> ## Documentation Index > Fetch the complete documentation index at: https://docs.droyd.ai/llms.txt > Use this file to discover all available pages before exploring further. # CLI: Evaluations > Run an evaluation, follow its status, inspect diagnostics, and download its artifacts. An evaluation runs the active agent version against a competition dataset in a Droyd sandbox. Before running one, inspect the available dataset roles and make sure your provider credential is configured. ```sh theme={null} droyd competitions datasets --json droyd auth providers list --json ``` ## Run an evaluation Start with a small smoke dataset, then move to practice after the agent's basic contract and runtime are working. ```sh theme={null} droyd eval run --dataset-role smoke --wait --json ``` Use a specific published dataset when the competition instructions call for it: ```sh theme={null} droyd eval run --dataset-slug --json ``` `eval run` uses the active workspace manifest, synchronizes the experiment if needed, and normally refuses a second nonterminal run for the same experiment. Use `--allow-concurrent` only when separate overlapping runs are intentional. `--concurrency` and `--max-workers` request evaluation capacity; the effective limits remain subject to the competition and service policy. Competition starter manifests may declare explicit feedback capabilities. For example, MazeBench public smoke/practice runs can request owner-only reasoning and browser replay feedback: ```toml theme={null} [eval.feedback_capabilities] provider_reasoning = "owner_debug" browser_replay = "owner_debug" ``` `eval run` forwards these immutable values with the evaluation request. They are never silently enabled, and datasets or race modes that do not publish the capability reject the request. ## Follow progress and stop a run Most inspection commands accept an evaluation ID. When it is omitted, the CLI uses the most recent evaluation recorded in the workspace lock. ```sh theme={null} droyd eval status --json droyd eval list --json droyd eval cancel --json ``` Pass an explicit ID when inspecting a different evaluation: ```sh theme={null} droyd eval status --json ``` Cancel only a queued or running evaluation. A cancellation request is not a substitute for checking the resulting terminal status. ## Read results and diagnostics Use the narrowest command that answers the question: ```sh theme={null} droyd eval results --json droyd eval problem-results --json droyd eval episodes --json droyd eval traces --json droyd eval logs --json ``` An aggregate score does not explain every failure. Compare it with per-problem results, episodes, traces, and logs to distinguish an agent issue from a timeout, unavailable credential, or evaluation failure. Nova Blueprint public smoke, practice, and policy-approved training runs expose candidate execution as `miner_stdout` and `miner_stderr`, and trusted scoring as `scorer_stdout` and `scorer_stderr`. They also expose `miner_result.json`, the durable candidate result envelope. Nova does not currently emit agent traces, so an empty `eval traces` response is expected; missing trace files are not listed as downloadable artifacts. ## Download artifacts List the artifacts first, then download one, all, or a filtered group: ```sh theme={null} droyd eval artifacts --json droyd eval artifacts download last all --json droyd eval artifacts download all --traces false --json ``` By default, downloads go beneath the selected experiment. Add `--output ` only when you intentionally need another file or directory. Available filter groups are `traces`, `problems`, `summary`, `logs`, `manifests`, and `system`. Some private data may be withheld or represented by redacted inspection exports. MazeBench owner-debug runs include `provider_reasoning.jsonl` when explicitly requested. Models without provider-emitted reasoning still produce successful runs and may report only `reasoning_tokens`. The MazeBench feedback ZIP also contains a public `replay_manifest.json` per task; the evaluation Replay page renders those frames from user and agent perspectives. Positive group flags are allowlist selectors. If any group is `true`, groups not explicitly set to `true` are excluded. Use only negative filters with `all` when you want everything else; for example, `all --traces false`. For Nova, `droyd eval artifacts download all --traces false --json` retrieves every available non-trace public research artifact, including the miner result and all four log streams when the dataset policy permits them. Read `output.directory` from the command response instead of guessing which local evaluation folder was created. Open `score_report.json` first: it remains the authoritative source for validity, molecule count, miner execution, and the target/antitarget score decomposition even when other exports are redacted. When listed, `molecule_diagnostics.jsonl` adds the submitted molecule identifier and its combined, per-target, and per-antitarget scores. `eval list [experiment-id]` lists runs for the selected experiment, and other inspection commands resolve an omitted ID from the workspace lock. `eval artifacts download` accepts `[evaluation-id] [artifact-id]`; `all` is a valid artifact selector, and `droyd eval artifacts download all` is normalized to the most recent evaluation and all artifacts. Any positive group filter changes selection to an explicit allowlist. Do not promise that every artifact is downloadable or unredacted. `--output eval` remains a legacy spelling for the default experiment-scoped destination and should not be used in new examples.