Upload folder using huggingface_hub

openenv_repl.egg-info/PKG-INFO

@@ -0,0 +1,16 @@
+Metadata-Version: 2.4
+Name: openenv-repl
+Version: 0.1.0
+Summary: Recursive Language Model REPL Environment for OpenEnv
+Requires-Python: >=3.10
+Requires-Dist: openenv-core[core]>=0.2.3
+Requires-Dist: fastapi>=0.115.0
+Requires-Dist: pydantic>=2.0.0
+Requires-Dist: uvicorn>=0.24.0
+Requires-Dist: requests>=2.31.0
+Requires-Dist: smolagents<2,>=1.22.0
+Requires-Dist: huggingface_hub>=0.20.0
+Requires-Dist: gradio>=4.0.0
+Provides-Extra: dev
+Requires-Dist: pytest>=9.0.3; extra == "dev"
+Requires-Dist: pytest-cov>=4.0.0; extra == "dev"

openenv_repl.egg-info/SOURCES.txt

@@ -0,0 +1,22 @@
+README.md
+pyproject.toml
+./__init__.py
+./client.py
+./local.py
+./models.py
+./prompts.py
+./recursive_backends.py
+./recursive_controller.py
+./rubrics.py
+./runner.py
+openenv_repl.egg-info/PKG-INFO
+openenv_repl.egg-info/SOURCES.txt
+openenv_repl.egg-info/dependency_links.txt
+openenv_repl.egg-info/entry_points.txt
+openenv_repl.egg-info/requires.txt
+openenv_repl.egg-info/top_level.txt
+server/__init__.py
+server/app.py
+server/gradio_ui.py
+server/python_executor.py
+server/repl_environment.py

openenv_repl.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

openenv_repl.egg-info/entry_points.txt

@@ -0,0 +1,2 @@
+[console_scripts]
+server = repl_env.server.app:main

openenv_repl.egg-info/requires.txt

@@ -0,0 +1,12 @@
+openenv-core[core]>=0.2.3
+fastapi>=0.115.0
+pydantic>=2.0.0
+uvicorn>=0.24.0
+requests>=2.31.0
+smolagents<2,>=1.22.0
+huggingface_hub>=0.20.0
+gradio>=4.0.0
+
+[dev]
+pytest>=9.0.3
+pytest-cov>=4.0.0

openenv_repl.egg-info/top_level.txt

@@ -0,0 +1 @@
+repl_env

server/gradio_ui.py

@@ -15,6 +15,58 @@ import gradio as gr
 from openenv.core.env_server.types import EnvironmentMetadata
 
 
+# One-shot example for the "Load example" button: a classic RLM
+# needle-in-a-haystack demo with parallel child LM calls over chunks.
+_EXAMPLE_CONTEXT = """ACME Robotics — Q1 internal changelog, build notes, and incident log.
+
+Week 1. Fleet rollout reached 412 units across warehouses A and B. Latency regression on the manipulator firmware was traced back to the new servo driver; hotfix 1.4.2 shipped Wednesday. No customer impact.
+
+Week 2. Vision team rotated the training dataset to include low-light scenes. Offline eval improved 3.1% on the occluded-grasping benchmark but regressed 0.8% on the clean-table benchmark. Product signed off on the trade-off.
+
+Week 3. Security audit flagged credential handling in the pairing flow. The legacy MQTT broker was retired. Any robot still on firmware < 1.3.0 will refuse to pair after May 1 — document this in the migration note. The activation code is BANANA-747. Do not share externally. Re-keying ceremony for the HSM happens next sprint.
+
+Week 4. Onboarding four new SREs. Runbook for the arm-joint recalibration was rewritten from scratch after the Tuesday incident. New runbook lives under ops/arm/joint-recal/v2.md. The Tuesday incident: a collision with a pallet rack during autonomous pickup. Root cause: stale depth-map cache. Mitigation: cache TTL dropped from 5 minutes to 20 seconds.
+
+Week 5. Starting the unification work on the control plane. Two clusters are being collapsed into one, with staged traffic shifting. Rollback criteria are defined in the RFC. Early signal looks good: no increase in p99 pick latency. Next milestone: full cutover.
+
+Week 6. Offsite in Porto. Platform team proposed a new interface between the planner and the low-level controller. Discussion deferred to the RFC process. Interesting prior art from the MIT paper on whole-body MPC. Follow-up reading list shared in the team channel."""
+
+_EXAMPLE_TASK_PROMPT = "Find the activation code hidden somewhere in the changelog."
+
+_EXAMPLE_CODE = """chunks = [context[i:i+600] for i in range(0, len(context), 600)]
+prompts = [f"Return only an activation code WORD-NNN if present, else NONE.\\n\\n{c}" for c in chunks]
+answers = llm_query_batched(prompts)
+hit = next((a.strip() for a in answers if "NONE" not in a.upper()), "not found")
+print(f"spawned {len(chunks)} children")
+print(FINAL(hit))"""
+
+
+_HELPERS_MD = """
+### REPL helpers
+
+These names are injected into the Python namespace once you Reset:
+
+- `context` — the string you passed in the *Context* field, available as a variable.
+- `task_prompt` — the string you passed in the *Task Prompt* field.
+- `llm_query(prompt, model=None)` — single direct call to the configured LLM.
+- `llm_query_batched(prompts, model=None)` — fan out N direct LLM calls in parallel.
+- `rlm_query(prompt)` / `rlm_query_batched(prompts)` — each child runs a full recursive REPL loop (deeper RLM pattern).
+- `FINAL(value)` — finalize the episode with `value` as the answer.
+- `FINAL_VAR("name")` — finalize with the value of the named variable.
+- `answer = {"content": ..., "ready": True}` — dict-based finalization.
+
+### Typical flow
+
+1. Open **Optional Model Settings**, paste an HF token, (optionally) set `LLM Model`.
+2. Write Context + Task Prompt.
+3. Click **Reset** — this loads your context and wires up the helpers above.
+4. Write Python in *Python Code* that uses those helpers and ends with `FINAL(...)`.
+5. Click **Run**. Inspect *Stdout* and *Raw JSON response* (the latter contains child-call metadata for recursive runs).
+
+Don't know where to start? Click **Load example** below to pre-fill a working needle-in-a-haystack demo.
+"""
+
+
 def _code_block(title: str, content: str) -> str:
     if not content:
         return ""
@@ -38,7 +90,8 @@ def _format_repl_response(data: Dict[str, Any]) -> str:
     available_variables = observation.get("available_variables") or []
     if available_variables:
         sections.append(
-            "**Available Variables:** " + ", ".join(f"`{name}`" for name in available_variables)
+            "**Available Variables:** "
+            + ", ".join(f"`{name}`" for name in available_variables)
         )
 
