Internal models

fast-agent comes with two internal models to aid development and testing: passthrough and playback.

Passthrough

By default, the passthrough model echos messages sent to it.

Fixed Responses

By sending a ***FIXED_RESPONSE <message> message, the model will return <message> to any request.

Tool Calling

By sending a ***CALL_TOOL <tool_name> [<json>] message, the model will call the specified MCP Tool, and return a string containing the results.

Playback

The playback model replays the first conversation sent to it. A typical usage may look like this:

---USER
Good morning!
---ASSISTANT
Hello
---USER
Generate some JSON
---ASSISTANT
{
   "city": "London",
   "temperature": 72
}

This can then be used with the prompt-server; you can apply the MCP Prompt to the agent either programmatically with apply_prompt or with the /prompts command in the interactive shell.

Alternatively, you can load the file with load_prompt.

JSON contents can be converted to structured outputs:

from pathlib import Path

from fast_agent import Prompt, PromptMessageExtended, load_prompt
from pydantic import BaseModel


class Weather(BaseModel):
    city: str
    temperature: int


@fast.agent(name="playback", model="playback")

...

playback_messages: list[PromptMessageExtended] = load_prompt(Path("playback.txt"))
# Set up the Conversation
loaded = await agent.playback.generate(playback_messages)
assert loaded.first_text().startswith("HISTORY LOADED")

response: str = await agent.playback.send("Good morning!") # Returns Hello
temperature, _ = await agent.playback.structured([Prompt.user("Generate some JSON")], Weather)

When the playback runs out of messages, it returns MESSAGES EXHAUSTED (list size [a]) ([b] overage).

List size is the total number of messages originally loaded, overage is the number of requests made after exhaustion.