> ## Documentation Index > Fetch the complete documentation index at: https://docs.moonbounce.ai/llms.txt > Use this file to discover all available pages before exploring further. # Get a run > Reads back a run until its `expires_at`: the body its create call answered, byte for byte, with the `include` and `results` that call used. It takes no query parameters and has no pages, so it is as large as the create's answer. To judge a run, pass its `run_id` to loss_report, which reads it without returning the results. A run of `items` or `cases` (createRun) is a Run; an import_examples call's run is an ImportExamplesResponse, whose results carry each example's `feedback_id`. Reading a run of `items` needs the `decisions:evaluate` scope; a run of `items_from` or stored `cases`, or an import's, needs `decisions:develop` (403 INSUFFICIENT_SCOPE otherwise). Another environment's run, an expired one and one made before runs could be read back are 404 RUN_UNKNOWN. The web app (WebApi) may not read runs (403). ## OpenAPI ````yaml /openapi.json get /v1/runs/{run_id} openapi: 3.1.0 info: title: Moonbounce Decisions API version: 0.0.0 description: >- Moonbounce decisions: evaluate an item's state against a decision structure (System One questions, attributes you supply and aggregations over both), record feedback and import labeled examples, review a ranked queue, and improve the structure through suggestions that ship as code diffs, each with a preview (backtest) and an evidence label. **Authentication.** Send an API key as `Authorization: Bearer ` on every operation except `GET /health` and `POST /v1/validate`, and an upload's own `url` (`PUT /v1/uploads/{upload_id}/{token}`), which its token authorizes. Call the API from a server, never a browser: a key must not reach one, and the API sends no CORS headers. A key belongs to one organization and one environment: production, or test for a key with the `env:test` permission. Test traffic never counts as production traffic. **Requests.** JSON bodies (`Content-Type: application/json`) of at most 1 MB, parsed strictly: duplicate keys, lone surrogates, integers outside ±(2^53 - 1), `__proto__` keys, U+0000 and nesting deeper than 64 are a 400. A larger dataset, or a file you'd rather not paste, goes up as a file: `createUpload` answers a URL to PUT it to. **Retries.** Send an `Idempotency-Key` on every POST under /v1 that takes one (all but `POST /v1/validate`, `POST /v1/review/items/fill`, whose retry is another fill within the day's budget, and `createUpload`, whose retry is another upload). Keep it for the request's retries. The same key with the same request returns the first stored result, marked `Idempotent-Replayed: true`, for 24 hours (410 if that result was since deleted); with another request it is 422 IDEMPOTENCY_KEY_REUSED. Keys are scoped to the organization and environment across every operation, so use a fresh key per request. A request that failed before its result was stored runs again when retried. 429 and 503 under /v1 may carry `Retry-After` (seconds); a daily QUOTA_EXCEEDED cap instead names its reset time. **Lists.** A list answers one page: `{environment, items, next_cursor, has_more}` (named `Page`), in the order the operation states. Pass `next_cursor` back as `cursor`, with the same filters, while `has_more` is true; on the last page `next_cursor` is null. `limit` defaults to 50 and is at most 100, with these exceptions: cases go up to 200 a page (a run's batch; 50 with content), suggestions default to 20, since each carries its whole candidate structure and evidence, and the review queue (a reviewer's screen) defaults to 20, at most 50. **Errors.** Every error under /v1 is `{"error": {"type", "message", "reason"?, "param"?, "details"?}}` (ErrorBody); `GET /health` answers its own shape. Every response carries a `Request-Id` header. Rate limits apply per key, and per client IP for requests without a valid key; a 429 RATE_LIMITED carries `Retry-After`. servers: - url: https://api.moonbounce.ai description: Production security: [] tags: - name: Evaluate description: Run one item through a decision and read evaluations back. Start here. - name: Decisions description: >- Validate a decision file, register its versions, and read decisions and versions. - name: Feedback description: >- Say what the right answer was, import labeled examples, and read feedback and cases. - name: Suggestions description: Ask for a better version of a decision, and follow the improvement loop. - name: Uploads description: >- Send a dataset or structure file once, then name it in runs, imports and registrations. - name: Previews & tests description: >- Replay a structure change over past cases, and score a version over many items. - name: Models description: List the models a decision can run on and choose one. - name: Objective description: >- Set what a decision optimizes for, then judge runs and tune cuts against it. - name: Usage description: What a decision's model calls cost. - name: Account description: Identify your key, and check that the API is up. paths: /v1/runs/{run_id}: get: tags: - Previews & tests summary: Get a run description: >- Reads back a run until its `expires_at`: the body its create call answered, byte for byte, with the `include` and `results` that call used. It takes no query parameters and has no pages, so it is as large as the create's answer. To judge a run, pass its `run_id` to loss_report, which reads it without returning the results. A run of `items` or `cases` (createRun) is a Run; an import_examples call's run is an ImportExamplesResponse, whose results carry each example's `feedback_id`. Reading a run of `items` needs the `decisions:evaluate` scope; a run of `items_from` or stored `cases`, or an import's, needs `decisions:develop` (403 INSUFFICIENT_SCOPE otherwise). Another environment's run, an expired one and one made before runs could be read back are 404 RUN_UNKNOWN. The web app (WebApi) may not read runs (403). operationId: getRun parameters: - schema: $ref: '#/components/schemas/RunId' required: true name: run_id in: path responses: '200': description: >- The run as its create call answered it: a Run from createRun, or an ImportExamplesResponse from import_examples content: application/json: examples: labeled_items: summary: >- Two labeled