Upload folder using huggingface_hub

supportdesk_env/models.py

@@ -90,6 +90,7 @@ class SupportDeskObservation(Observation):
 class SupportDeskState(State):
     """Current environment state returned by the OpenEnv state() API."""
 
+    episode_id: str | None = None
     task_id: str
     difficulty: Literal["easy", "medium", "hard"]
     step_count: int = 0

supportdesk_env/server/app.py

@@ -3,16 +3,21 @@
 from __future__ import annotations
 
 import os
+import threading
 from typing import Any
 
 import uvicorn
+from fastapi import Body
+from fastapi.routing import APIRoute
 
 try:
     from openenv.core.env_server.http_server import create_app
+    from openenv.core.env_server.types import ResetRequest, ResetResponse, StepRequest, StepResponse
 except ImportError:  # pragma: no cover - package name differs across releases
     from openenv_core.env_server.http_server import create_app
+    from openenv_core.env_server.types import ResetRequest, ResetResponse, StepRequest, StepResponse
 
-from supportdesk_env.models import SupportDeskAction, SupportDeskObservation
+from supportdesk_env.models import SupportDeskAction, SupportDeskObservation, SupportDeskState
 from supportdesk_env.server.supportdesk_environment import SupportDeskEnvironment
 from supportdesk_env.tasks import TASKS
 
@@ -23,6 +28,82 @@ app = create_app(
     env_name="supportdesk_env",
 )
 
+_http_session_lock = threading.RLock()
+_http_session_env: SupportDeskEnvironment | None = None
+
+
+def _remove_stateless_http_routes() -> None:
+    """Replace OpenEnv's stateless HTTP simulation routes with a persistent session."""
+
+    kept_routes = []
+    for route in app.router.routes:
+        if isinstance(route, APIRoute):
+            methods = route.methods or set()
+            if route.path == "/reset" and "POST" in methods:
+                continue
+            if route.path == "/step" and "POST" in methods:
+                continue
+            if route.path == "/state" and "GET" in methods:
+                continue
+        kept_routes.append(route)
+    app.router.routes = kept_routes
+    app.openapi_schema = None
+
+
+def _get_http_session_env() -> SupportDeskEnvironment:
+    global _http_session_env
+    if _http_session_env is None:
+        _http_session_env = SupportDeskEnvironment()
+    return _http_session_env
+
+
+def _serialize_observation(observation: SupportDeskObservation) -> dict[str, Any]:
+    return observation.model_dump()
+
+
+_remove_stateless_http_routes()
+
+
+@app.post("/reset", response_model=ResetResponse, tags=["Environment Control"])
+def reset_environment(
+    request: ResetRequest = Body(default_factory=ResetRequest),
+) -> ResetResponse:
+    """Keep a persistent HTTP environment so reset/step/state share the same case."""
+
+    with _http_session_lock:
+        env = _get_http_session_env()
+        observation = env.reset(seed=request.seed, episode_id=request.episode_id)
+        reward = float(observation.reward) if observation.reward is not None else None
+        return ResetResponse(
+            observation=_serialize_observation(observation),
+            reward=reward,
+            done=observation.done,
+        )
+
+
+@app.post("/step", response_model=StepResponse, tags=["Environment Control"])
+def step_environment(request: StepRequest) -> StepResponse:
+    """Advance the current HTTP session instead of stepping a fresh env instance."""
+
+    with _http_session_lock:
+        env = _get_http_session_env()
+        action = SupportDeskAction.model_validate(request.action)
+        observation = env.step(action, timeout_s=request.timeout_s)
+        reward = float(observation.reward) if observation.reward is not None else None
+        return StepResponse(
+            observation=_serialize_observation(observation),
+            reward=reward,
+            done=observation.done,
+        )
+
+
+@app.get("/state", response_model=SupportDeskState, tags=["State Management"])
+def get_environment_state() -> SupportDeskState:
+    """Return the real current HTTP session state for grader-style inspection."""
+
+    with _http_session_lock:
+        return _get_http_session_env().state
+
 
