Skip to content

fix(tbench2_env): keep verifier assets out of the agent's reach #972

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
nblintao wants to merge 2 commits into
base: main
Choose a base branch
from
Open

fix(tbench2_env): keep verifier assets out of the agent's reach #972

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
501a20c
fix(tbench2_env): canonical test.sh evaluate, real timeouts, native t…
nblintao Jul 15, 2026
d2b7a24
fix(tbench2_env): keep verifier assets out of the agent's reach
nblintao Jul 16, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions envs/tbench2_env/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -164,6 +164,7 @@ env.step(Tbench2Action(action_type="view", session_id="sess1"))
| `TB2_OUTPUT_DIR` | `/tmp/tbench2_env_runs` | Directory for session logs and cache |
| `TB2_CACHE_DIR` | `$TB2_OUTPUT_DIR/repo_cache` | Where to extract TB2 repo |
| `TB2_REPO_URL` | (GitHub main.zip) | Repo zip URL for auto-download |
| `TB2_WITHHOLD_TESTS` | `0` | `1`: `reset()` deletes the task's `tests/` and `solution/` from disk (tests kept in server memory, staged at `/tests` only while scoring). Set for RL training so the agent cannot read the expected outputs or the answer; leave off when `TB2_TASKS_DIR` is a working checkout you don't want modified |

## Reward

Expand Down
Loading