tickets dry-run on version 1, kept for loss_report value: run_id: evr_0199f2c4-1a2b-7c3d-8e4f-5a6b7c8d9e20 expires_at: '2026-11-07T10:00:00.000Z' dry_run: true environment: test decision_id: refund-exception version: structure_hash: >- sha256:bdad6e5b1b879209305f1555b43ec62666a4d74a925280c66e54cc4dc07bb1ae number: 1 model: id: jev-1.14.0 resolved_model: jev-1.14.0 revision: 1 profile: >- defective=jev:jev-1.14.0@jev@0.1.0,item_used=jev:jev-1.14.0@jev@0.1.0 counts: total: 2 decided: 2 computed: 0 abstained: 0 failed: 0 labeled: 2 cost: model_calls: 2 questions: 4 input_tokens: 1040 output_tokens: 8 usd_micros: 42 results: - item_id: t-001 id: dry_0199f2c4-1a2b-7c3d-8e4f-5a6b7c8d9e21 status: decided outcome: escalate cost: model_calls: 1 questions: 2 input_tokens: 520 output_tokens: 4 usd_micros: 21 - item_id: t-002 id: dry_0199f2c4-1a2b-7c3d-8e4f-5a6b7c8d9e22 status: decided outcome: grant cost: model_calls: 1 questions: 2 input_tokens: 520 output_tokens: 4 usd_micros: 21 schema: anyOf: - $ref: '#/components/schemas/Run' - $ref: '#/components/schemas/ImportExamplesResponse' '400': description: 'Invalid request: `param` names the field at fault when one applies' content: application/json: schema: $ref: '#/components/schemas/ErrorBody' '401': description: Missing or invalid API key (reason KEY_INVALID) content: application/json: schema: $ref: '#/components/schemas/ErrorBody' '403': description: The key may not do this content: application/json: schema: $ref: '#/components/schemas/ErrorBody' '404': description: Not found, or not visible to this key (reason RUN_UNKNOWN) x-error-reasons: - RUN_UNKNOWN content: application/json: schema: $ref: '#/components/schemas/ErrorBody' '429': description: >- RATE_LIMITED: retry after Retry-After seconds; QUOTA_EXCEEDED: details.reset_at gives the daily reset time (no Retry-After) headers: Retry-After: schema: type: string description: Seconds to wait before retrying, when waiting helps. required: false description: Seconds to wait before retrying, when waiting helps. content: application/json: schema: $ref: '#/components/schemas/ErrorBody' '503': description: >- Temporarily unavailable, with Retry-After (for example reason AUTH_UNAVAILABLE, ENGINE_UNAVAILABLE or STORE_UNAVAILABLE): retry with the same Idempotency-Key headers: Retry-After: schema: type: string description: Seconds to wait before retrying, when waiting helps. required: true description: Seconds to wait before retrying, when waiting helps. content: application/json: schema: $ref: '#/components/schemas/ErrorBody' security: - bearerAuth: - decisions:evaluate - bearerAuth: - decisions:develop components: schemas: RunId: type: string pattern: >- ^evr_[0-9a-f]{8}-[0-9a-f]{4}-7[0-9a-f]{3}-[89ab][0-9a-f]{3}-[0-9a-f]{12}$ Run: type: object properties: run_id: type: string pattern: >- ^evr_[0-9a-f]{8}-[0-9a-f]{4}-7[0-9a-f]{3}-[89ab][0-9a-f]{3}-[0-9a-f]{12}$ description: >- Pass it to loss_report, or read this response back with getRun; kept until `expires_at`. A stored run's evaluations stay after it expires. expires_at: $ref: '#/components/schemas/TimestampOutput' dry_run: type: boolean description: >- Whether the items were dry runs (no evaluation stored; the run keeps their results) or stored as evaluations. environment: $ref: '#/components/schemas/Environment' decision_id: $ref: '#/components/schemas/DecisionIdOutput' version: $ref: '#/components/schemas/EvaluatedVersion' model: $ref: '#/components/schemas/EvaluatedModel' counts: type: object properties: total: type: integer minimum: 0 decided: type: integer minimum: 0 computed: type: integer minimum: 0 abstained: type: integer minimum: 0 failed: type: integer minimum: 0 labeled: type: integer minimum: 0 description: Items that carried `expected`. required: - total - decided - computed - abstained - failed - labeled additionalProperties: true x-moonbounce-sdk-known-fields: true cost: $ref: '#/components/schemas/Cost' results: type: array items: $ref: '#/components/schemas/RunItemResult' description: >- One per item `results` lists (every item by default; with `failed` only the failed ones, with `none` none), in item order (cases: newest label first). cases: type: object properties: total: type: integer minimum: 0 description: >- Cases that match the filters, across every page; with `evaluation_ids`, those found. excluded: $ref: '#/components/schemas/CaseExcluded' next_cursor: anyOf: - type: string - type: 'null' description: Pass back in `cases.cursor` for the next page. required: - total - excluded - next_cursor additionalProperties: true description: 'With `cases`: which cases the run took.' x-moonbounce-sdk-known-fields: true required: - run_id - expires_at - dry_run - environment - decision_id - version - model - counts - cost - results additionalProperties: true x-moonbounce-sdk-known-fields: true ImportExamplesResponse: type: object properties: run_id: type: string pattern: >- ^evr_[0-9a-f]{8}-[0-9a-f]{4}-7[0-9a-f]{3}-[89ab][0-9a-f]{3}-[0-9a-f]{12}$ description: >- Pass it to loss_report, or read this response back with getRun; kept until `expires_at`. A stored run's evaluations stay after it expires. expires_at: $ref: '#/components/schemas/TimestampOutput' dry_run: type: boolean description: >- Whether the items were dry runs (no evaluation stored; the run keeps their results) or stored as evaluations. environment: $ref: '#/components/schemas/Environment' decision_id: $ref: '#/components/schemas/DecisionIdOutput' version: $ref: '#/components/schemas/EvaluatedVersion' model: $ref: '#/components/schemas/EvaluatedModel' counts: type: object properties: total: type: integer minimum: 0 decided: type: integer minimum: 0 computed: type: integer minimum: 0 abstained: type: integer minimum: 0 failed: type: integer minimum: 0 labeled: type: integer minimum: 0 description: Items that carried `expected`. required: - total - decided - computed - abstained - failed - labeled additionalProperties: true x-moonbounce-sdk-known-fields: true cost: $ref: '#/components/schemas/Cost' results: type: array items: $ref: '#/components/schemas/ImportExampleResult' description: >- One per example, in order (with `items_from`, the upload's lines in order). A failed example stored no evaluation and no feedback: send it again in a new call. required: - run_id - expires_at - dry_run - environment - decision_id - version - model - counts - cost - results additionalProperties: true x-moonbounce-sdk-known-fields: true ErrorBody: type: object properties: error: type: object properties: type: $ref: '#/components/schemas/ErrorType' reason: type: string pattern: ^[A-Z][A-Z0-9_]+$ description: >- Set where a caller can act on it, one of the reasons in the ErrorReason schema. New reasons may be added: treat an unknown one by the status and `type`. message: type: string description: For people; don't parse it. param: type: string description: >- The request field at fault, as a dotted path (`attribute_values.region`, `claims.1.value`). details: type: object properties: issues: type: array items: $ref: '#/components/schemas/ErrorIssue' additionalProperties: {} required: - type - message additionalProperties: true x-moonbounce-sdk-known-fields: true required: - error additionalProperties: true x-moonbounce-sdk-known-fields: true TimestampOutput: type: string format: date-time Environment: type: string enum: - production - test description: >- The environment of the key that made the call: `production` or `test`. Evaluations, feedback, reviews and suggestions are separate per environment; decisions and their versions belong to the whole organization. DecisionIdOutput: type: string pattern: ^[a-z][a-z0-9_.-]{0,127}$ description: >- A name you choose for this decision, such as `refund-exception`: a lowercase letter, then up to 127 of `a-z 0-9 _ . -`. Unique in your organization and shared by its test and production keys. The first registration or evaluation under a new one creates the decision. EvaluatedVersion: type: object properties: structure_hash: $ref: '#/components/schemas/StructureHashOutput' number: type: - integer - 'null' minimum: 1 description: >- The version's number under the decision (1, 2, 3...). Null when the structure isn't registered: a dry run or a preview of a structure nobody registered. The hash is the identity. required: - structure_hash - number additionalProperties: true description: The version that ran. x-moonbounce-sdk-known-fields: true EvaluatedModel: type: object properties: id: type: string description: >- The model the decision's setting names, as `GET .../model` reports it and `PUT .../model` takes it. resolved_model: type: string description: The versioned model that answered. revision: type: - integer - 'null' minimum: 1 description: >- The model setting's revision it ran on. Null when no setting was stored in the environment, so the deployment default applied. profile: type: string description: >- Every question's model and connector, as one opaque string. Compare it for equality (two runs are comparable when their profiles match); don't parse it. required: - id - resolved_model - revision - profile additionalProperties: true description: The model that answered. x-moonbounce-sdk-known-fields: true Cost: type: object properties: model_calls: type: integer minimum: 0 description: >- Upstream model calls, retries included. One call can answer several questions (Jev compiles them into one). questions: type: integer minimum: 0 description: >- Questions sent to a model. An answer from the cache, or one a stored case kept, is not counted. cache_hits: type: integer minimum: 0 description: >- Questions answered from the answer cache, when any were: previews and case runs always report it, evaluate and imports only when the cache served an answer. input_tokens: type: integer minimum: 0 output_tokens: type: integer minimum: 0 usd_micros: type: integer minimum: 0 description: What the model calls cost, in millionths of a US dollar. required: - model_calls - questions - input_tokens - output_tokens - usd_micros additionalProperties: true x-moonbounce-sdk-known-fields: true RunItemResult: type: object properties: item_id: type: string minLength: 1 maxLength: 256 description: The item's id; a stored case's `evaluation_id`. evaluation_id: type: string pattern: >- ^evl_[0-9a-f]{8}-[0-9a-f]{4}-7[0-9a-f]{3}-[89ab][0-9a-f]{3}-[0-9a-f]{12}$ description: 'A stored case: the evaluation replayed.' id: type: string description: >- The item's evaluation id, as one evaluate gives it: `evl_` when stored, `dry_` on a dry run (it names only the usage). Absent on a failed item. status: $ref: '#/components/schemas/RunItemStatusOutput' outcome: $ref: '#/components/schemas/OutcomeOutput' value: type: number via: type: string missing: type: array items: type: string description: Questions on the result's path with no answer. answers: type: object additionalProperties: anyOf: - type: number minimum: 0 maximum: 1 - $ref: '#/components/schemas/ChoiceAnswerValueOutput' - $ref: '#/components/schemas/ScoreAnswerValueOutput' - type: 'null' description: >- With `include: ["answers"]`: each question's answer (P(true) for a noul, an object for a choice or score), null when it has none. attributes: type: object additionalProperties: anyOf: - type: string maxLength: 200 - type: number - type: boolean description: >- With `include: ["attributes"]`, when the decision keeps content (absent when its `store_state` is false). cost: type: object properties: model_calls: type: integer minimum: 0 description: >- Upstream model calls, retries included. One call can answer several questions (Jev compiles them into one). questions: type: integer minimum: 0 description: >- Questions sent to a model. An answer from the cache, or one a stored case kept, is not counted. cache_hits: type: integer minimum: 0 description: >- Questions answered from the answer cache, when any were: previews and case runs always report it, evaluate and imports only when the cache served an answer. input_tokens: type: integer minimum: 0 output_tokens: type: integer minimum: 0 usd_micros: type: integer minimum: 0 description: What the model calls cost, in millionths of a US dollar. required: - model_calls - questions - input_tokens - output_tokens - usd_micros additionalProperties: true description: >- What this item's model calls cost (money): on a failed item, what they spent before failing; absent when none ran. x-moonbounce-sdk-known-fields: true evaluation: anyOf: - type: object properties: environment: $ref: '#/components/schemas/Environment' id: $ref: '#/components/schemas/EvaluationIdOutput' dry_run: not: {} description: 'Must be absent: only