 @app.get("/tasks")
 def list_tasks() -> dict[str, Any]:

supportdesk_env/server/supportdesk_environment.py

@@ -3,6 +3,7 @@
 from __future__ import annotations
 
 import os
+import uuid
 from pathlib import Path
 
 from supportdesk_env.graders import grade_case
@@ -41,6 +42,7 @@ class SupportDeskEnvironment(
         self._last_feedback = ""
         self._history: list[ActionHistoryEntry] = []
         self._case = SupportCaseProgress()
+        self._episode_id: str | None = None
         initial_grade = grade_case(self.task, self._case)
         self._score = initial_grade.total_score
         self._completed_milestones = list(initial_grade.completed_milestones)
@@ -48,6 +50,7 @@ class SupportDeskEnvironment(
     @property
     def state(self) -> SupportDeskState:
         return SupportDeskState(
+            episode_id=self._episode_id,
             task_id=self.task.task_id,
             difficulty=self.task.difficulty,
             step_count=self._step_count,
@@ -67,6 +70,7 @@ class SupportDeskEnvironment(
         episode_id: str | None = None,
         **kwargs,
     ) -> SupportDeskObservation:
+        self._episode_id = episode_id or f"{self.task.task_id}-{uuid.uuid4().hex[:8]}"
         self._step_count = 0
         self._reward_total = 0.0
         self._done = False

tests/test_supportdesk.py

@@ -1,5 +1,12 @@
 """Smoke tests for the SupportDesk environment."""
 
+import pytest
+
+try:
+    from fastapi.testclient import TestClient
+except RuntimeError:
+    TestClient = None  # type: ignore[assignment]
+
 from supportdesk_env.graders import grade_case
 from supportdesk_env.models import SupportDeskAction
 from supportdesk_env.server.supportdesk_environment import SupportDeskEnvironment
@@ -73,3 +80,46 @@ def test_grade_is_bounded_between_zero_and_one():
     env.reset()
     breakdown = grade_case(task, env.state.case)
     assert 0.0 <= breakdown.total_score <= 1.0
+
+
+def test_state_includes_episode_id_after_reset():
+    env = SupportDeskEnvironment(task_id="billing_refund_easy")
+    env.reset(episode_id="episode-123")
+    assert env.state.episode_id == "episode-123"
+
+
+@pytest.mark.skipif(TestClient is None, reason="httpx is not installed for FastAPI TestClient")
+def test_http_reset_step_state_are_session_consistent():
+    from supportdesk_env.server.app import app
+
+    client = TestClient(app)
+
+    reset_response = client.post("/reset", json={"episode_id": "http-episode"})
+    assert reset_response.status_code == 200
+
+    step_response = client.post(
+        "/step",
+        json={
+            "action": {
+                "operation": "classify",
+                "queue": "billing_ops",
+                "priority": "high",
+                "issue_type": "duplicate_charge",
+                "status": "new",
+                "requested_fields": [],
+                "reply": "",
+                "internal_note": "",
+            }
+        },
+    )
+    assert step_response.status_code == 200
+
+    state_response = client.get("/state")
+    assert state_response.status_code == 200
+    state_payload = state_response.json()
+
+    assert state_payload["episode_id"] == "http-episode"
+    assert state_payload["step_count"] == 1
+    assert state_payload["case"]["queue"] == "billing_ops"
+    assert state_payload["case"]["priority"] == "high"
+    assert state_payload["case"]["issue_type"] == "duplicate_charge"

uvicorn-test.err.log

@@ -0,0 +1,4 @@
+INFO:     Started server process [5720]
+INFO:     Waiting for application startup.
+INFO:     Application startup complete.
+INFO:     Uvicorn running on http://127.0.0.1:8001 (Press CTRL+C to quit)