Skip to main content

Module task

Module task 

Source
Expand description

Agentic tool-calling task schema for tune runs.

A TuneTask is a single scripted scenario: a prompt, a set of tools advertised to the model, and an expected outcome. Tasks are evaluated through the real agent loop (not a toy harness) so the recorded tool calls reflect exactly what the model would do in production.

§Categories

Modeled after the Berkeley Function Calling Leaderboard (BFCL) methodology: single-call and parallel-call correctness, multi-turn (stateful) tool use, and — importantly for avoiding loops — irrelevance detection (can the model correctly abstain from calling a tool when none applies). A fifth category, TaskCategory::LongContext, goes beyond BFCL: it pre-fills the conversation with a long simulated history before user_prompt, testing whether context degradation over a long session (attention fixating on stale context) causes the model to loop or stagnate on a task it would otherwise handle cleanly from a cold start.

Structs§

ExpectedCall
One expected tool call within a task’s ExpectedOutcome::ToolCalls.
TuneTask
A single scripted agentic scenario evaluated during a tune run.

Enums§

ExpectedOutcome
What a task expects the agent loop to do.
TaskCategory
Category of an agentic tool-calling scenario, following the BFCL split (plus LongContext, which is gglib-specific).
TaskSuite
The set of tasks a tune run evaluates each candidate against.