> ## 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. # Mark a suggestion pulled > Records that you applied a suggestion in code (`mb pull` does this after writing the candidate). No body (`{}` is accepted too; a body with any field is 400). proposed -> pulled; marking a pulled suggestion again is a no-op that returns it. Any other status is 409 with `details.status`, the status it has: a rejected, accepted or superseded suggestion can't be pulled. Once the candidate serves primary production traffic, it is recorded as `accepted`. Another environment's suggestion is 404. ## OpenAPI ````yaml /openapi.json post /v1/suggestions/{suggestion_id}/mark-pulled 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`. 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. **Retries.** Send an `Idempotency-Key` on every POST under /v1 that takes one (all but `POST /v1/validate` and `POST /v1/review/items/fill`, whose retry is another fill within the day's budget). 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: 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/suggestions/{suggestion_id}/mark-pulled: post: tags: - Suggestions summary: Mark a suggestion pulled description: >- Records that you applied a suggestion in code (`mb pull` does this after writing the candidate). No body (`{}` is accepted too; a body with any field is 400). proposed -> pulled; marking a pulled suggestion again is a no-op that returns it. Any other status is 409 with `details.status`, the status it has: a rejected, accepted or superseded suggestion can't be pulled. Once the candidate serves primary production traffic, it is recorded as `accepted`. Another environment's suggestion is 404. operationId: markSuggestionPulled parameters: - schema: $ref: '#/components/schemas/SuggestionId' required: true name: suggestion_id in: path - schema: type: string minLength: 1 maxLength: 255 pattern: ^[\x20-\x7e]+$ description: >- Makes a retry safe. For 24 hours, the same key with the same request returns the first stored result (with Idempotent-Replayed: true); the same key with a different request is a 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 with its key. required: false description: >- Makes a retry safe. For 24 hours, the same key with the same request returns the first stored result (with Idempotent-Replayed: true); the same key with a different request is a 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 with its key. name: idempotency-key in: header requestBody: required: false content: application/json: schema: $ref: '#/components/schemas/MarkSuggestionPulledRequest' responses: '200': description: The pulled suggestion headers: Idempotent-Replayed: schema: type: string enum: - 'true' description: >- Present and `true` when this is the stored result of an earlier request with the same Idempotency-Key. required: false description: >- Present and `true` when this is the stored result of an earlier request with the same Idempotency-Key. content: application/json: examples: pulled: summary: >- Applied in the repository and marked pulled; accepted once it serves production traffic value: id: sug_0199f2c4-1a2b-7c3d-8e4f-5a6b7c8d9e70 decision_id: refund-exception kind: new_question target: structure summary: >- Ask whether the parcel arrived late or got lost, and count it toward granting environment: test base: version: structure_hash: >- sha256:bdad6e5b1b879209305f1555b43ec62666a4d74a925280c66e54cc4dc07bb1ae number: 1 model: profile: >- defective=jev:jev-1.14.0@jev@0.1.0,item_used=jev:jev-1.14.0@jev@0.1.0 candidate: version: structure_hash: >- sha256:8b4e793adb3c0d8dbf8b57fd9fe3450789681a5d0a727e0e2013514fc210506d number: null model: profile: >- defective=jev:jev-1.14.0@jev@0.1.0,item_used=jev:jev-1.14.0@jev@0.1.0,shipping_failure=jev:jev-1.14.0@jev@0.1.0 requires: [] candidate_structure: questions: item_used: type: noul instructions: >- Has the customer used the item beyond trying it on or setting it up once? reads: - state.message defective: type: noul instructions: >- Does the customer describe a defect, damage on arrival, or the item failing under normal use? reads: - state.message shipping_failure: