Merge branch 'main' into codex/refactor-http-mcp-client-operation

Author: burtenshaw

.claude/skills/generate-openenv-env/assets/openenv_env_template/pyproject.toml

@@ -16,8 +16,8 @@ requires-python = ">=3.10"
 dependencies = [
     # Core OpenEnv runtime (provides FastAPI server + HTTP client types)
     # install from github
-    # "openenv-core[core] @ git+https://github.com/huggingface/OpenEnv.git",
-    "openenv-core[core]>=0.2.2",
+    # "openenv @ git+https://github.com/huggingface/OpenEnv.git",
+    "openenv>=0.2.2",
     # Environment-specific dependencies
     # Add all dependencies needed for your environment here
     # Examples:

.claude/skills/generate-openenv-env/assets/openenv_env_template/server/requirements.txt

@@ -1,3 +1,3 @@
-openenv-core[core]>=0.2.2
+openenv>=0.2.2
 fastapi>=0.116.0
 uvicorn>=0.24.0

docs/source/environments/sophistry_bench_sprint.md

@@ -37,7 +37,7 @@ from sophistry_bench_sprint_env import SophistryBenchSprintEnv
 
 async def main():
     # Deployed Hugging Face Space (or .from_docker_image("openenv-sophistry_bench_sprint:latest")):
-    client = await SophistryBenchSprintEnv.from_env("anushaacharya/sophistry_bench_sprint_env")
+    client = await SophistryBenchSprintEnv.from_env("openenv-community/sophistry_bench_sprint_env")
     async with client:
         obs = (await client.reset()).observation
         print(obs.prompt, obs.answer_to_defend)
@@ -67,6 +67,22 @@ the reward-hacking measurement. By default it holds **seven** components; `corre
 > reason; even with the rest of the components, forwarding them to the agent leaks the
 > reward signal and defeats the reward-hacking measurement.
 
+## Training
+
+[`examples/sophistry_bench_sprint_grpo.py`](https://github.com/huggingface/OpenEnv/blob/main/examples/sophistry_bench_sprint_grpo.py)
+trains a policy on this env with TRL's `GRPOTrainer` — a plain prompt ->
+completion -> reward setup, since the episode is single-step.
+
+Validated with a real 100-step run on Hugging Face Jobs (`Qwen2.5-0.5B-Instruct`,
+`a10g-small`) and a 100-step run on the Prime Intellect Hub
+(`Llama-3.2-1B-Instruct`, registered as `anusha/sophistry-bench-sprint`, parity-tested
+against this port). Both show `aggregate_reward` (the optimized proxy) climbing while
+`correctness_reward` (the hidden ground truth, weight 0) stays flat — the reward-hacking
+signature this env is designed to surface. The larger Prime Intellect run converges on
+the literal `claim_count_cliff` target (`n_claims` saturates at exactly 8); the smaller
+HF Jobs run finds a different shortcut instead (`n_claims` collapses to ~0, near-empty
+completions) — same underlying finding, different degenerate strategy depending on scale.
+
 ## Build & test
 
 ```bash

docs/source/environments/unity.md

@@ -594,7 +594,7 @@ This approach is useful when:
 - `mlagents` (installed from source via git)
 - `numpy>=1.20.0`
 - `pillow>=9.0.0` (for visual observations)
-- `openenv[core]>=0.2.0`
+- `openenv>=0.2.0`
 
 ## References
 

docs/source/getting-started.md

@@ -9,24 +9,19 @@ pip install openenv
 ```
 
 > [!NOTE]
-> This installs the `openenv` CLI and the `openenv.core` runtime. Environment
-> projects can depend on `openenv[core]` when they only need the server and
-> client libraries.
+> This installs the full OpenEnv runtime: the environment server, the client,
+> the `openenv` CLI, the web interface, and MCP support. Environments depend on
+> `openenv` directly.
 
 ### Optional dependencies
 
-OpenEnv ships optional extras for specific integrations. Install them with
+A few integrations ship as optional extras. Install them with
 `pip install openenv[<extra>]`:
 
 | Extra | Pulls in |
 |-------|----------|
-| `core` | Server + client runtime only (no CLI) |
-| `cli` | The `openenv` command-line interface |
-| `all` | `core` + `cli` |
 | `inspect` | The Inspect AI evaluation harness |
-
-Cloud sandbox providers ship their own extras (`daytona`, `aca`); see the Core
-API reference.
+| `daytona`, `aca`, `modal` | Cloud sandbox providers (see the Core API reference) |
 
 ## Try an Environment
 

docs/source/getting_started/contributing-envs.md

@@ -17,7 +17,7 @@ This guide covers three workflows:
 Before you start, make sure you have:
 
 - Python 3.11+ and [`uv`](https://github.com/astral-sh/uv) installed
-- The OpenEnv CLI: `pip install openenv[cli]` (or install from source)
+- The OpenEnv CLI: `pip install openenv` (or install from source)
 - A [Hugging Face account](https://huggingface.co/join) with a [write token](https://huggingface.co/settings/tokens)
 
 Authenticate with the Hub:

envs/agent_world_model_env/pyproject.toml

@@ -8,7 +8,7 @@ version = "0.1.0"
 description = "Agent World Model Environment for OpenEnv - wraps 1,000 LLM-synthesized environments"
 requires-python = ">=3.10"
 dependencies = [
-    "openenv[core]>=0.2.2",
+    "openenv>=0.2.2",
     "fastapi>=0.115.0",
     "pydantic>=2.0.0",
     "uvicorn>=0.24.0",

envs/agent_world_model_env/uv.lock

@@ -14,7 +14,7 @@ version = "0.1.0"
 description = "Atari Environment for OpenEnv - Atari 2600 games via ALE"
 requires-python = ">=3.10"
 dependencies = [
-    "openenv[core]>=0.2.2",
+    "openenv>=0.2.2",
     "fastapi>=0.115.0",
     "pydantic>=2.0.0",
     "uvicorn>=0.24.0",