Spaces:

anugrah55
/

opensleuth-env-gemini-cli

Paused

App Files Files Community

opensleuth-env-gemini-cli / opensleuth_env

110 kB

Ctrl+K

Ctrl+K

1 contributor

History: 7 commits

anugrah55's picture

OpenEnv 0.2.3 conformance: mount /openenv sub-app, add adapter + tests + example client

31715b5 verified 13 days ago

scripts
Level 2 open-ended env: auto-fuzzer + TaskCatalog + Hub-driven catalog + extended /reset 13 days ago
__init__.py

733 Bytes
Level 2 open-ended env: auto-fuzzer + TaskCatalog + Hub-driven catalog + extended /reset 13 days ago
auto_fuzzer.py

14 kB
Level 2 open-ended env: auto-fuzzer + TaskCatalog + Hub-driven catalog + extended /reset 13 days ago
black_box.py

10.7 kB
Level 2 open-ended env: auto-fuzzer + TaskCatalog + Hub-driven catalog + extended /reset 13 days ago
client.py

173 Bytes
Upload folder using huggingface_hub 13 days ago
env.py

14.3 kB
Level 2 open-ended env: auto-fuzzer + TaskCatalog + Hub-driven catalog + extended /reset 13 days ago
models.py

4.85 kB
Level 2 open-ended env: auto-fuzzer + TaskCatalog + Hub-driven catalog + extended /reset 13 days ago
openenv_adapter.py

10.9 kB
OpenEnv 0.2.3 conformance: mount /openenv sub-app, add adapter + tests + example client 13 days ago
task_catalog.py

17 kB
Level 2 open-ended env: auto-fuzzer + TaskCatalog + Hub-driven catalog + extended /reset 13 days ago
verifier.py

16.8 kB
verifier: fix SIGALRM-in-worker-thread bug that scored every well-formed submission 100/100 under uvicorn (fall back to no-timeout call when signal.signal raises). Trainer was training on a saturated reward landscape; this restores real per-submission scoring. 13 days ago