a dry run sets `dry_run`.' x-moonbounce-absent: true answers: type: object additionalProperties: $ref: '#/components/schemas/Answer' description: Each question's answer, as System One returns it. aggregations: type: object additionalProperties: $ref: '#/components/schemas/AggregationResult' description: >- Every aggregation's result. The result's own aggregation carries `via` when it is bands, rules or match. moonbounce: type: object properties: decision_id: $ref: '#/components/schemas/DecisionIdOutput' item_id: type: string metadata: $ref: '#/components/schemas/MetadataOutput' summary: type: string required: - decision_id - item_id additionalProperties: true description: >- What you sent in `moonbounce`, echoed. What ran is in `version` and `model`. x-moonbounce-sdk-known-fields: true version: $ref: '#/components/schemas/EvaluatedVersion' model: $ref: '#/components/schemas/EvaluatedModel' cost: $ref: '#/components/schemas/EvaluateCost' status: type: string enum: - computed value: type: number outcome: not: {} description: >- Must be absent: a computed result is a number, with no outcome. x-moonbounce-absent: true missing: type: array items: $ref: '#/components/schemas/FeatureRefOutput' description: >- The questions the result depends on (through `result` and every aggregation on its path) that have no answer, abstained or failed, as `questions.x` paths in authored question order. Absent when none is missing; reported for every status. A caller who must not act on partial evidence checks that it is absent, for example `status === "decided" && !missing`. required: - environment - id - answers - aggregations - moonbounce - version - model - cost - status - value additionalProperties: true x-moonbounce-sdk-known-fields: true - type: object properties: environment: $ref: '#/components/schemas/Environment' id: $ref: '#/components/schemas/EvaluationIdOutput' dry_run: not: {} description: 'Must be absent: only a dry run sets `dry_run`.' x-moonbounce-absent: true answers: type: object additionalProperties: $ref: '#/components/schemas/Answer' description: Each question's answer, as System One returns it. aggregations: type: object additionalProperties: $ref: '#/components/schemas/AggregationResult' description: >- Every aggregation's result. The result's own aggregation carries `via` when it is bands, rules or match. moonbounce: type: object properties: decision_id: $ref: '#/components/schemas/DecisionIdOutput' item_id: type: string metadata: $ref: '#/components/schemas/MetadataOutput' summary: type: string required: - decision_id - item_id additionalProperties: true description: >- What you sent in `moonbounce`, echoed. What ran is in `version` and `model`. x-moonbounce-sdk-known-fields: true version: $ref: '#/components/schemas/EvaluatedVersion' model: $ref: '#/components/schemas/EvaluatedModel' cost: $ref: '#/components/schemas/EvaluateCost' status: type: string enum: - decided value: type: number outcome: $ref: '#/components/schemas/OutcomeOutput' missing: type: array items: $ref: '#/components/schemas/FeatureRefOutput' description: >- The questions the result depends on (through `result` and every aggregation on its path) that have no answer, abstained or failed, as `questions.x` paths in authored question order. Absent when none is missing; reported for every status. A caller who must not act on partial evidence checks that it is absent, for example `status === "decided" && !missing`. required: - environment - id - answers - aggregations - moonbounce - version - model - cost - status - outcome additionalProperties: true x-moonbounce-sdk-known-fields: true - type: object properties: environment: $ref: '#/components/schemas/Environment' id: $ref: '#/components/schemas/EvaluationIdOutput' dry_run: not: {} description: 'Must be absent: only a dry run sets `dry_run`.' x-moonbounce-absent: true answers: type: object additionalProperties: $ref: '#/components/schemas/Answer' description: Each question's answer, as System One returns it. aggregations: type: object additionalProperties: $ref: '#/components/schemas/AggregationResult' description: >- Every aggregation's result. The result's own aggregation carries `via` when it is bands, rules or match. moonbounce: type: object properties: decision_id: $ref: '#/components/schemas/DecisionIdOutput' item_id: type: string metadata: $ref: '#/components/schemas/MetadataOutput' summary: type: string required: - decision_id - item_id additionalProperties: true description: >- What you sent in `moonbounce`, echoed. What ran is in `version` and `model`. x-moonbounce-sdk-known-fields: true version: $ref: '#/components/schemas/EvaluatedVersion' model: $ref: '#/components/schemas/EvaluatedModel' cost: $ref: '#/components/schemas/EvaluateCost' status: type: string enum: - abstained value: not: {} description: 'Must be absent: an abstained result has no value.' x-moonbounce-absent: true outcome: $ref: '#/components/schemas/OutcomeOutput' missing: type: array items: $ref: '#/components/schemas/FeatureRefOutput' description: >- The questions the result depends on (through `result` and every aggregation on its path) that have no answer, abstained or failed, as `questions.x` paths in authored question order. Absent when none is missing; reported for every status. A caller who must not act on partial evidence checks that it is absent, for example `status === "decided" && !missing`. required: - environment - id - answers - aggregations - moonbounce - version - model - cost - status additionalProperties: true x-moonbounce-sdk-known-fields: true - type: object properties: environment: $ref: '#/components/schemas/Environment' id: $ref: '#/components/schemas/DryRunId' dry_run: type: boolean enum: - true answers: type: object additionalProperties: $ref: '#/components/schemas/Answer' description: Each question's answer, as System One returns it. aggregations: type: object additionalProperties: $ref: '#/components/schemas/AggregationResult' description: >- Every aggregation's result. The result's own aggregation carries `via` when it is bands, rules or match. moonbounce: type: object properties: decision_id: $ref: '#/components/schemas/DecisionIdOutput' item_id: type: string metadata: $ref: '#/components/schemas/MetadataOutput' summary: type: string required: - decision_id - item_id additionalProperties: true description: >- What you sent in `moonbounce`, echoed. What ran is in `version` and `model`. x-moonbounce-sdk-known-fields: true version: $ref: '#/components/schemas/EvaluatedVersion' model: $ref: '#/components/schemas/EvaluatedModel' cost: $ref: '#/components/schemas/EvaluateCost' status: type: string enum: - computed value: type: number outcome: not: {} description: >- Must be absent: a computed result is a number, with no outcome. x-moonbounce-absent: true missing: type: array items: $ref: '#/components/schemas/FeatureRefOutput' description: >- The questions the result depends on (through `result` and every aggregation on its path) that have no answer, abstained or failed, as `questions.x` paths in authored question order. Absent when none is missing; reported for every status. A caller who must not act on partial evidence checks that it is absent, for example `status === "decided" && !missing`. required: - environment - id - dry_run - answers - aggregations - moonbounce - version - model - cost - status - value additionalProperties: true x-moonbounce-sdk-known-fields: true - type: object properties: environment: $ref: '#/components/schemas/Environment' id: $ref: '#/components/schemas/DryRunId' dry_run: type: boolean enum: - true answers: type: object additionalProperties: $ref: '#/components/schemas/Answer' description: Each question's answer, as System One returns it. aggregations: type: object additionalProperties: $ref: '#/components/schemas/AggregationResult' description: >- Every aggregation's result. The result's own aggregation carries `via` when it is bands, rules or match. moonbounce: type: object properties: decision_id: $ref: '#/components/schemas/DecisionIdOutput' item_id: type: string metadata: $ref: '#/components/schemas/MetadataOutput' summary: type: string required: - decision_id - item_id additionalProperties: true description: >- What you sent in `moonbounce`, echoed. What ran is in `version` and `model`. x-moonbounce-sdk-known-fields: true version: $ref: '#/components/schemas/EvaluatedVersion' model: $ref: '#/components/schemas/EvaluatedModel' cost: $ref: '#/components/schemas/EvaluateCost' status: type: string enum: - decided value: type: number outcome: $ref: '#/components/schemas/OutcomeOutput' missing: type: array items: $ref: '#/components/schemas/FeatureRefOutput' description: >- The questions the result depends on (through `result` and every aggregation on its path) that have no answer, abstained or failed, as `questions.x` paths in authored question order. Absent when none is missing; reported for every status. A caller who must not act on partial evidence checks that it is absent, for example `status === "decided" && !missing`. required: - environment - id - dry_run - answers - aggregations - moonbounce - version - model - cost - status - outcome additionalProperties: true x-moonbounce-sdk-known-fields: true - type: object properties: environment: $ref: '#/components/schemas/Environment' id: $ref: '#/components/schemas/DryRunId' dry_run: type: boolean enum: - true answers: type: object additionalProperties: $ref: '#/components/schemas/Answer' description: Each question's answer, as System One returns it. aggregations: type: object additionalProperties: $ref: '#/components/schemas/AggregationResult' description: >- Every aggregation's result. The result's own aggregation carries `via` when it is bands, rules or match. moonbounce: type: object properties: decision_id: $ref: '#/components/schemas/DecisionIdOutput' item_id: type: string metadata: $ref: '#/components/schemas/MetadataOutput' summary: type: string required: - decision_id - item_id additionalProperties: true description: >- What you sent in `moonbounce`, echoed. What ran is in `version` and `model`. x-moonbounce-sdk-known-fields: true version: $ref: '#/components/schemas/EvaluatedVersion' model: $ref: '#/components/schemas/EvaluatedModel' cost: $ref: '#/components/schemas/EvaluateCost' status: type: string enum: - abstained value: not: {} description: 'Must be absent: an abstained result has no value.' x-moonbounce-absent: true outcome: $ref: '#/components/schemas/OutcomeOutput' missing: type: array items: $ref: '#/components/schemas/FeatureRefOutput' description: >- The questions the result depends on (through `result` and every aggregation on its path) that have no answer, abstained or failed, as `questions.x` paths in authored question order. Absent when none is missing; reported for every status. A caller who must not act on partial evidence checks that it is absent, for example `status === "decided" && !missing`. required: - environment - id - dry_run - answers - aggregations - moonbounce - version - model - cost - status additionalProperties: true x-moonbounce-sdk-known-fields: true description: >- With `include: ["evaluation"]`: what evaluate returns for this item on its own (absent on a failed item). error: type: object properties: code: type: string description: >- The reason, such as `ENGINE_FAILED`, `ENGINE_UNAVAILABLE` or `NOT_STARTED`. message: type: string retryable: type: boolean description: Sending the item again may work. required: - code - message - retryable additionalProperties: true description: Why it failed; only with status `failed`. x-moonbounce-sdk-known-fields: true required: - item_id - status additionalProperties: true x-moonbounce-sdk-known-fields: true CaseExcluded: type: object properties: withdrawn: type: integer minimum: 1 retired: type: integer minimum: 1 excluded: type: integer minimum: 1 contested: type: integer minimum: 1 no_consensus: type: integer minimum: 1 no_outcome: type: integer minimum: 1 outcome_not_in_result: type: integer minimum: 1 no_deciding_ballot: type: integer minimum: 1 attribute_inputs_unavailable: type: integer minimum: 1 duplicate_group: type: integer minimum: 1 description: >- Evaluations with feedback that are not cases, by reason: `withdrawn` (all feedback withdrawn), `retired` (feedback older than the last policy change), `excluded` (flagged input_broken), `contested` (reviewers disagree), `no_consensus` (no feedback that decides an outcome), `no_outcome` (feedback rules outcomes out without naming one), `outcome_not_in_result` (expected outcome not in `outcomes`), `no_deciding_ballot`, `attribute_inputs_unavailable` (stored before attribute