifier(self, runtime: Runtime) -> None:
|
|
254
|
-
|
|
253
|
+
async def stage_verifier(self, trace: Trace, runtime: Runtime) -> None:
|
|
254
|
+
if any(
|
|
255
|
+
PurePosixPath(root).is_relative_to("/tests")
|
|
256
|
+
for root in trace.state.artifacts
|
|
257
|
+
):
|
|
258
|
+
raise TaskError("Harbor artifacts cannot restore into /tests")
|
|
255
259
|
await self.stage_tests(runtime, wipe=True)
|
|
256
260
|
self.verifier_staged = True
|
|
257
261
|
|
|
258
262
|
async def stage_tests(self, runtime: Runtime, wipe: bool = False) -> None:
|
|
259
|
-
"""
|
|
263
|
+
"""Use a dedicated verifier image's tests, or stage the task package's tests.
|
|
260
264
|
|
|
261
265
|
Raises rather than scoring stale state: a leftover reward file — planted by
|
|
262
266
|
the agent or shipped in the image — must be gone before `test.sh` runs, so a
|
|
263
267
|
removal that fails must not fall through to reading it.
|
|
264
|
-
|
|
265
|
-
`wipe` for a box we did not watch being built: a fresh container of the task's
|
|
266
|
-
image can ship its own `/tests`, and a leftover file there would be graded as
|
|
267
|
-
though it came from the package.
|
|
268
268
|
"""
|
|
269
|
-
|
|
270
|
-
|
|
271
|
-
|
|
272
|
-
|
|
273
|
-
|
|
269
|
+
# Harbor's dedicated verifier image owns the complete test suite and its
|
|
270
|
+
# dependencies. Mixing it with packaged tests can retain obsolete helpers.
|
|
271
|
+
stage = "test -f /tests/test.sh"
|
|
272
|
+
if self.data.verifier is None or self.data.verifier.image is None:
|
|
273
|
+
await runtime.write(
|
|
274
|
+
"/tmp/tests.tgz", make_tar(Path(self.data.task_dir) / "tests")
|
|
275
|
+
)
|
|
276
|
+
stage = (
|
|
277
|
+
f"{'rm -rf /tests && ' if wipe else ''}"
|
|
278
|
+
"mkdir -p /tests && tar -xzf /tmp/tests.tgz -C /tests"
|
|
279
|
+
)
|
|
280
|
+
command = (
|
|
274
281
|
"rm -f /logs/verifier/reward.json /logs/verifier/reward.txt && "
|
|
275
|
-
"mkdir -p /logs/verifier
|
|
282
|
+
f"mkdir -p /logs/verifier && {stage}"
|
|
276
283
|
)
|
|
277
|
-
result = await runtime.run(["sh", "-c",
|
|
284
|
+
result = await runtime.run(["sh", "-c", command], {})
|
|
278
285
|
if result.exit_code:
|
|
279
286
|
raise TaskError(
|
|
280
287
|
f"staging tests failed (exit {result.exit_code}): "
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
{verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/envs/isolated_verifier/__init__.py
RENAMED
|
File without changes
|
|
File without changes
|
{verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/envs/shared_agentic_judge/__init__.py
RENAMED
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
{verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/harnesses/browser_use/__init__.py
RENAMED
|
File without changes
|
{verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/harnesses/browser_use/harness.py
RENAMED
|
File without changes
|
{verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/harnesses/browser_use/program.py
RENAMED
|
File without changes
|
{verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/harnesses/claude_code/__init__.py
RENAMED
|
File without changes
|
{verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/harnesses/claude_code/harness.py
RENAMED
|
File without changes
|
|
File without changes
|
|
File without changes
|
{verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/harnesses/hermes_agent/__init__.py
RENAMED
|
File without changes
|
{verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/harnesses/hermes_agent/harness.py
RENAMED
|
File without changes
|
{verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/harnesses/hermes_agent/program.py
RENAMED
|
File without changes
|
{verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/harnesses/kimi_code/__init__.py
RENAMED
|
File without changes
|
|
File without changes
|
{verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/harnesses/mini_swe_agent/__init__.py
RENAMED
|
File without changes
|
{verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/harnesses/mini_swe_agent/harness.py
RENAMED
|
File without changes
|
{verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/harnesses/mini_swe_agent/program.py
RENAMED
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
{verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/harnesses/prime_agent/__init__.py
RENAMED
|
File without changes
|
{verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/harnesses/prime_agent/harness.py
RENAMED
|
File without changes
|
|
File without changes
|
|
File without changes
|
{verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/harnesses/terminus_2/__init__.py
RENAMED
|
File without changes
|
{verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/harnesses/terminus_2/harness.py
RENAMED
|
File without changes
|
{verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/harnesses/terminus_2/program.py
RENAMED
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
{verifiers-0.3.2.dev70 → verifiers-0.3.2.dev71}/verifiers/v1/interception/tunnel/__init__.py
RENAMED
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|