rltakashige c2f2111b88 Fix tool calling (#1529) ...

## Motivation

GPT OSS tool calling issues.

## Changes

Fixes those and adds a bunch of evals for tool calling.
Fixes GLM5 prefix caching, where CacheList wasn't getting handled
properly.
Extracts a bunch of the setup functionality of exo bench to a harness
that can be reused elsewhere, such as in the tool calling eval.

## Test Plan
### Automated Testing
Let's run the evals for all models

2026-02-18 20:29:18 +00:00

..

auto_bench.sh

auto bench (#1405)

2026-02-06 15:35:46 +00:00

eval_tool_calls.sh

Fix tool calling (#1529)

2026-02-18 20:29:18 +00:00

get_all_models_on_cluster.py

auto bench (#1405)

2026-02-06 15:35:46 +00:00

headless_runner.py

Normalize TextGenerationTaskParams.input to list[InputMessage] (#1360)

2026-02-03 06:01:56 -08:00

run_exo_on.sh

cancel downloads for deleted instances (#1393)

2026-02-05 18:16:43 +00:00

start_distributed_test.py

improve distributed testing (#1300)

2026-02-02 18:25:39 +00:00