Fetching metadata from the HF Docker repository...
Apr 3 17:31 Merge pull request #25 from ArshVermaGit/main feat: complete implementation of CodeReview Environment, Models, and Scenarios 17:15 feat: implement core CodeReview evaluation, 30-scenario registry, and deterministic graders 12:15 Merge pull request #24 from ArshVermaGit/main feat: add complete Pydantic models and 30 synthetic code review scenarios Apr 2 15:14 Add action validation and reward recording Add validation and tighten action handling across the env and inference code.
- codereview_env/models.py: add a pydantic model_validator on Action to enforce required fields for FLAG_ISSUE (body, filename, line_number, category, severity) and require verdict/body for APPROVE/REQUEST_CHANGES actions.
- codereview_env/env.py: record ActionRecord before applying action (initialize reward=0.0), append it to history, compute reward delta and update running_score, then update the history record's reward (rounded to 4 decimals). Also guard history access when determining termination reason and set a default terminated_reason.
- codereview_env/scenarios.py: change required_verdict for arch_003, arch_005, and arch_008 from NEEDS_DISCUSSION to REQUEST_CHANGES.
- inference.py: normalize verdict strings to lowercase ("lgtm" and "request_changes").
These changes improve data validation, ensure accurate per-action reward recording in history, and standardize verdict values. 14:51 Update scenarios.py 14:48 feat(core): implement Pydantic v2 models and 30 synthetic scenarios - Overwrite codereview_env/models.py with standardized Pydantic v2 classes
- Create codereview_env/scenarios.py with 30 realistic code review cases
- Update env.py and app.py for model and scenario registry compatibility
- Reorder BUG_DETECTION scenarios to align with seed-based test expectations
- Remove legacy codereview_env/scenario_bank.py and deprecated StateResult Apr 1 21:30 chore: fix TestClient compatibility in requirements.txt 21:29 feat: OpenEnv spec compliance + blast radius enrichment (0→10) Merging full hardening pass — 20/20 tests, spec-compliant, blast radius enriched. 21:22 feat: OpenEnv spec compliance + blast radius enrichment (0→10) Critical fixes:
- Add inference.py at root with [START]/[STEP]/[END] stdout format
- Add /state/{episode_id} endpoint (required by OpenEnv spec)
- Fix openenv.yaml: tags:[openenv], base_url, api_version, difficulty labels
- Add get_state() method to CodeReviewEnv
Score improvements:
- Fix reward to return incremental delta per step (not cumulative sum)
- Add blast_radius, affected_users, service_criticality, service_name to Observation
- Enrich all 30 scenarios with service metadata + incident-inspired PR titles
- Add StateResult model for /state endpoint
Polish:
- Fix Dockerfile CMD to python app.py (was uvicorn directly)
- Add openai>=1.0.0 to requirements.txt
- Rewrite README with full observation/action space tables + reward docs
- Update .gitignore (.DS_Store, IDE folders)
- Expand test suite: 20/20 tests passing 20:59 Merge pull request #22 from ArshVermaGit/main fix: resolve critical startup bugs, port mismatch, and leaderboard crash 20:52 fix: resolve critical startup bugs, port mismatch, and leaderboard crash - Fix hardcoded port 8000 → 7860 in scripts/baseline.py
- Add proper argparse CLI with --url, --task, --seed flags
- Fix leaderboard rank calculation crashing after list slicing
- Fix WebSocket disconnect to catch WebSocketDisconnect and use discard()
- Fix incoherent grading weights in openenv.yaml
- Add .env.example with documented environment variables
- Add missing package init files for codereview_env and graders 05:54 Add Pylint workflow for Python code analysis Mar 27 06:52 Merge pull request #21 from DsThakurRawat/update-readme Update README.md 06:52 Update README.md with project structure and cleanup 06:51 Merge pull request #20 from DsThakurRawat/remove-roadmap-remote Untrack Roadmap.html 06:51 Untrack Roadmap.html and add to .gitignore 06:50 Merge pull request #19 from DsThakurRawat/add-grader-security Add codereview_env/graders/security_grader.py 06:50 Add codereview_env/graders/security_grader.py 06:50 Merge pull request #18 from DsThakurRawat/add-grader-utils Add codereview_env/graders/grader_utils.py 06:49 Add codereview_env/graders/grader_utils.py 06:49 Merge pull request #17 from DsThakurRawat/add-grader-bug Add codereview_env/graders/bug_grader.py 06:49 Add codereview_env/graders/bug_grader.py 06:49 Merge pull request #16 from DsThakurRawat/add-grader-arch Add codereview_env/graders/arch_grader.py 06:49 Add codereview_env/graders/arch_grader.py 06:49 Merge pull request #15 from DsThakurRawat/add-env-bank Add codereview_env/scenario_bank.py 06:49 Add codereview_env/scenario_bank.py 06:49 Merge pull request #14 from DsThakurRawat/add-env-models Add codereview_env/models.py 06:49 Add codereview_env/models.py 06:49 Merge pull request #13 from DsThakurRawat/add-env-py Add codereview_env/env.py 06:49 Add codereview_env/env.py 06:49 Merge pull request #12 from DsThakurRawat/add-env-init Add codereview_env/__init__.py 06:48 Add codereview_env/__init__.py 06:48 Merge pull request #11 from DsThakurRawat/add-test-graders Add tests/test_graders.py 06:48 Add tests/test_graders.py 06:48 Merge pull request #10 from DsThakurRawat/add-test-env Add tests/test_env.py 06:48 Add tests/test_env.py 06:48 Merge pull request #9 from DsThakurRawat/add-test-api Add tests/test_api.py 06:48 Add tests/test_api.py 06:48 Merge pull request #8 from DsThakurRawat/add-validate Add scripts/validate.py 06:48 Add scripts/validate.py 06:47 Merge pull request #7 from DsThakurRawat/add-baseline Add scripts/baseline.py 06:47 Add scripts/baseline.py 06:47 Merge pull request #6 from DsThakurRawat/add-requirements Add requirements.txt 06:47 Add requirements.txt 06:47 Merge pull request #5 from DsThakurRawat/add-openenv Add openenv.yaml 06:47 Add openenv.yaml 06:47 Merge pull request #4 from DsThakurRawat/add-app Add app.py 06:47 Add app.py 06:46 Merge pull request #3 from DsThakurRawat/add-roadmap Add Roadmap.html 06:46 Add Roadmap.html