Commit History

Phase 9: HuggingFace Space deployment with WebSocket passthrough verification
bb40e1c

Arun-Sanjay commited on

Phase 8: Docker local deployment with health checks, single + concurrent smoke tests per PROJECT.md Section 24.1
711aa6b

Arun-Sanjay commited on

Doc cleanup: Environment is Generic[ActT, ObsT, StateT], not single-param β€” match real openenv-core API surface
0aea479

Arun-Sanjay commited on

Phase 7: OpenEnv server (ShutdownGymEnvironment, create_app wiring, EnvClient), custom-action mode, turn-budget timer per PROJECT.md Sections 4, 8, 10, 11, 13
453233a

Arun-Sanjay commited on

Migrate models.py to inherit from openenv.core.env_server.interfaces base classes (Action, Observation, State)
d813a27

Arun-Sanjay commited on

Fix OpenEnv package: swap squatter openenv for openenv-core>=0.2.1, update PROJECT.md API sections and rubrics imports to match real Meta-PyTorch framework
1f6d405

Arun-Sanjay commited on

Pre-Phase-7 cleanup: migrate models.py to turn-budget fields, add episode_seed helper for deterministic-per-UUID sampling
a72e3bd

Arun-Sanjay commited on

PROJECT.md amendments: turn-budget timer (replaces wall-clock), Section 14.8 reward-hacking defenses, Section 2.5 critical risks for Claude Code awareness
2d70bd9

Arun-Sanjay commited on

Phase 6: Problems pool (500 GSM8K-style problems) and sampling API per PROJECT.md Section 12
0738d13

Arun-Sanjay commited on

Models fix: add state field to ShutdownObservation for rubric access per PROJECT.md Section 14
313cc30

Arun-Sanjay commited on

Phase 5: Audit classifier and rubric stack per PROJECT.md Sections 9 and 14
99f1f74

Arun-Sanjay commited on

Phase 4 cleanup: allow ast.IfExp (ternary expressions) in restricted Python, update tests
39dd2ab

Arun-Sanjay commited on

Phase 4: run_python AST-whitelisted executor with iteration cap via sys.settrace, wired into TOOLS per PROJECT.md Section 7
ff38834

Arun-Sanjay commited on

Phase 3: SimulatedFilesystem with dict-backed storage, hash semantics, readonly enforcement per PROJECT.md Section 6
e88ef62

Arun-Sanjay commited on

Fix subagent registration: add Task tool to agent frontmatter, document venv dependency install in CLAUDE.md
613e322

Arun-Sanjay commited on

Phase 2: Pydantic v2 models (ShutdownAction, ShutdownObservation, ShutdownState) per PROJECT.md Section 11
1cc5dd4

Arun-Sanjay commited on

Rename project: Shutdown-Gym β†’ Red Button (Shutdown-Gym remains as subtitle)
76a8376

Arun-Sanjay commited on

Phase 1 cleanup: update settings.json to current schema, document venv activation in CLAUDE.md
79189a7

Arun-Sanjay commited on

Phase 1: Initial scaffold, Claude Code workspace, repo structure per PROJECT.md Section 5
f707fd4

Arun-Sanjay commited on