Skip to main content
Replays run an existing conversation through the current agent configuration so you can compare a previous answer with what Fini would do now. Use them after a prompt, knowledge, Rulebook, or model change to verify a known conversation before you roll the change into broader testing.
Replay runs create separate replay conversations. They do not overwrite the original conversation, publish a fix, or apply prompt, knowledge, or rule changes by themselves.

​
Endpoints

​
Replay modes

​
string
Replays the conversation up to the user event linked to the target response. This is the default mode when mode is omitted.
​
string
Replays only the selected response turn.

​
Model overrides

mlModels lets you override model selection for one replay run without changing the agent’s saved configuration.
​
string
Model name used for the planning step.
​
string
Model name used for knowledge search.
​
string
Model name used for answer generation.
​
string
Model name used for tag selection.
The API accepts only these four operation keys. If mlModels is present, it must contain at least one supported operation and every value must be a non-empty string.

Create replay

Start a replay for a known Fini response event.

List replays

See every replay created from one original conversation.

Get replay

Fetch the replay conversation record.

Get replay events

Fetch the message events created during the replay.