> ## Documentation Index > Fetch the complete documentation index at: https://docs.errorbar.ai/llms.txt > Use this file to discover all available pages before exploring further. # Export the environment bundle > The grader, packaged: reward spec, each judge's calibration certificate, deterministic assertions, declared env tools (names only — never endpoint URLs or auth), the session's stored tasks, the anchor and its hold state, and adapter snippets for TRL and verifiers. Signed with the same key as eval evidence bundles; verify with `POST /v1/verify`. `format=tasks` returns just `tasks.jsonl` — one task per line in the shape `rl/omnia_grpo/tasks.py` and OpenEnv-style loaders read. ## OpenAPI ````yaml /openapi.json get /v1/reward/sessions/{id}/environment openapi: 3.1.0 info: title: errorbar Management API description: >- The management API behind the improvement loop: capture and setup, request logs and datasets, grades (labels), judges (criteria), evals and deploy gates, fine-tuning and reinforcement learning, dedicated GPU endpoints, and model aliases and versions. Authenticated with a workspace API key (sk_sovereign_...). The inference API (chat, embeddings, rerank, responses) is OpenAI-compatible and documented separately. Responses are snake_case, list endpoints on the loop products use the {"object": "list", "data": [...]} envelope, and refusals use the same nested error shape the gateway emits: {"error": {"message", "type", "code"}}. Request bodies on the loop products (logs, labels, criteria, evals, datasets, aliases) are snake_case; the training and infrastructure products (fine-tuning, GRPO, environment tools, dedicated, model-version adoption) validate camelCase bodies, and each schema below says which it is. Endpoints that spend money require a key minted by a workspace owner or admin and return 403 otherwise. version: 1.0.0 servers: - url: https://gateway.errorbar.ai description: Production - url: https://www.errorbar.ai/api description: Control plane (also served at this base URL) security: - bearerAuth: [] tags: - name: Certified reward description: >- The certified reward for your own trainer: sessions with judge certificates, scoring with a ledger-true kill switch, and the mid-run anchor that holds a run when the reward diverges from an independent judge. paths: /v1/reward/sessions/{id}/environment: parameters: - name: id in: path required: true schema: type: string get: tags: - Certified reward summary: Export the environment bundle description: >- The grader, packaged: reward spec, each judge's calibration certificate, deterministic assertions, declared env tools (names only — never endpoint URLs or auth), the session's stored tasks, the anchor and its hold state, and adapter snippets for TRL and verifiers. Signed with the same key as eval evidence bundles; verify with `POST /v1/verify`. `format=tasks` returns just `tasks.jsonl` — one task per line in the shape `rl/omnia_grpo/tasks.py` and OpenEnv-style loaders read. operationId: getRewardEnvironment parameters: - name: format in: query required: false schema: type: string enum: - bundle - tasks description: '`bundle` (default, JSON) or `tasks` (JSONL).' responses: '200': description: The signed bundle, or tasks.jsonl when format=tasks. content: application/json: schema: $ref: '#/components/schemas/RewardEnvironmentBundle' application/jsonl: schema: type: string '400': $ref: '#/components/responses/BadRequest' '401': $ref: '#/components/responses/Unauthorized' '403': $ref: '#/components/responses/Forbidden' '404': $ref: '#/components/responses/NotFound' components: schemas: RewardEnvironmentBundle: type: object description: >- Signed (HS256 over canonical JSON; `signature: null` + `unsigned: true` when the deployment has no signing key). properties: bundle_v: type: integer kind: type: string enum: - errorbar.reward_environment issued_at: type: string format: date-time session: type: object properties: id: type: string status: type: string agentic: type: boolean label: type: - string - 'null' created_at: type: string expires_at: type: string held: type: boolean pinned_step: type: - string - 'null' reward: $ref: '#/components/schemas/RewardSpec' grader: type: object properties: criteria: type: array items: type: object certificates: type: array items: type: object description: One signed judge certificate per reward criterion. assertions: type: array items: type: object anchor: type: - object - 'null' tools: type: array items: type: object properties: name: type: string read_only: type: boolean max_calls_per_episode: type: - integer - 'null' tasks: type: array items: $ref: '#/components/schemas/RewardTask' task_count: type: integer endpoints: type: object adapters: type: object properties: trl: type: string verifiers: type: string signature: type: - object - 'null' RewardSpec: oneOf: - type: object required: - mode - criterionId properties: mode: type: string enum: - single criterionId: type: string description: A calibrated judge (TPR and TNR ≥ 0.9, not drift-flagged). - type: object required: - mode - criterionIds properties: mode: type: string enum: - compositional criterionIds: type: array items: type: string minItems: 2 description: >- Two or more calibrated judges (each ≥ 0.75); the composite grade is their mean with any assertions. assertions: type: array items: type: object description: >- Deterministic components (json_schema, regex_match, tool_called, exec …), 0/1 each. RewardTask: type: object required: - goal properties: goal: type: array items: type: object properties: role: type: string content: type: string description: The task as chat messages (1..50). image: type: string description: Optional sandbox image. verifier: type: array items: type: object properties: command: type: string timeout_sec: type: integer description: >- Per-task exec verifiers (≤ 8), run server-side as deterministic reward components. Error: type: object properties: error: type: object properties: message: type: string type: type: string description: >- invalid_request_error, insufficient_quota, rate_limit_error, or api_error. code: type: string description: >- Machine-stable cause, e.g. invalid_api_key, not_found, insufficient_permissions, precondition_failed. required: - message - type - code description: >- Every refusal — gateway and management API alike — uses this one envelope. responses: BadRequest: description: Malformed request or invalid field. content: application/json: schema: $ref: '#/components/schemas/Error' Unauthorized: description: Missing, malformed, or revoked API key. content: application/json: schema: $ref: '#/components/schemas/Error' example: error: message: Invalid API key type: invalid_request_error code: invalid_api_key Forbidden: description: The key lacks the required owner/admin permission. content: application/json: schema: $ref: '#/components/schemas/Error' NotFound: description: The resource does not exist in your workspace. content: application/json: schema: $ref: '#/components/schemas/Error' securitySchemes: bearerAuth: type: http scheme: bearer description: >- Your workspace API key, e.g. `sk_sovereign_...`, sent as `Authorization: Bearer `. ````