Skip to main content
Start every investigation with the run overview. It returns the first 20 immediate steps in the root run, including persisted summaries when available. Every command that targets one run accepts either its Sovara UUID (or an unambiguous UUID prefix) or its exact project-scoped SDK run key:
Use the same selector form with step-overview and logs. Do not pass both forms in one command. Use --range for another zero-based, end-exclusive page:
Subruns stay collapsed in their parent overview. Open one with --scope; the range applies to that subrun’s immediate steps, not to a flattened tree.
The first command returns 3.1 and 3.2; the second returns 3.2.1 and 3.2.2. Nesting can continue to any depth.

​
Inspect one step

Use the step_ref from the overview:
--preview keeps large fields readable. Use it before fetching full input or output.

​
Inspect selected keys

Use --input, --output, and --key-regex when you know the field you need:
For LLM steps, inspection uses the actual input sent to the model, including the supplementary user message containing lessons applied to that step. Use --key-regex to select only the fields you need instead of dumping full prompts, tool arguments, or response payloads.

​
Get a semantic summary

When the exact payload is less important than the behavior, ask Sovara for a step overview:

​
Read logs

Use logs for captured stdout and stderr:

​
Good inspection sequence

Use step refs such as 6.2, not internal IDs.