Skip to main content
Use sovara rerun when you want to test a small change to one recorded LLM call without rerunning the entire agent. Typical uses:
  • Change a prompt fragment
  • Change an existing model parameter such as max tokens
  • Replace a user message from a file
  • Compare whether one step would have produced a better answer

​
Requirements

Before rerunning a step:
  1. Record or locate a run.
  2. Inspect the run and find the step ref.
  3. Confirm the step is an LLM call.
  4. Inspect the exact input keys you want to edit.
  5. Configure a replay API key for the provider used by that step.
For a step recorded through Palantir Foundry, store the Foundry token under the palantir provider:
See Replay keys for provider key management.

​
Basic rerun

This reruns current lesson retrieval, replays the resulting LLM input, and returns the new output plus the retrieval snapshot. To compare the step without retrieving or injecting new lessons:
The flag removes the selected step’s recorded lesson injection and skips fresh retrieval for that step.

​
Edit string values

Use --set KEY=VALUE for a string edit:
Keys must use the flattened names shown by probe; unknown keys are rejected:

​
Edit JSON values

Use --set-json for numbers, booleans, arrays, objects, or null:
For arrays or objects, quote the JSON for your shell:

​
Read an edit from a file

Use --set-file KEY=PATH for larger prompt text:

​
Combine edits

​
Output

Successful reruns return JSON with:
  • status
  • run_id
  • step_ref
  • overwritten_output
  • lesson_retrieval
The Sovara app will show the rerun output for the selected step.

​
Limits

sovara rerun is for one recorded LLM step. It does not rerun tool calls, custom traced functions, or the full agent. If a provider key is missing, set it with sovara replay-keys set. If the provider is not replayable with an API key, inspect the step and rerun the full agent instead.