What the model reads in a task

​

Quickstart

from unmute_core.tasks import REFUSED_BUSY, Refused, ToolDeclaration, ToolStatus

Refused(refused="Run take_order first.").model_dump()  # {"refused": "Run take_order first."}
ToolStatus(status="completed").model_dump()  # {"status": "completed"}

​

Why use unmute for this

​

What the model reads when a task runs

​

What a step hears of the call

• include_tool_calls: false leaves tool calls and results out of full and last_n.
• last_n needs max_messages, from 1 to 200, and any other history refuses it.
• A summary step asks for its summary as it opens. A summary that fails gives the step messages.
• In an isolated group, every step starts fresh, whatever its history.

TaskSpec(name="confirm_order", instructions="...", history="last_n", max_messages=6)

​

Placeholder names

1. A placeholder name becomes a template-variable key. a.b is a__b.
2. When the model call names a limit, a key over it is refused, with a message that names the placeholder.
3. The check covers a task’s instructions, and the agent’s main prompt when the adapter builds the agent.
4. A model call with no variable_key_max, like a framework’s own LLM plugin, checks nothing.

​

Troubleshooting

​

A placeholder name is refused when the agent is built

​

Where to go next