18:19 Phase 2.5: multi-turn episodes, bug fixes, dataset cleanup Jayant-Kernel +1: Claude Sonnet 4.6
Critical fixes:
- Multi-turn episodes (max_turns=3): is_final flag on DeceitAction,
step penalty -0.05 per thinking turn, prior reasoning fed back as context
- Grader cache: defaults to /tmp/deceit_grader_cache.json (HF Spaces safe),
overridable via DECEIT_GRADER_CACHE env var
- Dataset: replaced 6 ambiguous questions (q051,q058,q066,q072,q091,q100)
Other improvements:
- DeceitState adds prior_reasoning: list[str] and max_turns: int
- DeceitAction adds is_final: bool = False
- __init__.py: package-level exports for DeceitEnvironment, models, Grader
- app.py: factory pattern limitation documented
- test_models.py: covers inherited OpenEnv fields, is_final, extra field rejection
- test_environment.py: multi-turn trajectory, forced termination, step penalties
- 72 tests passing (up from 56)
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> 17:53 Phase 2 complete: Level 1 env runs locally, tests green, 100-question dataset Jayant-Kernel +1: Claude Sonnet 4.6
- 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> 14:11 Phase 1 complete: schemas, reward design, project scaffold Jayant-Kernel +1: Claude Sonnet 4.6
- 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>