rewardkit

Help the user write task verifiers with Reward Kit. Reward Kit is a lightweight Python package that turns a directory of criteria files into a reward score. Each criterion is a Python function call or a TOML judge file; folders become separate rewards. ## Setup in a Harbor task Put criteria alongside `test.sh` in the task's `tests/` directory: ``` tests/ ├── test.sh ├── checks.py # programmatic criteria └── judge.toml # optional LLM/agent judge ``` `tests/test.sh`: ```bash #!/bin/bash uvx harbor-rewardkit@0.1 /tests ``` This runs all criteria in `/tests/` against the workspace at `/app` and writes `/logs/verifier/reward.json`. Defaults match Harbor's conventions — no extra config needed. If judge criteria need API keys, pass them through `task.toml`: ```toml [verifier.env] ANTHROPIC_API_KEY = "${ANTHROPIC_API_KEY}" ``` ## Programmatic criteria Call built-ins from any `.py` file in `tests/`: ```python import rewardkit as rk rk.file_exists("output.txt") rk.file_contains("output.txt", "hello") rk.command_succeeds("python main.py", weight=2.0) rk.json_key_equals("result.json", "status", "ok") ``` All criteria accept `weight` (default `1.0`) and `isolated` (default `False`, runs in overlayfs so side effects don't leak). ### Available built-ins - **Files**: `file_exists`, `file_not_exists`, `file_contains`, `file_contains_regex`, `file_matches`, `files_equal`, `diff_ratio` - **Commands**: `command_succeeds`, `command_output_contains`, `command_output_matches`, `command_output_matches_regex` (30s default timeout, optional `cwd`) - **Data**: `json_key_equals`, `json_path_equals`, `csv_cell_equals`, `xlsx_cell_equals` (needs `[office]` extra), `sqlite_query_equals` - **HTTP**: `http_status_equals`, `http_response_contains` - **Images**: `image_similarity`, `image_size_equals` (needs `[image]` extra) - **Trajectory**: `trajectory_tool_used`, `trajectory_tool_not_used`, `trajectory_turn_count` For extras, install with `uv tool install harbor-rewardkit[all]`. ## Custom criteria Use the `@criterion` decorator. First parameter is always `workspace: Path`. Returns `bool` or `float`: ```python from pathlib import Path from rewardkit import criterion @criterion def has_valid_output(workspace: Path) -> bool: return (workspace / "output.txt").read_text().strip() != "" ``` Zero-parameter criteria auto-register. Criteria with extra args must be called via `rk`: ```python @criterion(description="output has at least {n} lines") def has_n_lines(workspace: Path, n: int) -> bool: return len((workspace / "output.txt").read_text().splitlines()) >= n rk.has_n_lines(10, weight=2.0) rk.has_n_lines(50, weight=1.0) ``` For criteria shared across reward subdirs, define with `shared=True` in a root-level file and call from subdirs. ## Judge criteria (LLM or agent-as-a-judge) For subjective checks (quality, readability, edge cases), create a TOML file: ```toml [judge] judge = "anthropic/claude-sonnet-4-6" # LiteLLM model string files = ["/app/main.py"] [[criterion]] description = "Is the code correct?" type = "binary" [[criterion]] description = "How readable is the code?" type = "likert" points = 5 weight = 2.0 ``` Criterion types: - `binary` — yes/no → 1.0 or 0.0 - `likert` — 1..points, normalized to [0, 1] - `numeric` — min..max, normalized to [0, 1] ### Agent judges Agent judges shell out to a CLI and can explore the filesystem: ```toml [judge] judge = "claude-code" model = "anthropic/claude-sonnet-4-6" isolated = true [[criterion]] description = "Does the solution handle edge cases?" type = "binary" ``` Slower and more expensive than LLM judges, but they can run commands and inspect files. ### Useful `[judge]` options `timeout` (default 300), `reasoning_effort` (`low`|`medium`|`high`), `reference` (path to reference solution), `atif-trajectory` (evaluate the agent's trajectory), `weight`, `prompt_template` (custom prompt with `{criteria}` placeholder). ### Scoring aggregation ```toml [scoring] aggregation = "all_pass" # weighted_mean | all_pass | any_pass | threshold threshold = 0.7 # only for threshold ``` Only affects aggregation *within* this TOML file. ## Multi-reward tasks Put criteria in subdirectories — each becomes a separate reward: ``` tests/ ├── test.sh ├── correctness/ │ └── check.py ├── structure/ │ └── files_exist.py └── quality/ └── quality.toml ``` Produces: ```json { "correctness": 0.75, "structure": 1.0, "quality": 0.6 } ``` ## Output files - `/logs/verifier/reward.json` — per-reward scores - `/logs/verifier/reward-details.json` — per-criterion results, judge reasoning, errors ## When to reach for what - **Use built-ins** for file existence, string matches, command output, JSON/CSV checks, HTTP probes. - **Use `@criterion`** when logic is task-specific but still programmatic. - **Use LLM judges** for subjective quality dimensions (readability, correctness of prose). - **Use agent judges** when the rubric requires exploring the filesystem or running code (e.g. "does the test suite actually pass?"). - **Use subdirectories** when you want separate scores (correctness vs structure vs quality) rather than one blended number. - **Use `isolated=True`** for any criterion that runs mutating commands, so it doesn't corrupt the workspace for other criteria. ## Working example See `examples/tasks/reward-kit-example/` in the Harbor repo.