inputs were kept, with a default that can't be read back), `duplicate_group` (another evaluation in its group counts instead: the same item, or near-identical content with the same label). ImportExampleResult: type: object properties: item_id: type: string minLength: 1 maxLength: 256 description: The item's id; a stored case's `evaluation_id`. evaluation_id: type: string pattern: >- ^evl_[0-9a-f]{8}-[0-9a-f]{4}-7[0-9a-f]{3}-[89ab][0-9a-f]{3}-[0-9a-f]{12}$ description: 'A stored case: the evaluation replayed.' id: type: string description: >- The item's evaluation id, as one evaluate gives it: `evl_` when stored, `dry_` on a dry run (it names only the usage). Absent on a failed item. status: $ref: '#/components/schemas/RunItemStatusOutput' outcome: $ref: '#/components/schemas/OutcomeOutput' value: type: number via: type: string missing: type: array items: type: string description: Questions on the result's path with no answer. answers: type: object additionalProperties: anyOf: - type: number minimum: 0 maximum: 1 - $ref: '#/components/schemas/ChoiceAnswerValueOutput' - $ref: '#/components/schemas/ScoreAnswerValueOutput' - type: 'null' description: >- With `include: ["answers"]`: each question's answer (P(true) for a noul, an object for a choice or score), null when it has none. attributes: type: object additionalProperties: anyOf: - type: string maxLength: 200 - type: number - type: boolean description: >- With `include: ["attributes"]`, when the decision keeps content (absent when its `store_state` is false). cost: type: object properties: model_calls: type: integer minimum: 0 description: >- Upstream model calls, retries included. One call can answer several questions (Jev compiles them into one). questions: type: integer minimum: 0 description: >- Questions sent to a model. An answer from the cache, or one a stored case kept, is not counted. cache_hits: type: integer minimum: 0 description: >- Questions answered from the answer cache, when any were: previews and case runs always report it, evaluate and imports only when the cache served an answer. input_tokens: type: integer minimum: 0 output_tokens: type: integer minimum: 0 usd_micros: type: integer minimum: 0 description: What the model calls cost, in millionths of a US dollar. required: - model_calls - questions - input_tokens - output_tokens - usd_micros additionalProperties: true description: >- What this item's model calls cost (money): on a failed item, what they spent before failing; absent when none ran. x-moonbounce-sdk-known-fields: true evaluation: anyOf: - type: object properties: environment: $ref: '#/components/schemas/Environment' id: $ref: '#/components/schemas/EvaluationIdOutput' dry_run: not: {} description: 'Must be absent: only a dry run sets `dry_run`.' x-moonbounce-absent: true answers: type: object additionalProperties: $ref: '#/components/schemas/Answer' description: Each question's answer, as System One returns it. aggregations: type: object additionalProperties: $ref: '#/components/schemas/AggregationResult' description: >- Every aggregation's result. The result's own aggregation carries `via` when it is bands, rules or match. moonbounce: type: object properties: decision_id: $ref: '#/components/schemas/DecisionIdOutput' item_id: type: string metadata: $ref: '#/components/schemas/MetadataOutput' summary: type: string required: - decision_id - item_id additionalProperties: true description: >- What you sent in `moonbounce`, echoed. What ran is in `version` and `model`. x-moonbounce-sdk-known-fields: true version: $ref: '#/components/schemas/EvaluatedVersion' model: $ref: '#/components/schemas/EvaluatedModel' cost: $ref: '#/components/schemas/EvaluateCost' status: type: string enum: - computed value: type: number outcome: not: {} description: >- Must be absent: a computed result is a number, with no outcome. x-moonbounce-absent: true missing: type: array items: $ref: '#/components/schemas/FeatureRefOutput' description: >- The questions the result depends on (through `result` and every aggregation on its path) that have no answer, abstained or failed, as `questions.x` paths in authored question order. Absent when none is missing; reported for every status. A caller who must not act on partial evidence checks that it is absent, for example `status === "decided" && !missing`. required: - environment - id - answers - aggregations - moonbounce - version - model - cost - status - value additionalProperties: true x-moonbounce-sdk-known-fields: true - type: object properties: environment: $ref: '#/components/schemas/Environment' id: $ref: '#/components/schemas/EvaluationIdOutput' dry_run: not: {} description: 'Must be absent: only a dry run sets `dry_run`.' x-moonbounce-absent: true answers: type: object additionalProperties: $ref: '#/components/schemas/Answer' description: Each question's answer, as System One returns it. aggregations: type: object additionalProperties: $ref: '#/components/schemas/AggregationResult' description: >- Every aggregation's result. The result's own aggregation carries `via` when it is bands, rules or match. moonbounce: type: object properties: decision_id: $ref: '#/components/schemas/DecisionIdOutput' item_id: type: string metadata: $ref: '#/components/schemas/MetadataOutput' summary: type: string required: - decision_id - item_id additionalProperties: true description: >- What you sent in `moonbounce`, echoed. What ran is in `version` and `model`. x-moonbounce-sdk-known-fields: true version: $ref: '#/components/schemas/EvaluatedVersion' model: $ref: '#/components/schemas/EvaluatedModel' cost: $ref: '#/components/schemas/EvaluateCost' status: type: string enum: - decided value: type: number outcome: $ref: '#/components/schemas/OutcomeOutput' missing: type: array items: $ref: '#/components/schemas/FeatureRefOutput' description: >- The questions the result depends on (through `result` and every aggregation on its path) that have no answer, abstained or failed, as `questions.x` paths in authored question order. Absent when none is missing; reported for every status. A caller who must not act on partial evidence checks that it is absent, for example `status === "decided" && !missing`. required: - environment - id - answers - aggregations - moonbounce - version - model - cost - status - outcome additionalProperties: