jeevesagent.model.scripted

A test-only model that replays a fixed sequence of turns.

Each ScriptedTurn describes one model response: optional text followed by zero or more tool calls, terminated by a finish chunk. The model advances through the script with each call to stream(), which lets a single agent run() exercise multi-turn flows end-to-end.

Classes

ScriptedModel	Model that emits canned responses, one per call to stream().
ScriptedTurn

Module Contents

class jeevesagent.model.scripted.ScriptedModel(turns: list[ScriptedTurn])

Model that emits canned responses, one per call to stream().

async complete(messages: list[jeevesagent.core.types.Message], *, tools: list[jeevesagent.core.types.ToolDef] | None = None, temperature: float = 1.0, max_tokens: int | None = None) → tuple[str, list[jeevesagent.core.types.ToolCall], jeevesagent.core.types.Usage, str]

Single-shot replay of the next scripted turn.

Mirrors stream() but returns the turn’s text + tool_calls + usage in one tuple. Used by the non-streaming hot path (agent.run()); agent.stream() keeps using stream() for per-chunk replay.

async stream(messages: list[jeevesagent.core.types.Message], *, tools: list[jeevesagent.core.types.ToolDef] | None = None, temperature: float = 1.0, max_tokens: int | None = None) → collections.abc.AsyncIterator[jeevesagent.core.types.ModelChunk]

name: str = 'scripted'

property remaining: int

class jeevesagent.model.scripted.ScriptedTurn

text: str = ''

tool_calls: list[jeevesagent.core.types.ToolCall] = []

usage: jeevesagent.core.types.Usage