type: noul instructions: >- Did the order arrive later than promised, or get lost in transit? reads: - state.message attributes: days_since_delivery: type: number minimum: 0 aggregations: grant_score: type: weighted_mean inputs: - name: questions.item_used invert: true - name: questions.defective - name: questions.shipping_failure handling: type: rules rules: - when: name: attributes.days_since_delivery gt: 30 outcome: escalate - when: name: aggregations.grant_score gte: 0.72 outcome: grant - when: name: aggregations.grant_score lt: 0.38 outcome: deny else: escalate result: aggregations.handling diff: - op: add path: /questions/shipping_failure after: type: noul instructions: >- Did the order arrive later than promised, or get lost in transit? reads: - state.message - op: add path: /aggregations/grant_score/inputs/- after: name: questions.shipping_failure evidence: label: training_cases frozen_at: '2026-11-06T16:00:00.000Z' by_split: train: 'n': 5 fixes: 2 breaks: 0 base_correct: 3 candidate_correct: 5 noise_rate: 0 action_mix: null changed_items: - evaluation_id: evl_0199f2c4-1a2b-7c3d-8e4f-5a6b7c8d9e41 feedback_id: fbk_0199f2c4-1a2b-7c3d-8e4f-5a6b7c8d9e50 split: train change: fix before: outcome: escalate answers: item_used: 0.02 defective: 0.3 after: outcome: grant answers: item_used: 0.02 defective: 0.3 shipping_failure: 0.97 - evaluation_id: evl_0199f2c4-1a2b-7c3d-8e4f-5a6b7c8d9e42 feedback_id: fbk_0199f2c4-1a2b-7c3d-8e4f-5a6b7c8d9e51 split: train change: fix before: outcome: escalate answers: item_used: 0 defective: 0.2 after: outcome: grant answers: item_used: 0 defective: 0.2 shipping_failure: 0.99 credited_feedback: [] preview_id: prv_0199f2c4-1a2b-7c3d-8e4f-5a6b7c8d9e71 objective: revision: 1 objective_hash: >- sha256:17c4fed8a47b7094ae83485aab46436ced0b00f24be5b059f2bf6984a4e4e4b3 generator: name: anthropic version: '3' model: claude-sonnet status: pulled created_at: '2026-11-06T16:00:00.000Z' status_at: '2026-11-06T17:00:00.000Z' schema: $ref: '#/components/schemas/Suggestion' '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 in this key's organization and environment content: application/json: schema: $ref: '#/components/schemas/ErrorBody' '409': description: Conflict with the current state content: application/json: schema: $ref: '#/components/schemas/ErrorBody' '410': description: >- The Idempotency-Key's first result was deleted, so it cannot be replayed content: application/json: schema: $ref: '#/components/schemas/ErrorBody' '413': description: The HTTP body exceeds 1 MB (reason BODY_TOO_LARGE) content: application/json: schema: $ref: '#/components/schemas/ErrorBody' '422': description: >- The request is well formed but cannot be processed (IDEMPOTENCY_KEY_REUSED requires a fresh key; REQUEST_TOO_LARGE requires a smaller request) 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: $ref: '#/components/schemas/ErrorBody' security: - bearerAuth: - decisions:develop components: schemas: SuggestionId: type: string pattern: >- ^sug_[0-9a-f]{8}-[0-9a-f]{4}-7[0-9a-f]{3}-[89ab][0-9a-f]{3}-[0-9a-f]{12}$ MarkSuggestionPulledRequest: type: object properties: {} additionalProperties: false description: 'No fields: send no body, or `{}`.' Suggestion: type: object properties: id: $ref: '#/components/schemas/SuggestionIdOutput' decision_id: $ref: '#/components/schemas/DecisionIdOutput' kind: $ref: '#/components/schemas/SuggestionKind' target: $ref: '#/components/schemas/SuggestionTarget' summary: type: string environment: $ref: '#/components/schemas/Environment' base: $ref: '#/components/schemas/VersionRef' candidate: $ref: '#/components/schemas/VersionRef' requires: type: array items: $ref: '#/components/schemas/SuggestionIdOutput' candidate_structure: $ref: '#/components/schemas/DecisionStructureOutput' diff: type: array items: $ref: '#/components/schemas/StructureDiffEntry' evidence: $ref: '#/components/schemas/Evidence' preview_id: type: string pattern: >- ^(prv|run)_[0-9a-f]{8}-[0-9a-f]{4}-7[0-9a-f]{3}-[89ab][0-9a-f]{3}-[0-9a-f]{12}$ description: >- The preview that is this suggestion's evidence: `prv_`, or `run_` for one stored before `prv_`. objective: anyOf: - $ref: '#/components/schemas/ObjectiveRef' - type: 'null' description: >- The stored objective revision its preview was scored with, or null when none was set (balanced losses). Absent on suggestions made before previews were judged, when none was set. generator: $ref: '#/components/schemas/Generator' status: $ref: '#/components/schemas/SuggestionStatusOutput' status_at: $ref: '#/components/schemas/TimestampOutput' rejection_reason: type: string accepted_evaluation_id: $ref: '#/components/schemas/EvaluationIdOutput' accepted_at: $ref: '#/components/schemas/TimestampOutput' created_at: $ref: '#/components/schemas/TimestampOutput' stale: type: object properties: reason: type: string cases: type: integer minimum: 1 description: How many of its evaluated cases have changed feedback. required: - reason - cases additionalProperties: true description: >- Present when feedback on cases this suggestion was evaluated on changed after its evidence was read: an answer it read was changed, withdrawn or corrected, or the owner, a reviewer or an imported example judged one of its cases since, or any feedback since marked one's input as broken. Its evidence is as it was then; preview it again before relying on it. x-moonbounce-sdk-known-fields: true required: - id - decision_id - kind - target - summary - environment - base - candidate - requires - candidate_structure - diff - evidence - preview_id - generator - status - created_at 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: $ref: '#/components/schemas/ErrorIssue' additionalProperties: {} required: - type - message additionalProperties: true x-moonbounce-sdk-known-fields: true required: - error additionalProperties: true x-moonbounce-sdk-known-fields: true SuggestionIdOutput: type: string pattern: >- ^sug_[0-9a-f]{8}-[0-9a-f]{4}-7[0-9a-f]{3}-[89ab][0-9a-f]{3}-[0-9a-f]{12}$ 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. SuggestionKind: type: string enum: - question_rewrite - new_question description: >- question_rewrite: new wording for one question (its question text and criteria). new_question: one new question, added as an input of the aggregation that feeds the result's bands or rules. SuggestionTarget: type: string enum: - structure 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. VersionRef: type: object properties: version: $ref: '#/components/schemas/EvaluatedVersion' model: $ref: '#/components/schemas/ModelProfile' required: - version - model additionalProperties: true x-moonbounce-sdk-known-fields: true DecisionStructureOutput: type: object properties: questions: type: object additionalProperties: $ref: '#/components/schemas/QuestionOutput' description: System One questions, keyed by name. attributes: type: object additionalProperties: $ref: '#/components/schemas/AttributeOutput' description: >- Values your app supplies with each call in `attribute_values`. The model never sees them. aggregations: type: object additionalProperties: $ref: '#/components/schemas/AggregationOutput' result: type: string minLength: 1 maxLength: 80 description: The final feature's path, such as `aggregations.band`. examples: - questions.asks_for_refund - aggregations.band required: - questions - result additionalProperties: true description: >- Everything that defines a decision: questions, attribute declarations, aggregations and the result. Names are unique across all three maps. x-moonbounce-sdk-known-fields: true StructureDiffEntry: type: object properties: op: type: string enum: - replace - add - remove path: type: string pattern: ^\/(questions|aggregations)\/[a-z][a-z0-9_]*(\/[^/]*)*$ before: {} after: {} required: - op - path additionalProperties: true x-moonbounce-sdk-known-fields: true Evidence: type: object properties: label: $ref: '#/components/schemas/EvidenceLabel' frozen_at: $ref: '#/components/schemas/TimestampOutput' by_split: type: object properties: example: $ref: '#/components/schemas/SplitStats' train: $ref: '#/components/schemas/SplitStats' additionalProperties: true x-moonbounce-sdk-known-fields: true noise_rate: type: - number - 'null' minimum: 0 maximum: 1 by_source: type: object properties: app_native: $ref: '#/components/schemas/SplitStats' app_resolution: $ref: '#/components/schemas/SplitStats' reviewer: $ref: '#/components/schemas/SplitStats' owner: $ref: '#/components/schemas/SplitStats' import: $ref: '#/components/schemas/SplitStats' synthetic_review: $ref: '#/components/schemas/SplitStats' action_mix: anyOf: - $ref: '#/components/schemas/ActionMix' - type: 'null' changed_items: type: array items: $ref: '#/components/schemas/ChangedItem' credited_feedback: type: array items: $ref: '#/components/schemas/FeedbackIdOutput' required: - label - frozen_at - by_split - noise_rate - action_mix - changed_items - credited_feedback additionalProperties: true x-moonbounce-sdk-known-fields: true ObjectiveRef: type: object properties: revision: type: integer minimum: 1 objective_hash: type: string required: - revision - objective_hash additionalProperties: true description: The stored objective revision in effect, and its hash. x-moonbounce-sdk-known-fields: true Generator: type: object properties: name: type: string minLength: 1 version: type: string minLength: 1 model: type: string required: - name - version additionalProperties: true x-moonbounce-sdk-known-fields: true SuggestionStatusOutput: type: string enum: - proposed - pulled - accepted - rejected - superseded TimestampOutput: type: string format: date-time EvaluationIdOutput: type: string pattern: >- ^evl_[0-9a-f]{8}-[0-9a-f]{4}-7[0-9a-f]{3}-[89ab][0-9a-f]{3}-[0-9a-f]{12}$ 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 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 ModelProfile: type: object properties: 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: - profile additionalProperties: true description: The model that answered, as its opaque profile. x-moonbounce-sdk-known-fields: true QuestionOutput: oneOf: - $ref: '#/components/schemas/NoulQuestionOutput' discriminator: propertyName: type mapping: noul: '#/components/schemas/NoulQuestionOutput' AttributeOutput: oneOf: - $ref: '#/components/schemas/StringAttributeOutput' - $ref: '#/components/schemas/NumberAttributeOutput' - $ref: '#/components/schemas/BooleanAttributeOutput' discriminator: propertyName: type mapping: string: '#/components/schemas/StringAttributeOutput' number: '#/components/schemas/NumberAttributeOutput' boolean: '#/components/schemas/BooleanAttributeOutput' AggregationOutput: oneOf: - $ref: '#/components/schemas/WeightedMeanOutput' - $ref: '#/components/schemas/LogisticOutput' - $ref: '#/components/schemas/MinOutput' - $ref: '#/components/schemas/MaxOutput' - $ref: '#/components/schemas/ProductOutput' - $ref: '#/components/schemas/NoisyOrOutput' - $ref: '#/components/schemas/AllOutput' - $ref: '#/components/schemas/AnyOutput' - $ref: '#/components/schemas/BandsOutput' - $ref: '#/components/schemas/RulesOutput' - $ref: '#/components/schemas/MatchOutput' discriminator: propertyName: type mapping: weighted_mean: '#/components/schemas/WeightedMeanOutput' logistic: '#/components/schemas/LogisticOutput' min: '#/components/schemas/MinOutput' max: '#/components/schemas/MaxOutput' product: '#/components/schemas/ProductOutput' noisy_or: '#/components/schemas/NoisyOrOutput' all: '#/components/schemas/AllOutput' any: '#/components/schemas/AnyOutput' bands: '#/components/schemas/BandsOutput' rules: '#/components/schemas/RulesOutput' match: '#/components/schemas/MatchOutput' EvidenceLabel: type: string enum: - imported_examples - training_cases SplitStats: type: object properties: 'n': type: integer minimum: 0 fixes: type: integer minimum: 0 breaks: type: integer minimum: 0 base_correct: type: integer minimum: 0 candidate_correct: type: integer minimum: 0 required: - 'n' - fixes - breaks - base_correct - candidate_correct additionalProperties: true x-moonbounce-sdk-known-fields: true ActionMix: type: object properties: before: type: object additionalProperties: type: number minimum: 0 maximum: 1 after: type: object additionalProperties: type: number minimum: 0 maximum: 1 'on': type: string 'n': type: integer minimum: 0 required: - before - after - 'on' - 'n' additionalProperties: true x-moonbounce-sdk-known-fields: true ChangedItem: type: object properties: evaluation_id: $ref: '#/components/schemas/EvaluationIdOutput' feedback_id: $ref: '#/components/schemas/FeedbackIdOutput' split: $ref: '#/components/schemas/Split' change: type: string enum: - fix - break before: type: object properties: outcome: $ref: '#/components/schemas/OutcomeOutput' value: type: number answers: type: object additionalProperties: type: - number - 'null' minimum: 0 maximum: 1 required: - answers additionalProperties: true x-moonbounce-sdk-known-fields: true after: type: object properties: outcome: $ref: '#/components/schemas/OutcomeOutput' value: type: number answers: type: object additionalProperties: type: - number - 'null' minimum: 0 maximum: 1 required: - answers additionalProperties: true x-moonbounce-sdk-known-fields: true required: - evaluation_id - feedback_id - split - change - before - after additionalProperties: true x-moonbounce-sdk-known-fields: true FeedbackIdOutput: type: string pattern: >- ^fbk_[0-9a-f]{8}-[0-9a-f]{4}-7[0-9a-f]{3}-[89ab][0-9a-f]{3}-[0-9a-f]{12}$ StructureHashOutput: type: string pattern: ^sha256:[0-9a-f]{64}$ NoulQuestionOutput: type: object properties: type: type: string enum: - noul instructions: $ref: '#/components/schemas/InstructionsOutput' criteria: type: object properties: 'true': type: string minLength: 1 maxLength: 4000 'false': type: string minLength: 1 maxLength: 4000 additionalProperties: true x-moonbounce-sdk-known-fields: true reads: type: array items: $ref: '#/components/schemas/StatePathOutput' minItems: 1 maxItems: 64 description: >- Paths into an object `state` this question reads, such as `state.message` or `state.order.customer.tier`. The question sees just those values, nested as in the state. Without it the question sees the whole state, as in System One. Every path must exist in the call's `state`; no entry may repeat or contain another. required: - type - instructions additionalProperties: true description: P(true) for a statement about the state. x-moonbounce-sdk-known-fields: true StringAttributeOutput: type: object properties: type: type: string enum: - string enum: type: array items: type: string minLength: 1 maxLength: 200 minItems: 1 maxItems: 255 default: type: string source: type: string minLength: 1 maxLength: 200 description: >- The model and version behind this attribute, such as `toxicity-classifier-v3`. Hashed. from: type: string minLength: 1 maxLength: 256 description: >- A state path (as in `reads`) evaluate fills this attribute from, in place of `attribute_values`: the value at that path, validated by this declaration with no coercion. A missing or null path takes `default`, else it is a 400. A value for it in `attribute_values` is a 400. Hashed as written. examples: - state.message - state.order.order_total_usd required: - type - enum additionalProperties: true x-moonbounce-sdk-known-fields: true NumberAttributeOutput: type: object properties: type: type: string enum: - number minimum: type: number maximum: type: number default: type: number source: type: string minLength: 1 maxLength: 200 description: >- The model and version behind this attribute, such as `toxicity-classifier-v3`. Hashed. from: type: string minLength: 1 maxLength: 256 description: >- A state path (as in `reads`) evaluate fills this attribute from, in place of `attribute_values`: the value at that path, validated by this declaration with no coercion. A missing or null path takes `default`, else it is a 400. A value for it in `attribute_values` is a 400. Hashed as written. examples: - state.message - state.order.order_total_usd required: - type additionalProperties: true x-moonbounce-sdk-known-fields: true BooleanAttributeOutput: type: object properties: type: type: string enum: - boolean default: type: boolean source: type: string minLength: 1 maxLength: 200 description: >- The model and version behind this attribute, such as `toxicity-classifier-v3`. Hashed. from: type: string minLength: 1 maxLength: 256 description: >- A state path (as in `reads`) evaluate fills this attribute from, in place of `attribute_values`: the value at that path, validated by this declaration with no coercion. A missing or null path takes `default`, else it is a 400. A value for it in `attribute_values` is a 400. Hashed as written. examples: - state.message - state.order.order_total_usd required: - type additionalProperties: true x-moonbounce-sdk-known-fields: true WeightedMeanOutput: type: object properties: type: type: string enum: - weighted_mean inputs: type: array items: type: object properties: name: $ref: '#/components/schemas/FeatureRefOutput' weight: type: number exclusiveMinimum: 0 invert: type: boolean required: - name additionalProperties: true x-moonbounce-sdk-known-fields: true minItems: 1 maxItems: 64 required: - type - inputs additionalProperties: true description: 'Σ wᵢ·xᵢ / Σ wᵢ: a weighted average from 0 to 1, not a probability.' x-moonbounce-sdk-known-fields: true LogisticOutput: type: object properties: type: type: string enum: - logistic bias: type: number inputs: type: array items: type: object properties: name: $ref: '#/components/schemas/FeatureRefOutput' weight: type: number required: - name - weight additionalProperties: true x-moonbounce-sdk-known-fields: true minItems: 1 maxItems: 64 required: - type - bias - inputs additionalProperties: true description: σ(bias + Σ wᵢ·xᵢ), with signed weights on raw input values. x-moonbounce-sdk-known-fields: true MinOutput: type: object properties: type: type: string enum: - min inputs: type: array items: type: object properties: name: $ref: '#/components/schemas/FeatureRefOutput' invert: type: boolean required: - name additionalProperties: true x-moonbounce-sdk-known-fields: true minItems: 1 maxItems: 64 required: - type - inputs additionalProperties: true description: 'min xᵢ: all of these, when they overlap.' x-moonbounce-sdk-known-fields: true MaxOutput: type: object properties: type: type: string enum: - max inputs: type: array items: type: object properties: name: $ref: '#/components/schemas/FeatureRefOutput' invert: type: boolean required: - name additionalProperties: true x-moonbounce-sdk-known-fields: true minItems: 1 maxItems: 64 required: - type - inputs additionalProperties: true description: 'max xᵢ: any of these, when they overlap.' x-moonbounce-sdk-known-fields: true ProductOutput: type: object properties: type: type: string enum: - product inputs: type: array items: type: object properties: name: $ref: '#/components/schemas/FeatureRefOutput' invert: type: boolean required: - name additionalProperties: true x-moonbounce-sdk-known-fields: true minItems: 1 maxItems: 64 required: - type - inputs additionalProperties: true description: 'Π xᵢ: all of these, when they are independent.' x-moonbounce-sdk-known-fields: true NoisyOrOutput: type: object properties: type: type: string enum: - noisy_or inputs: type: array items: type: object properties: name: $ref: '#/components/schemas/FeatureRefOutput' invert: type: boolean required: - name additionalProperties: true x-moonbounce-sdk-known-fields: true minItems: 1 maxItems: 64 required: - type - inputs additionalProperties: true description: '1 − Π(1 − xᵢ): any of these, when they are independent.' x-moonbounce-sdk-known-fields: true AllOutput: type: object properties: type: type: string enum: - all inputs: type: array items: type: object properties: name: $ref: '#/components/schemas/FeatureRefOutput' gte: type: number gt: type: number lte: type: number lt: type: number required: - name additionalProperties: true x-moonbounce-sdk-known-fields: true minItems: 1 maxItems: 64 required: - type - inputs additionalProperties: true description: 1 when every input passes its threshold (default ≥ 0.5), else 0. x-moonbounce-sdk-known-fields: true AnyOutput: type: object properties: type: type: string enum: - any inputs: type: array items: type: object properties: name: $ref: '#/components/schemas/FeatureRefOutput' gte: type: number gt: type: number lte: type: number lt: type: number required: - name additionalProperties: true x-moonbounce-sdk-known-fields: true minItems: 1 maxItems: 64 required: - type - inputs additionalProperties: true description: 1 when any input passes its threshold (default ≥ 0.5), else 0. x-moonbounce-sdk-known-fields: true BandsOutput: type: object properties: type: type: string enum: - bands input: $ref: '#/components/schemas/FeatureRefOutput' below: $ref: '#/components/schemas/NameOutput' cuts: type: array items: type: object properties: at: type: number outcome: $ref: '#/components/schemas/NameOutput' required: - at - outcome additionalProperties: true x-moonbounce-sdk-known-fields: true minItems: 1 maxItems: 9 abstain: $ref: '#/components/schemas/NameOutput' required: - type - input - below - cuts additionalProperties: true description: >- Names an outcome for each range of one feature's value. `at` means ≥; `below` is under the first cut. x-moonbounce-sdk-known-fields: true RulesOutput: type: object properties: type: type: string enum: - rules rules: type: array items: type: object properties: when: $ref: '#/components/schemas/ConditionOutput' outcome: $ref: '#/components/schemas/NameOutput' required: - when - outcome additionalProperties: true x-moonbounce-sdk-known-fields: true minItems: 1 maxItems: 64 else: $ref: '#/components/schemas/NameOutput' required: - type - rules - else additionalProperties: true description: >- The first rule whose condition is true names its `outcome`; otherwise `else`. x-moonbounce-sdk-known-fields: true MatchOutput: type: object properties: type: type: string enum: - match input: $ref: '#/components/schemas/FeatureRefOutput' cases: type: object additionalProperties: $ref: '#/components/schemas/NameOutput' description: >- Maps labels to outcomes. "__proto__" is not supported as a case key; use a rules is-condition for that label. else: $ref: '#/components/schemas/NameOutput' abstain: $ref: '#/components/schemas/NameOutput' required: - type - input - cases additionalProperties: true description: Maps a label straight to an outcome. x-moonbounce-sdk-known-fields: true Split: type: string enum: - example - train OutcomeOutput: type: string minLength: 1 maxLength: 200 description: >- An outcome name, or the exact enum label when a string attribute is the result. InstructionsOutput: anyOf: - type: string minLength: 1 maxLength: 4000 - type: object additionalProperties: {} - type: array items: {} minItems: 1 StatePathOutput: type: string minLength: 1 maxLength: 256 description: >- `state.` or a nested object path such as `state.order.customer.tier`: keys of an object `state`. A key has no `.`, `[` or `]`. Array indexes are not supported yet. examples: - state.message - state.order.order_total_usd FeatureRefOutput: type: string minLength: 1 maxLength: 80 description: >- A feature's path: `questions.`, `attributes.` or `aggregations.`. examples: - questions.asks_for_refund - aggregations.band NameOutput: type: string pattern: ^[a-z][a-z0-9_]{0,63}$ ConditionOutput: anyOf: - type: object properties: name: $ref: '#/components/schemas/FeatureRefOutput' gte: type: number gt: type: number lte: type: number lt: type: number is: type: string minLength: 1 maxLength: 200 in: type: array items: type: string minLength: 1 maxLength: 200 minItems: 1 maxItems: 255 abstained: type: boolean enum: - true required: - name additionalProperties: true x-moonbounce-sdk-known-fields: true - type: object properties: all: type: array items: $ref: '#/components/schemas/ConditionOutput' minItems: 1 maxItems: 64 required: - all additionalProperties: true x-moonbounce-sdk-known-fields: true - type: object properties: any: type: array items: $ref: '#/components/schemas/ConditionOutput' minItems: 1 maxItems: 64 required: - any additionalProperties: true x-moonbounce-sdk-known-fields: true - type: object properties: not: $ref: '#/components/schemas/ConditionOutput' required: - not additionalProperties: true x-moonbounce-sdk-known-fields: true securitySchemes: bearerAuth: type: http scheme: bearer description: >- An API key, sent as `Authorization: Bearer `. Each operation lists the scope its key needs: `decisions:evaluate` (evaluate and read evaluations), `decisions:feedback` (your app's feedback) or `decisions:develop` (everything else, including owner feedback and the review queue). An operation listing no scope takes any scoped key. A key with no scope, or without the operation's, gets 403 INSUFFICIENT_SCOPE. ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.