     if result.get("locals_snapshot"):
@@ -70,7 +123,12 @@ def build_repl_gradio_app(
     quick_start_md: str,
 ) -> gr.Blocks:
     """Build the REPL-specific Gradio tab."""
-    del action_fields, is_chat_env, metadata, quick_start_md
+    del action_fields, is_chat_env
+
+    env_description = metadata.description if metadata and metadata.description else ""
+    readme_content = (
+        metadata.readme_content if metadata and metadata.readme_content else ""
+    )
 
     async def reset_repl(
         context: str,
@@ -122,14 +180,30 @@ def build_repl_gradio_app(
         except Exception as exc:
             return f"Error: {exc}"
 
+    def load_example():
+        return _EXAMPLE_CONTEXT, _EXAMPLE_TASK_PROMPT, _EXAMPLE_CODE
+
     with gr.Blocks(title=f"{title} - REPL") as blocks:
         gr.Markdown(
             "# REPL Control Panel\n\n"
             "Load a problem into the REPL, execute Python, and inspect state without "
             "leaving the Space."
         )
+
+        with gr.Accordion("About this environment", open=True):
+            if env_description:
+                gr.Markdown(env_description)
+            if quick_start_md:
+                gr.Markdown(quick_start_md)
+            gr.Markdown(_HELPERS_MD)
+
+        if readme_content:
+            with gr.Accordion("Full README", open=False):
+                gr.Markdown(readme_content)
+
         with gr.Row():
             with gr.Column(scale=2):
+                example_btn = gr.Button("Load example", variant="secondary")
                 context = gr.Textbox(
                     label="Context",
                     placeholder="Problem context or source text...",
@@ -191,5 +265,9 @@ def build_repl_gradio_app(
             outputs=[session_view, raw_json, state_json, status],
         )
         state_btn.click(fn=get_state_sync, outputs=[state_json])
+        example_btn.click(
+            fn=load_example,
+            outputs=[context, task_prompt, code],
+        )
 
     return blocks

server/repl_environment.py

@@ -138,7 +138,6 @@ class REPLEnvironment(Environment):
         self._executor: Optional[PythonExecutor] = None
         self._runtime_controller = None
         self._runtime_controller_chat_fn: Optional[Callable[..., str]] = None
-        self._current_llm_model: Optional[str] = None
 
     @staticmethod
     def _build_hf_chat_fn(
@@ -258,16 +257,11 @@ class REPLEnvironment(Environment):
 
         # Create or rebuild LLM functions when needed.
         # Token resolution: explicit hf_token > HF_TOKEN env var > cached HF login.
-        # Rebuild when the caller supplies new credentials or switches models,
-        # so repeated resets with a different llm_model/hf_token take effect.
-        model_changed = llm_model != self._current_llm_model
-        token_provided = hf_token is not None
-        if not self.llm_query_fn or model_changed or token_provided:
+        if not self.llm_query_fn:
             effective_token = (
                 hf_token if hf_token is not None else os.environ.get("HF_TOKEN")
             )
             self._create_llm_functions(effective_token, llm_model)
-            self._current_llm_model = llm_model
         elif depth_changed and self._runtime_controller is not None:
             # Rebuild controller with new depth/iteration config but reuse
             # the existing chat_fn — don't require re-providing credentials.