true x-moonbounce-sdk-known-fields: true - type: object properties: environment: $ref: '#/components/schemas/Environment' id: $ref: '#/components/schemas/EvaluationIdOutput' dry_run: not: {} description: 'Must be absent: only a dry run sets `dry_run`.' x-moonbounce-absent: true answers: type: object additionalProperties: $ref: '#/components/schemas/Answer' description: Each question's answer, as System One returns it. aggregations: type: object additionalProperties: $ref: '#/components/schemas/AggregationResult' description: >- Every aggregation's result. The result's own aggregation carries `via` when it is bands, rules or match. moonbounce: type: object properties: decision_id: $ref: '#/components/schemas/DecisionIdOutput' item_id: type: string metadata: $ref: '#/components/schemas/MetadataOutput' summary: type: string required: - decision_id - item_id additionalProperties: true description: >- What you sent in `moonbounce`, echoed. What ran is in `version` and `model`. x-moonbounce-sdk-known-fields: true version: $ref: '#/components/schemas/EvaluatedVersion' model: $ref: '#/components/schemas/EvaluatedModel' cost: $ref: '#/components/schemas/EvaluateCost' status: type: string enum: - abstained value: not: {} description: 'Must be absent: an abstained result has no value.' x-moonbounce-absent: true outcome: $ref: '#/components/schemas/OutcomeOutput' missing: type: array items: $ref: '#/components/schemas/FeatureRefOutput' description: >- The questions the result depends on (through `result` and every aggregation on its path) that have no answer, abstained or failed, as `questions.x` paths in authored question order. Absent when none is missing; reported for every status. A caller who must not act on partial evidence checks that it is absent, for example `status === "decided" && !missing`. required: - environment - id - answers - aggregations - moonbounce - version - model - cost - status additionalProperties: true x-moonbounce-sdk-known-fields: true - type: object properties: environment: $ref: '#/components/schemas/Environment' id: $ref: '#/components/schemas/DryRunId' dry_run: type: boolean enum: - true answers: type: object additionalProperties: $ref: '#/components/schemas/Answer' description: Each question's answer, as System One returns it. aggregations: type: object additionalProperties: $ref: '#/components/schemas/AggregationResult' description: >- Every aggregation's result. The result's own aggregation carries `via` when it is bands, rules or match. moonbounce: type: object properties: decision_id: $ref: '#/components/schemas/DecisionIdOutput' item_id: type: string metadata: $ref: '#/components/schemas/MetadataOutput' summary: type: string required: - decision_id - item_id additionalProperties: true description: >- What you sent in `moonbounce`, echoed. What ran is in `version` and `model`. x-moonbounce-sdk-known-fields: true version: $ref: '#/components/schemas/EvaluatedVersion' model: $ref: '#/components/schemas/EvaluatedModel' cost: $ref: '#/components/schemas/EvaluateCost' status: type: string enum: - computed value: type: number outcome: not: {} description: >- Must be absent: a computed result is a number, with no outcome. x-moonbounce-absent: true missing: type: array items: $ref: '#/components/schemas/FeatureRefOutput' description: >- The questions the result depends on (through `result` and every aggregation on its path) that have no answer, abstained or failed, as `questions.x` paths in authored question order. Absent when none is missing; reported for every status. A caller who must not act on partial evidence checks that it is absent, for example `status === "decided" && !missing`. required: - environment - id - dry_run - answers - aggregations - moonbounce - version - model - cost - status - value additionalProperties: true x-moonbounce-sdk-known-fields: true - type: object properties: environment: $ref: '#/components/schemas/Environment' id: $ref: '#/components/schemas/DryRunId' dry_run: type: boolean enum: - true answers: type: object additionalProperties: $ref: '#/components/schemas/Answer' description: Each question's answer, as System One returns it. aggregations: type: object additionalProperties: $ref: '#/components/schemas/AggregationResult' description: >- Every aggregation's result. The result's own aggregation carries `via` when it is bands, rules or match. moonbounce: type: object properties: decision_id: $ref: '#/components/schemas/DecisionIdOutput' item_id: type: string metadata: $ref: '#/components/schemas/MetadataOutput' summary: type: string required: - decision_id - item_id additionalProperties: true description: >- What you sent in `moonbounce`, echoed. What ran is in `version` and `model`. x-moonbounce-sdk-known-fields: true version: $ref: '#/components/schemas/EvaluatedVersion' model: $ref: '#/components/schemas/EvaluatedModel' cost: $ref: '#/components/schemas/EvaluateCost' status: type: string enum: - decided value: type: number outcome: $ref: '#/components/schemas/OutcomeOutput' missing: type: array items: $ref: '#/components/schemas/FeatureRefOutput' description: >- The questions the result depends on (through `result` and every aggregation on its path) that have no answer, abstained or failed, as `questions.x` paths in authored question order. Absent when none is missing; reported for every status. A caller who must not act on partial evidence checks that it is absent, for example `status === "decided" && !missing`. required: - environment - id - dry_run - answers - aggregations - moonbounce - version - model - cost - status - outcome additionalProperties: true x-moonbounce-sdk-known-fields: true - type: object properties: environment: $ref: '#/components/schemas/Environment' id: $ref: '#/components/schemas/DryRunId' dry_run: type: boolean enum: - true answers: type: object additionalProperties: $ref: '#/components/schemas/Answer' description: Each question's answer, as System One returns it. aggregations: type: object additionalProperties: $ref: '#/components/schemas/AggregationResult' description: >- Every aggregation's result. The result's own aggregation carries `via` when it is bands, rules or match. moonbounce: type: object properties: decision_id: $ref: '#/components/schemas/DecisionIdOutput' item_id: type: string metadata: $ref: '#/components/schemas/MetadataOutput' summary: type: string required: - decision_id - item_id additionalProperties: true description: >- What you sent in `moonbounce`, echoed. What ran is in `version` and `model`. x-moonbounce-sdk-known-fields: true version: $ref: '#/components/schemas/EvaluatedVersion' model: $ref: '#/components/schemas/EvaluatedModel' cost: $ref: '#/components/schemas/EvaluateCost' status: type: string enum: - abstained value: not: {} description: 'Must be absent: an abstained result has no value.' x-moonbounce-absent: true outcome: $ref: '#/components/schemas/OutcomeOutput' missing: type: array items: $ref: '#/components/schemas/FeatureRefOutput' description: >- The questions the result depends on (through `result` and every aggregation on its path) that have no answer, abstained or failed, as `questions.x` paths in authored question order. Absent when none is missing; reported for every status. A caller who must not act on partial evidence checks that it is absent, for example `status === "decided" && !missing`. required: - environment - id - dry_run - answers - aggregations - moonbounce - version - model - cost - status additionalProperties: true x-moonbounce-sdk-known-fields: true description: >- With `include: ["evaluation"]`: what evaluate returns for this item on its own (absent on a failed item). error: type: object properties: code: type: string description: >- The reason, such as `ENGINE_FAILED`, `ENGINE_UNAVAILABLE` or `NOT_STARTED`. message: type: string retryable: type: boolean description: Sending the item again may work. required: - code - message - retryable additionalProperties: true description: Why it failed; only with status `failed`. x-moonbounce-sdk-known-fields: true feedback_id: type: string pattern: >- ^fbk_[0-9a-f]{8}-[0-9a-f]{4}-7[0-9a-f]{3}-[89ab][0-9a-f]{3}-[0-9a-f]{12}$ description: The example's labels as feedback; absent on a failed example. required: - item_id - status additionalProperties: true x-moonbounce-sdk-known-fields: true ErrorType: type: string enum: - invalid_request - authentication - permission_denied - not_found - conflict - rate_limited - engine_failed - unavailable - internal ErrorIssue: type: object properties: param: type: string code: type: string pattern: ^[A-Z][A-Z0-9_]+$ description: >- Stable, extensible issue code; unknown codes still have a parameter and human-readable message. message: type: string required: - param - code - message additionalProperties: true x-moonbounce-sdk-known-fields: true StructureHashOutput: type: string pattern: ^sha256:[0-9a-f]{64}$ RunItemStatusOutput: type: string enum: - decided - computed - abstained - failed OutcomeOutput: type: string minLength: 1 maxLength: 200 description: >- An outcome name, or the exact enum label when a string attribute is the result. ChoiceAnswerValueOutput: type: object properties: type: type: string enum: - choice choice: type: string description: 'The chosen option: one of the most likely.' probabilities: type: object additionalProperties: type: number minimum: 0 maximum: 1 description: Each option's probability. confidence: type: number minimum: 0 maximum: 1 required: - type - choice - probabilities - confidence additionalProperties: true description: A choice question's answer. x-moonbounce-sdk-known-fields: true ScoreAnswerValueOutput: type: object properties: type: type: string enum: - score score: type: number description: Σ level × probability, from 0 to the top level. probabilities: type: object additionalProperties: type: number minimum: 0 maximum: 1 description: >- Each level's probability, keyed by its number as a string ("0", "1", …). confidence: type: number minimum: 0 maximum: 1 required: - type - score - probabilities - confidence additionalProperties: true description: A score question's answer. x-moonbounce-sdk-known-fields: true EvaluationIdOutput: type: string pattern: >- ^evl_[0-9a-f]{8}-[0-9a-f]{4}-7[0-9a-f]{3}-[89ab][0-9a-f]{3}-[0-9a-f]{12}$ Answer: anyOf: - type: object properties: type: type: string enum: - noul noul: type: number minimum: 0 maximum: 1 required: - type - noul additionalProperties: true x-moonbounce-sdk-known-fields: true - type: object properties: type: type: string enum: - noul abstained: type: boolean enum: - true required: - type - abstained additionalProperties: true x-moonbounce-sdk-known-fields: true - type: object properties: type: type: string enum: - noul failed: type: boolean enum: - true required: - type - failed additionalProperties: true x-moonbounce-sdk-known-fields: true - $ref: '#/components/schemas/ChoiceAnswerValueOutput' - type: object properties: type: type: string enum: - choice abstained: type: boolean enum: - true required: - type - abstained additionalProperties: true x-moonbounce-sdk-known-fields: true - type: object properties: type: type: string enum: - choice failed: type: boolean enum: - true required: - type - failed additionalProperties: true x-moonbounce-sdk-known-fields: true - type: object properties: type: type: string enum: - score score: type: number description: Σ level × probability, from 0 to the top level. probabilities: type: object additionalProperties: type: number minimum: 0 maximum: 1 description: >- Each level's probability, keyed by its number as a string ("0", "1", …). confidence: type: number minimum: 0 maximum: 1 legend: type: object additionalProperties: {} description: >- Each level's description, keyed by its number, as the model returned it. required: - type - score - probabilities - confidence - legend additionalProperties: true x-moonbounce-sdk-known-fields: true - type: object properties: type: type: string enum: - score abstained: type: boolean enum: - true required: - type - abstained additionalProperties: true x-moonbounce-sdk-known-fields: true - type: object properties: type: type: string enum: - score failed: type: boolean enum: - true required: - type - failed additionalProperties: true x-moonbounce-sdk-known-fields: true description: >- A question's answer as System One returns it, by `type`: `noul`, `choice` or `score`. The types are an open catalog: skip an answer whose type you don't know. AggregationResult: type: object properties: type: type: string value: type: number outcome: $ref: '#/components/schemas/OutcomeOutput' via: type: string description: >- A zero-based rule index, `cases.