Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
fix: persist initial context (distractors/pressure) across all episode turns
Jayant-Kernel+1: Claude Sonnet 4.6
Unverified signature
725414c
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
feat: extend environment with level=3, resistance reward ±0.2
Jayant-Kernel+1: Claude Sonnet 4.6
Unverified signature
27deeb6
Adds Level 3 adversarial pressure support: level3 dataset loading,
pressure_messages context injection, pressure_shown state tracking,
and a RESISTANCE_BONUS=0.2 reward component in the terminal step.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
feat: add pressure_shown field to DeceitState
Jayant-Kernel
Unverified signature
ed81b09
fix: remove dead import, skip sleep when api unavailable
Fix notebook: HF Space URL, /step envelope, health check retry on cold start
Jayant-Kernel+1: Claude Sonnet 4.6
Unverified signature
db475da
- ENV_BASE_URL now points to ajsaxena-deceit.hf.space by default (USE_LOCAL_DOCKER=False)
- /step calls now use {"action": {...}} envelope as required by OpenEnv
- /reset response unpacked from {"observation": {...}} wrapper
- Health check retries 12x with 10s sleep to handle HF cold start
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- models.py: upgraded to real OpenEnv base classes (Action/Observation/State)
- grader.py: exact-match + GPT-4o-mini semantic fallback with disk cache
- environment.py: DeceitEnvironment inheriting openenv.core.env_server.Environment
- reset/step/state implementing full episode loop
- compute_reward() pure function (correctness + calibration signals)
- app.py: create_fastapi_app wrapper exposing /reset /step /state
- level1.jsonl: 100 hand-curated QA pairs across 5 categories
- 56 tests passing: models, rewards, grader (mocked), environment (mocked)
- Smoke test: +1.3 correct+confident, -1.3 wrong+confident, 0.0 abstain
OpenEnv API note: step() returns Observation with reward embedded (not tuple).
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Fix build backend: use setuptools.build_meta instead of legacy path
Jayant-Kernel+1: Claude Sonnet 4.6
Unverified signature
db07765
setuptools.backends.legacy:build is not supported by the pip vendor
bundled with Python 3.14. Classic setuptools.build_meta works cleanly.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Pydantic v2 schemas for DeceitObservation, DeceitAction, DeceitState
- REWARD_DESIGN.md with correctness + calibration signals, worked examples, gaming analysis
- Full folder structure with Phase 2-6 stubs
- pytest tests for all three schemas (validation, defaults, JSON roundtrip)
- pyproject.toml with openenv-core[core]>=0.2.1 dependency pinned for Phase 2
- Design doc in docs/superpowers/specs/
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>