You can deploy this model and start earning money today!

Avnishjain/
support-triage-env

Name: support-triage-env
Availability: InStock

openenv

reinforcement-learning

customer-support

Views

No views yet

Support Triage OpenEnv

A real-world OpenEnv environment where an agent performs customer support triage: prioritization, routing, tagging, information gathering, and response drafting.

This project is designed for Round 1 style hackathon evaluation:

Full typed OpenEnv models
reset() / step() / state() API
3 deterministic graded tasks (easy/medium/hard)
Dense reward shaping with partial progress
Baseline inference.py using OpenAI client and required env vars
Docker + Hugging Face Spaces deployment files

Why This Environment Has Real Utility

Teams actually do this workflow in support operations and trust/safety queues. This environment evaluates whether an agent can:

classify urgency
route to the right team
attach relevant operational tags
ask for required evidence
draft safe and useful customer responses
close only when resolution criteria are met

Module-Aligned Build Guide (From Your Course)

Module 1: Why OpenEnv?

We treat the environment as a service with typed contracts.
Core loop follows RL structure: observe -> act -> reward.

Module 2: Using Existing Environments

support_triage_env/models.py defines typed Action, Observation, State.
support_triage_env/client.py gives a reusable typed client.

Module 3: Deploying Environments

server/app.py is the OpenEnv validator-compatible entrypoint (main() + callable script).
server/Dockerfile provides reproducible container runtime.
openenv.yaml defines deployment metadata.

Module 4: Building Your Own Environment

support_triage_env/server/environment.py implements task simulation.
support_triage_env/tasks.py defines deterministic fixtures.
support_triage_env/graders.py implements 0.0-1.0 grading.

Module 5: Training with OpenEnv + Reward Signals

Reward shaping is dense and trajectory-aware.
inference.py runs model-based episodes and exports reproducible baseline scores.

Action Space

Action model: SupportTriageAction

text

set_priority(value)
route_team(value)
add_tag(value)
draft_reply(value)
request_info(value)
close_ticket()
noop()

Valid priorities: low | medium | high | urgent

Valid teams: billing | technical | account | trust_safety | shipping

Observation Space

Observation model: SupportTriageObservation

Key fields:

task_id, difficulty, objective
title, customer_tier, customer_message
current working state: priority, routed_team, tags, draft_reply, info_requested
steps_remaining, last_feedback, allowed_actions
inherited reward, done

State Space

State model: SupportTriageState

Contains episode metadata and full workflow state:

episode_id, step_count
task_id, difficulty, objective, max_steps
priority, routed_team, tags
info_requested, closed, close_valid
history

Tasks and Graders

Easy: `easy_password_reset`

Scenario: login token failure after password reset
Expected routing: account
Expected priority: medium
Required tags: password-reset, login

Medium: `medium_double_charge`

Scenario: premium customer charged twice
Expected routing: billing
Expected priority: high
Required tags: refund, double-charge, vip
Needs additional evidence request

Hard: `hard_account_takeover`

Scenario: possible account takeover + fraud + abusive content
Expected routing: trust_safety
Expected priority: urgent
Required tags: security, account-takeover, fraud, content-abuse
Needs security-safe communication and evidence collection

Grading Design

support_triage_env/graders.py computes deterministic component scores:

priority correctness
routing correctness
required tags coverage
reply quality (required/forbidden phrase logic)
process quality (info request + closure quality + efficiency)

Final score is normalized to [0.0, 1.0].

Reward Function

The environment provides dense rewards at each step:

positive reward for correct priority/routing/tagging
incremental reward for improving draft response quality
positive signal for meaningful information requests when required
strong bonus for valid close
penalties for invalid actions, repeated loops, no-op behavior, or premature close
small per-step cost to discourage inefficient trajectories

Windows Setup

powershell

py -3.11 -m venv .venv
.\.venv\Scripts\Activate.ps1
python -m pip install -U pip
pip install -r requirements.txt

Optional: if openenv command is not found, use:

& "$env:APPDATA\Python\Python313\Scripts\openenv.exe" --help

Run Locally

Start API server

python -m uvicorn support_triage_env.server.app:app --host 0.0.0.0 --port 8000 --reload

Validate with OpenEnv tooling

powershell

openenv validate --verbose
openenv validate --url http://localhost:8000

Baseline Inference

inference.py is at project root as required.

Set env vars first:

powershell

$env:API_BASE_URL = "https://router.huggingface.co/v1"
$env:MODEL_NAME = "meta-llama/Llama-3.1-8B-Instruct"
$env:HF_TOKEN = "<your_hf_token>"

Run:

python .\inference.py

Output:

per-task scores
average score
baseline_scores.json

Docker

Build:

docker build -t support-triage-openenv:latest -f server/Dockerfile .

Run:

docker run --rm -p 8000:8000 support-triage-openenv:latest

Deploy to Hugging Face Spaces

openenv push --repo-id <your-username>/support-triage-openenv

Then set in Space settings:

API_BASE_URL
MODEL_NAME
HF_TOKEN

Suggested Baseline Reporting Format

Include in submission:

model name
per-task score table
average score
runtime in minutes
commit hash

Project Structure

text

support-triage-openenv/
|- server/
|  |- __init__.py
|  |- app.py
|  |- Dockerfile
|- support_triage_env/
|  |- __init__.py
|  |- models.py
|  |- client.py
|  |- tasks.py
|  |- graders.py
|  |- server/
|     |- __init__.py
|     |- app.py
|     |- environment.py
|     |- Dockerfile
|- inference.py
|- openenv.yaml
|- pyproject.toml
|- requirements.txt
|- uv.lock
|- README.md

Avnishjain/support-triage-env

Support Triage OpenEnv

Why This Environment Has Real Utility

Module-Aligned Build Guide (From Your Course)

Module 1: Why OpenEnv?

Module 2: Using Existing Environments

Module 3: Deploying Environments

Module 4: Building Your Own Environment

Module 5: Training with OpenEnv + Reward Signals

Action Space

Observation Space

State Space

Tasks and Graders

Easy: easy_password_reset

Medium: medium_double_charge

Hard: hard_account_takeover

Grading Design

Reward Function

Windows Setup

Run Locally

Start API server

Validate with OpenEnv tooling

Baseline Inference

Docker

Deploy to Hugging Face Spaces

Suggested Baseline Reporting Format

Project Structure

Avnishjain/
support-triage-env

Easy: `easy_password_reset`

Medium: `medium_double_charge`

Hard: `hard_account_takeover`