cargo-analytics

Cargo CLI — Analytics

Measurement and export: monitoring run metrics, downloading run and batch results, and exporting segment data.

See references/response-shapes.md for full JSON response structures. See references/troubleshooting.md for common errors and how to fix them. See references/examples/run-analytics.md for run metrics and error monitoring. See references/examples/exports.md for data export and download examples. For billing, usage metrics, and subscription: use the cargo-billing skill.

Bootstrap

Already signed in (cargo-ai whoami returns a workspace)? Skip to the next section.

npm install -g @cargo-ai/cli            # no global install? prefix every command with `npx @cargo-ai/cli`
cargo-ai login --email you@company.com  # emailed code, no browser; creates the account on first use
                                        # alternatives: --oauth (browser) · --token <api-token> (CI)

Every command prints JSON to stdout; failures exit non-zero with {"errorMessage": "..."}. Anything that creates a run or a batch is async — pass --wait-until-finished or poll the matching get. When the full skill bundle is installed, ../cargo/references/prerequisites.md adds the CLI version pin, token scopes, and the admin-only surface.

Scope — measure and export, not explain

This skill answers "what happened" and "give me the data": metrics, counts, downloads, exports. The moment the question becomes "why" — why did this run fail, why is the output wrong or empty, which root cause explains these errors, why is this play so expensive — switch to the cargo-diagnostics skill; its runbooks sequence the raw surfaces into a diagnosis.

The two skills chain naturally: analytics detects (error rate spiked, batch reports failures), diagnostics explains (18 of 20 failures share one root cause), then analytics retrieves the clean results once the cause is fixed and the runs re-executed.

Discover resources first

Most analytics commands require UUIDs. Discover them before querying.

Quick reference

Picking the right command:

• run get-metrics / run count — workflow-scoped, predefined aggregations. Best when you already have a workflowUuid.
• orchestration query execute — ad-hoc SQL across the entire workspace (runs, batches, spans, records). Best for cross-workflow analytics, per-node breakdowns, and time-series.
• run download / run download-outputs — per-record output retrieval.
• segment download / storage query execute — storage data (Companies, Contacts, …).

Workflow run metrics

Aggregated metrics for workflow runs (success/error rates, credits per node).

Run count

Count runs matching specific criteria — useful for monitoring.

Supports: --statuses, --batch-uuid, --release-uuid, --is-finished, --created-after, --created-before, --record-id, --record-title.

For cross-workflow analytics or shapes that run count doesn't expose (per-node failure breakdowns, p95 durations, error rate over time), use orchestration query execute — see the Ad-hoc execution analytics section.

Ad-hoc execution analytics (orchestration query)

Run SQL against orchestration runtime tables — runs, batches, spans, records — for analytics that the canned metrics commands don't cover. Tables are referenced without a schema prefix; workspace scoping is automatic. See cargo-orchestration/references/examples/queries.md for schemas and limits.

Read-only and capped: 30s execution time, 10 000 result rows, 10 000 000 rows scanned. Narrow with a created_at/execution_started_at predicate to stay under the row-scan cap.

Downloading run results

Two distinct commands — pick the right one for the job.

run download — one row per run, one column per node (gzipped CSV)

Returns {"url": "..."} — a signed URL to a gzipped CSV. Each row is a run: _uuid, _workspace_uuid, _workflow_uuid, _record_id, _record_title, _created_at, _finished_at, _status, _error_message, followed by one column per node slug.

Each node column holds that execution's title — a truncated human-readable summary, not the node's output. There is no runContext and no executions[] in this file. Treat it as a status board across many runs (which node errored, on which record), never as evidence of what a node produced — the same rule cargo-diagnostics applies to title everywhere else.

run download-outputs — per-run input + output (CSV/JSON via signed URL)

This is the canonical way to get action results out of the platform. Maps to API POST /v1/orchestration/runs/download-outputs. Returns {"url": "..."} — a signed URL to a CSV (default) or JSON file. One row per run: the same _-prefixed run metadata, plus input (the first node's resolved config) and output (the chosen node's context, defaulting to the last executed node when --output-node-slug is omitted).

To find the output-node-slug: cargo-ai orchestration release get <release-uuid> → look at nodes[].slug. The terminal output node is typically named output or end. Without --limit, the file covers every matching run of the workflow, so pass one when you only need a sample.

Per record instead of per run: cargo-ai orchestration record download-outputs takes the same --workflow-uuid / --output-node-slug and emits one row per record. It pages with --limit and --offset (CLI ≥ 1.0.90) — the way to export a set too large for a single file is to walk it in fixed slices (--limit 1000 --offset 0, then --offset 1000, …) rather than requesting everything at once. run download-outputs pages the same way, over runs.

Getting the full runContext for several runs

You can't, in one call. The full per-node context is a per-run S3 object, and orchestration run get <run-uuid> is the only command that hydrates it — one run at a time. The two exports above are projections: download gives you node titles across many runs, download-outputs gives you first-node input + one node's output across many runs. For everything in between, loop run get over the UUIDs from the discovery ladder in ../cargo-diagnostics/references/run-trace.md § 0.

Orchestration SQL is not an alternative here: runs and spans carry status, timing, and credits, but no node input/output columns.

Downloading batch results

To find the output-node-slug: run cargo-ai orchestration release get <release-uuid> (get the release UUID from the batch) and look at nodes[].slug.

Handling partial batch failures

A batch with status: "success" can still contain individual run failures. Always inspect the batch for errors before treating results as complete.

Step 1 — Check the batch summary:

Step 2 — Count and download the failed runs:

Step 3 — Diagnose. Working out why they failed — grouping failures by root cause, picking exemplar runs, reading runContext — is the cargo-diagnostics skill's job: load ../cargo-diagnostics/references/batch-error-sweep.md and feed it the batch UUID.

Step 4 — Re-run only the failed records:

After the diagnosis and fixing the underlying issue (connector credentials, bad input data, rate limits):

Filtering by node output slug:

To download only a specific node's output from a batch (e.g. just the enrichment node, not the full run):

Segment data export

Filter JSON uses conjonction (not conjunction) — this is intentional. See the cargo-orchestration skill's references/filter-syntax.md for the full filter syntax.

IMPORTANT: segment download requires --model-uuid, not --segment-uuid. Get the modelUuid from segment list.

For live paginated queries with enrichment, use segmentation segment fetch from the cargo-orchestration skill.

Help

Every command supports --help: