OpenThoughts TBLite

Harbor environment for the latest openthoughts/openthoughts-tblite Harbor dataset, wired through the v1 HarborTaskset and packaged v1 harnesses.

Each task uses the prebuilt Prime sandbox image:

team-clyvldofb0000gg1kx39rgzjq/openthoughts-tblite-<task>:latest

Run

uv pip install -e ./environments/openthoughts_tblite

Select harnesses in eval TOML through the v1 package id:

[eval.harness]
id = "verifiers.v1.packages.harnesses.opencode"
max_turns = 4

Argument	Default	Description
`taskset.dataset`	`openthoughts/openthoughts-tblite`	Harbor dataset ID.
`taskset.task_names`	`None`	Optional task-name allowlist.
`taskset.agent_timeout_seconds`	`900.0`	Fallback agent timeout when a task does not set `[agent].timeout_sec`.
`taskset.verifier_timeout_seconds`	`900.0`	Fallback verifier timeout when a task does not set `[verifier].timeout_sec`.
`taskset.timeout_multiplier`	`1.0`	Multiplies each task's sandbox lease, agent command timeout, and verifier timeout.