| spec_version: 1 |
| name: helpdesk_env |
| version: "0.1.0" |
| description: > |
| An OpenEnv RL environment simulating UPI banking customer support workflows. |
| An AI agent classifies issues, retrieves the correct FAQ or escalation path, |
| and completes a safe multi-turn support flow across three graded tasks of |
| increasing difficulty. |
| author: Freakdivi |
| tags: |
| - openenv |
| - banking |
| - upi |
| - customer-support |
| - rl-environment |
|
|
| type: space |
| runtime: fastapi |
| app: server.app:app |
| port: 8000 |
| default_task: medium |
|
|
| tasks: |
| - id: easy |
| difficulty: easy |
| description: Classify the customer's issue into the correct support category |
| dataset: data/tickets/easy.json |
| max_steps: 1 |
| reward_range: [0.0, 1.0] |
| grader: |
| type: python |
| reward_source: server.helpdesk_environment:HelpdeskEnv.step |
| score_field: reward.value |
| functions: |
| - graders.category_grader:grade_classification |
| - graders.resolution_grader:grade_resolution |
| - graders.score_utils:ensure_open_unit_interval |
|
|
| - id: medium |
| difficulty: medium |
| description: Select the correct FAQ or escalate cases that require manual handling |
| dataset: data/tickets/medium.json |
| max_steps: 3 |
| reward_range: [0.0, 1.0] |
| grader: |
| type: python |
| reward_source: server.helpdesk_environment:HelpdeskEnv.step |
| score_field: reward.value |
| functions: |
| - graders.faq_grader:grade_faq_retrieval |
| - graders.faq_grader:grade_escalation |
| - graders.faq_grader:grade_operation_choice |
| - graders.score_utils:ensure_open_unit_interval |
|
|
| - id: hard |
| difficulty: hard |
| description: Run a multi-turn support conversation with clarification, guidance, and safe closure |
| dataset: data/tickets/hard.json |
| max_steps: 8 |
| reward_range: [0.0, 1.0] |
| grader: |
| type: python |
| reward_source: server.helpdesk_environment:HelpdeskEnv.step |
| score_field: reward.value |
| functions: |
| - graders.category_grader:grade_information_collection |
| - graders.faq_grader:grade_faq_retrieval |
| - graders.resolution_grader:grade_case_closure |
| - graders.resolution_grader:grade_resolution |
| - graders.score_utils:ensure_open_unit_interval |
|
|
| observation_space: |
| type: object |
| fields: |
| case_id: string |
| track: string |
| customer_message: string |
| conversation_history: array |
| known_facts: object |
| required_slots: array |
| available_actions: array |
| turn_number: integer |
|
|
| action_space: |
| type: object |
| fields: |
| action_type: "classify | lookup_faq | ask_clarification | reply | escalate | resolve_ticket" |
| category: string (optional) |
| faq_id: string (optional) |
| message: string (optional) |
| fields_requested: array (optional) |
| target: string (optional) |
| operation: string (optional) |
|
|
| reward: |
| type: float |
| range: [0.0, 1.0] |
| description: > |
| Partial reward is produced at each step and normalized by the environment. |
| The final reward combines correctness, safety, resolution, efficiency, and |
| penalties, with score outputs constrained to the open interval (0, 1) for |
| submission compatibility. |
| |
| endpoints: |
| reset: POST /reset |
| step: POST /step |
| state: GET /state |
| health: GET /health |
|
|
| runtime_config: |
| framework: fastapi |
| python: "3.10" |
| port: 8000 |
|
|
