Spaces:

NanduKondreddy
/

config-debug-env

Sleeping

App Files Files Community

config-debug-env

733 kB

Ctrl+K

Ctrl+K

2 contributors

History: 45 commits

Deepika

FIX: Parse request body directly in /step override

b618887 7 months ago

server
FIX: Parse request body directly in /step override 7 months ago
.dockerignore
56 Bytes
Phase 2: Benchmark Quality Upgrades - Progressive graders, realistic multi-bug tasks, ground_truth exposure 7 months ago
.gitattributes
0 Bytes
Phase 2: Benchmark Quality Upgrades - Progressive graders, realistic multi-bug tasks, ground_truth exposure 7 months ago
.gitignore
19 Bytes
Phase 2: Benchmark Quality Upgrades - Progressive graders, realistic multi-bug tasks, ground_truth exposure 7 months ago
Dockerfile
276 Bytes
Phase 2: Benchmark Quality Upgrades - Progressive graders, realistic multi-bug tasks, ground_truth exposure 7 months ago
PROGRESSION_VERIFICATION.md
2.22 kB
ADD: Local progression test and verification document 7 months ago
README.md
8.64 kB
Phase 2: Benchmark Quality Upgrades - Progressive graders, realistic multi-bug tasks, ground_truth exposure 7 months ago
SESSION_DIAGNOSIS.md
4.6 kB
ADD: Session state management issue diagnostic summary 7 months ago
__init__.py
187 Bytes
Phase 2: Benchmark Quality Upgrades - Progressive graders, realistic multi-bug tasks, ground_truth exposure 7 months ago
check_hf_rebuild.py
579 Bytes
ADD: HF rebuild status checker 7 months ago
client.py
1.03 kB
Phase 2: Benchmark Quality Upgrades - Progressive graders, realistic multi-bug tasks, ground_truth exposure 7 months ago
inference.py
8 kB
FIX: Remove incorrect action wrapper in HTTPEnvClient.step() - POST body must be direct ConfigDebugAction, not nested 7 months ago
openenv.yaml
1.61 kB
Phase 2: Benchmark Quality Upgrades - Progressive graders, realistic multi-bug tasks, ground_truth exposure 7 months ago
pyproject.toml
446 Bytes
Phase 2: Benchmark Quality Upgrades - Progressive graders, realistic multi-bug tasks, ground_truth exposure 7 months ago
requirements.txt
72 Bytes
Phase 2: Benchmark Quality Upgrades - Progressive graders, realistic multi-bug tasks, ground_truth exposure 7 months ago
test_env.py
540 Bytes
Phase 2: Benchmark Quality Upgrades - Progressive graders, realistic multi-bug tasks, ground_truth exposure 7 months ago
test_global_env_fallback.py
1.82 kB
FIX: Override /reset and /step to use global env when no session_id 7 months ago
test_grader_audit.py
3.14 kB
CRITICAL FIX: Graders now return FLOAT ONLY (not tuples) for validator contract compliance - extracted float from raw grader tuples 7 months ago
test_hf_space_edge_cases.py
8.82 kB
VALIDATED: All 4 edge cases pass against live HF Space - ready for validator resubmission 7 months ago
test_http_response_flow.py
6.32 kB
FIX: Handle null/None values gracefully in json_grader and yaml_grader - all edge cases now safe 7 months ago
test_k8s_multistep.py
1.77 kB
Phase 2: Benchmark Quality Upgrades - Progressive graders, realistic multi-bug tasks, ground_truth exposure 7 months ago
test_local_progression.py
1.41 kB
ADD: Local progression test and verification document 7 months ago
test_nginx_multistep.py
1.53 kB
Phase 2: Benchmark Quality Upgrades - Progressive graders, realistic multi-bug tasks, ground_truth exposure 7 months ago
test_reward_audit.py
8.99 kB
FIX: Handle null/None values gracefully in json_grader and yaml_grader - all edge cases now safe 7 months ago
test_session_persistence.py
1.64 kB
ADD: Local session persistence verification test 7 months ago
test_task_graders.py
2.95 kB
Fix: Enforce strict open interval (0.01, 0.99) for all grader rewards - validator compliance 7 months ago
test_validator_simulation.py
3.78 kB
Initial commit: config debug environment application 7 months ago
test_validator_stress.py
15.3 kB
FIX: Handle null/None values gracefully in json_grader and yaml_grader - all edge cases now safe 7 months ago
test_wrapped_grader_audit.py
9.51 kB
FIX: Handle null/None values gracefully in json_grader and yaml_grader - all edge cases now safe 7 months ago
uv.lock
538 kB
Phase 2: Benchmark Quality Upgrades - Progressive graders, realistic multi-bug tasks, ground_truth exposure 7 months ago
verify_graders.py
1.61 kB
Initial commit: config debug environment application 7 months ago