Skip to main content

ScriptedReply

Defined in the scripted module.
AI Agent One assistant turn the double should return. Attributes: text: Assistant message content, or None for a pure tool-call turn. tool_calls: Tool calls to emit alongside/instead of text. finish_reason: Overrides the finish reason (“tool_calls” when the turn has tool calls, otherwise “stop”). usage: Optional {"prompt_tokens": .., "completion_tokens": ..} to report, for tests that assert on token accounting.

Properties

Optional[str]
No description available.
Tuple[ScriptedToolCall, ...]
No description available.
Optional[str]
No description available.
Optional
No description available.

Methods

resolved_finish_reason()

The finish reason to report for this turn.

Source

View on GitHub

praisonaiagents/model_harness/scripted.py at line 113