feat: add E2B sandbox support (#35)

* feat: add E2B sandbox support

Add a new E2BREPL environment that runs Python code in E2B sandboxes,
following the same HTTP broker pattern as ModalREPL and PrimeREPL.

Changes:
- Add rlm/environments/e2b_repl.py with E2BREPL class
- Add examples/e2b_repl_example.py demonstrating usage
- Register "e2b" environment in environments/__init__.py
- Add "e2b" to EnvironmentType in core/types.py
- Add e2b optional dependency to pyproject.toml

Key implementation details:
- Uses e2b-code-interpreter SDK with Sandbox.create() API
- Runs Flask broker on port 8889 (8888 is used by E2B's Jupyter)
- Uses sandbox.get_host(port) for public URL access
- Supports llm_query(), llm_query_batched(), FINAL_VAR()

* update e2b example to use real LLM backend

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

* feat(e2b): add persistent parameter for SupportsPersistence protocol

Align E2BREPL with other environments (DockerREPL, ModalREPL, PrimeREPL)
by adding the persistent parameter introduced in PR #40. Raises
NotImplementedError when persistent=True since E2BREPL doesn't yet
implement the SupportsPersistence protocol.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

---------

Co-authored-by: az <alex.lx.zhang@gmail.com>
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>

Author: 3 people

examples/e2b_repl_example.py

@@ -0,0 +1,28 @@
+import os
+
+from dotenv import load_dotenv
+
+from rlm import RLM
+from rlm.logger import RLMLogger
+
+load_dotenv()
+
+logger = RLMLogger(log_dir="./logs")
+
+rlm = RLM(
+    backend="openai",
+    backend_kwargs={
+        "api_key": os.getenv("OPENAI_API_KEY"),
+        "model_name": "gpt-5-nano",
+    },
+    environment="e2b",
+    environment_kwargs={
+        "timeout": 300,
+    },
+    max_depth=1,
+    logger=logger,
+    verbose=True,
+)
+
+result = rlm.completion("Using your code, solve 2^(2^(2^(2))). Show your work in Python.")
+print(result.response)

pyproject.toml

@@ -36,6 +36,7 @@ Issues = "https://github.com/alexzhang13/rlm/issues"
 
 [project.optional-dependencies]
 modal = ["modal>=0.73.0", "dill>=0.3.7"]
+e2b = ["e2b-code-interpreter>=0.0.11", "dill>=0.3.7"]
 daytona = ["daytona>=0.128.1", "dill>=0.3.7"]
 prime = ["prime-sandboxes>=0.2.0", "dill>=0.3.7"]
 

rlm/core/types.py

@@ -13,7 +13,7 @@
     "azure_openai",
     "gemini",
 ]
-EnvironmentType = Literal["local", "docker", "modal", "prime", "daytona"]
+EnvironmentType = Literal["local", "docker", "modal", "prime", "daytona", "e2b"]
 
 
 def _serialize_value(value: Any) -> Any:

rlm/environments/__init__.py

@@ -7,12 +7,12 @@
 
 
 def get_environment(
-    environment: Literal["local", "modal", "docker", "daytona", "prime"],
+    environment: Literal["local", "modal", "docker", "daytona", "prime", "e2b"],
     environment_kwargs: dict[str, Any],
 ) -> BaseEnv:
     """
     Routes a specific environment and the args (as a dict) to the appropriate environment if supported.
-    Currently supported environments: ['local', 'modal', 'docker', 'daytona', 'prime']
+    Currently supported environments: ['local', 'modal', 'docker', 'daytona', 'prime', 'e2b']
     """
     if environment == "local":
         return LocalREPL(**environment_kwargs)
@@ -32,7 +32,11 @@ def get_environment(
         from rlm.environments.prime_repl import PrimeREPL
 
         return PrimeREPL(**environment_kwargs)
+    elif environment == "e2b":
+        from rlm.environments.e2b_repl import E2BREPL
+
+        return E2BREPL(**environment_kwargs)
     else:
         raise ValueError(
-            f"Unknown environment: {environment}. Supported: ['local', 'modal', 'docker', 'daytona', 'prime']"
+            f"Unknown environment: {environment}. Supported: ['local', 'modal', 'docker', 'daytona', 'prime', 'e2b']"
         )