Upload 5 files

README.md

@@ -1,12 +1,157 @@
----
-title: Hackathon Repo 1
-emoji: 🏆
-colorFrom: blue
-colorTo: yellow
-sdk: gradio
-sdk_version: 6.10.0
-app_file: app.py
-pinned: false
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# Office Workflow OpenEnv Environment
+
+`office_workflow_env` simulates three realistic office tasks humans do and exposes them via OpenEnv’s standard `reset()` / `step()` / `state()` API.
+
+It supports deterministic grading (0.0–1.0) for:
+
+1. `email_triage` (easy)
+2. `data_cleaning` (medium)
+3. `support_escalation` (hard)
+
+At the end of each episode, the environment writes the final task score to `observation.info.final_score` and the structured breakdown to `observation.info.final_breakdown`.
+
+## Task / Episode API
+
+### Reset
+Call `reset(task_id=..., seed=..., episode_id=...)`.
+
+* `task_id`: one of `email_triage`, `data_cleaning`, `support_escalation`
+* `seed`: integer seed for deterministic shuffling
+
+### Step
+Call `step(action)` where `action` is an `OfficeAction`.
+
+The server returns:
+* `observation`: an `OfficeObservation`
+* `reward`: scalar float (shaped with partial progress)
+* `done`: boolean when the task is finished or `max_steps` is reached
+
+The `info` field is carried inside `observation.info`.
+
+### State
+Call `state()` to retrieve `OfficeState` (progress + action trace; no hidden ground truth answers).
+
+## Action Space (`OfficeAction`)
+
+Single action schema for all tasks, discriminated by `type`:
+
+* `type="triage_email"`
+  * `email_id`: string
+  * `category`: one of `billing`, `technical`, `spam`, `other`
+  * `priority`: int in `[0, 5]`
+
+* `type="correct_cell"`
+  * `row_id`: string
+  * `column`: one of `email`, `phone`, `date`
+  * `value`: proposed cleaned value
+
+* `type="support_decision"`
+  * `ticket_id`: string
+  * `intent`: one of `ask_for_information`, `resolve`, `escalate`
+  * `reply`: draft reply text
+  * plus intent-specific fields:
+    * `requested_info` (when `ask_for_information`)
+    * `resolution_steps` (when `resolve`)
+    * `escalation_reason` (when `escalate`)
+
+Optional helper actions:
+* `type="request_status"`
+* `type="noop"`
+
+## Observation Space (`OfficeObservation`)
+
+Common fields:
+* `task_id`, `status`, `max_steps`, `step_index`
+
+Task-specific fields:
+* `email_triage`: `emails`, `triaged`
+* `data_cleaning`: `dataset`, `cleaned_cells`
+* `support_escalation`: `tickets`, `handled_tickets`
+
+Grader-facing info:
+* `info.objective`, `info.completion_rule` (task instructions)
+* `info.reward_breakdown` (per-step reward component breakdown)
+* final episode results in `info.final_score` and `info.final_breakdown`
+
+## Reward Shaping (partial progress)
+
+Rewards are not binary: they increase as the agent makes correct partial progress.
+
+All tasks:
+* progress component grows with corrected/handled items
+* correctness component rewards correct submissions
+* stalling/wrong actions are penalized by driving reward toward `0.0`
+
+## Local Setup
+
+### Step-by-step (Windows / PowerShell)
+
+1. Open a terminal in `c:\Users\hp\Desktop\hackathon`
+2. Install dependencies:
+
+```bash
+python -m pip install -U pip
+python -m pip install "openenv-core[core]>=0.2.1" openai requests uvicorn
+```
+
+3. Validate OpenEnv structure:
+
+```bash
+openenv validate
+```
+
+4. Start the server:
+
+```bash
+uvicorn server.app:app --host 0.0.0.0 --port 8000
+```
+
+5. Confirm it responds:
+   - `http://localhost:8000/health`
+   - `http://localhost:8000/docs`
+
+6. Run the connectivity smoke test (expected score 0.0 because it sends only `noop`):
+
+```bash
+python scripts/smoke_test.py
+```
+
+7. Run a “real” local demo baseline (no OpenAI key required; rule-based):
+
+```bash
+python scripts/baseline_inference.py
+```
+
+## Baseline Inference (OpenAI)
+
+The baseline script runs a model against all 3 tasks and prints reproducible scores.
+
+Environment variables:
+* `OPENAI_API_KEY`
+* `OPENAI_MODEL` (optional, default `gpt-4o-mini`)
+* `OPENENV_BASE_URL` (optional, default `http://localhost:8000`)
+* `BASELINE_SEED` (optional, default `123`)
+
+Run:
+```bash
+python scripts/baseline_inference.py
+```
+
+## Hugging Face Spaces Deployment
+
+This repo includes a `server/Dockerfile` suitable for Hugging Face Spaces.
+
+When you’re ready to deploy:
+```bash
+openenv validate
+openenv push --repo-id YOUR_HF_USERNAME/office-workflow-env
+```
+
+`openenv push` will package the environment and build the Docker image for Spaces.
+
+After it deploys, validate the running Space:
+
+```bash
+openenv validate https://YOUR_HF_USERNAME-office-workflow-env.hf.space
+```
+

client.py

@@ -0,0 +1,29 @@
+from __future__ import annotations
+
+from typing import Any, Dict
+
+from openenv.core.client_types import StepResult
+from openenv.core.env_client import EnvClient
+
+from server.models import OfficeAction, OfficeObservation, OfficeState
+
+
+class OfficeEnvClient(EnvClient[OfficeAction, OfficeObservation, OfficeState]):
+    def _step_payload(self, action: OfficeAction) -> Dict[str, Any]:
+        # The env server deserializes via Pydantic, so we send only provided fields.
+        return action.model_dump(exclude_none=True)
+
+    def _parse_result(self, payload: Dict[str, Any]) -> StepResult[OfficeObservation]:
+        obs_data = payload.get("observation", {}) or {}
+        reward = payload.get("reward", None)
+        done = bool(payload.get("done", False))
+        observation = OfficeObservation(
+            **obs_data,
+            done=done,
+            reward=reward,
+        )
+        return StepResult(observation=observation, reward=reward, done=done)
+
+    def _parse_state(self, payload: Dict[str, Any]) -> OfficeState:
+        return OfficeState.model_validate(payload)
+

openenv.yaml

@@ -0,0 +1,6 @@
+spec_version: 1
+name: office_workflow_env
+type: space
+runtime: fastapi
+app: server.app:app
+port: 8000

pyproject.toml

@@ -0,0 +1,24 @@
+[build-system]
+requires = ["setuptools>=45", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "openenv-office-workflow-env"
+version = "0.1.0"
+description = "Real-world office workflow environment with graded tasks"
+requires-python = ">=3.11"
+dependencies = [
+    "openenv-core[core]>=0.2.1",
+    "openai>=2.7.2",
+    "requests>=2.31.0",
+]
+
+[project.scripts]
+# Entry point required by `openenv validate`
+server = "server.app:main"
+
+[tool.setuptools]
+include-package-data = true
+packages = ["server"]
+package-dir = { "server" = "server" }
+

uv.lock

@@ -0,0 +1,3 @@
+# Placeholder lockfile for OpenEnv validation.
+# If you run `uv lock` / `openenv build`, this will be replaced with a real lock.
+