feat: append Phase 5 Level 3 training section to sanity_run.ipynb
Jayant-Kernel+1: Claude Sonnet 4.6
Unverified signature
c893cdf
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
feat: append Phase 4 Level 2 training section to sanity_run.ipynb
Jayant-Kernel+1: Claude Sonnet 4.6
Unverified signature
f8a8477
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
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>
- 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>