> ## Documentation Index > Fetch the complete documentation index at: https://evalgate.com/docs/llms.txt > Use this file to discover all available pages before exploring further. # Get evaluations human review > Requires scopes: runs:read ## OpenAPI ````yaml /api-reference/openapi.json get /api/evaluations/{id}/human-review openapi: 3.1.0 info: title: EvalGate API version: 3.7.6 description: EvalGate API. See docs/api-contract.md for stability commitments. servers: - url: https://evalgate.com description: Production - url: http://localhost:3000 description: Local security: [] paths: /api/evaluations/{id}/human-review: get: tags: - evaluations summary: Get evaluations human review description: 'Requires scopes: runs:read' operationId: get_evaluations_id_human_review parameters: - name: id in: path required: true schema: type: integer - name: batchId in: query required: false schema: type: string - name: runId in: query required: false schema: type: string responses: '200': description: Successful response content: application/json: schema: $ref: >- #/components/schemas/GetApiEvaluationsIdHumanReviewResponse200ApplicationJson '400': $ref: '#/components/responses/ValidationError' '401': $ref: '#/components/responses/Unauthorized' '403': $ref: '#/components/responses/Forbidden' '404': $ref: '#/components/responses/NotFound' '409': $ref: '#/components/responses/Conflict' '429': $ref: '#/components/responses/RateLimited' '500': $ref: '#/components/responses/InternalError' security: - bearerAuth: - runs:read components: schemas: GetApiEvaluationsIdHumanReviewResponse200ApplicationJson: type: object properties: batch: type: object properties: id: type: number evaluationId: type: number evaluationRunId: oneOf: - type: 'null' - type: number sampleSize: type: number samplingStrategy: type: string seed: oneOf: - type: 'null' - type: string assignedReviewerId: oneOf: - type: 'null' - type: string createdBy: type: string createdAt: type: string additionalProperties: false required: - id - evaluationId - evaluationRunId - sampleSize - samplingStrategy - seed - assignedReviewerId - createdBy - createdAt items: type: array items: type: object properties: sampleId: type: number testCaseId: type: number testResultId: type: number snapshot: type: object properties: testCaseId: type: number testResultId: type: number systemVerdict: oneOf: - type: string enum: - pass - type: string enum: - fail caseName: type: string input: type: string expectedOutput: oneOf: - type: 'null' - type: string output: oneOf: - type: 'null' - type: string error: oneOf: - type: 'null' - type: string assertions: oneOf: - type: 'null' - type: object additionalProperties: oneOf: - type: string - type: number - type: boolean enum: - false - type: boolean enum: - true messages: oneOf: - type: 'null' - type: array items: type: object properties: role: type: string content: type: string timestamp: type: string additionalProperties: false required: - role - content toolCalls: oneOf: - type: 'null' - type: array items: type: object properties: name: type: string arguments: type: object additionalProperties: $ref: '#/components/schemas/JsonValue' output: type: string timestamp: type: string additionalProperties: false required: - name - arguments trajectory: oneOf: - type: 'null' - type: object properties: testCaseId: type: number status: oneOf: - type: string enum: - failed - type: string enum: - passed behavior: oneOf: - type: string enum: - tool_use - type: string enum: - classification - type: string enum: - retrieval - type: string enum: - extraction - type: string enum: - multi_step_reasoning taskType: type: string trajectory: type: object properties: id: type: string input: type: string finalOutput: type: string steps: type: array items: type: object properties: index: type: number type: oneOf: - type: string enum: - final - type: string enum: - reasoning - type: string enum: - tool_call - type: string enum: - tool_result content: type: string toolName: type: string toolArgs: type: object additionalProperties: $ref: '#/components/schemas/JsonValue' timestamp: type: number additionalProperties: false required: - index - type - content totalSteps: type: number totalToolCalls: type: number durationMs: type: number terminatedEarly: oneOf: - type: boolean enum: - false - type: boolean enum: - true error: type: string additionalProperties: false required: - id - input - finalOutput - steps - totalSteps - totalToolCalls - durationMs idealTrajectory: type: object properties: expectedSteps: type: number expectedToolCalls: type: number requiredTools: type: array items: type: string forbiddenTools: type: array items: type: string allowParallel: oneOf: - type: boolean enum: - false - type: boolean enum: - true maxRedundantSteps: type: number additionalProperties: false required: - expectedSteps - expectedToolCalls baseline: oneOf: - type: 'null' - type: object properties: behavior: oneOf: - type: string enum: - tool_use - type: string enum: - classification - type: string enum: - retrieval - type: string enum: - extraction - type: string enum: - multi_step_reasoning taskType: type: string stepDistribution: type: object properties: p50: type: number p75: type: number p90: type: number additionalProperties: false required: - p50 - p75 - p90 toolCallDistribution: type: object properties: p50: type: number p75: type: number additionalProperties: false required: - p50 - p75 durationDistribution: type: object properties: p50: type: number p75: type: number additionalProperties: false required: - p50 - p75 commonToolSequences: type: array items: type: array items: type: string redundancyProfile: type: object properties: mean: type: number p90: type: number additionalProperties: false required: - mean - p90 parallelToolGroups: type: array items: type: array items: type: string sampleSize: type: number updatedAt: type: string version: type: string model: type: string additionalProperties: false required: - behavior - stepDistribution - toolCallDistribution - durationDistribution - commonToolSequences - redundancyProfile - sampleSize - updatedAt evaluation: oneOf: - type: 'null' - type: object properties: schemaVersion: type: number trajectoryId: type: string behavior: oneOf: - type: string enum: - tool_use - type: string enum: - classification - type: string enum: - retrieval - type: string enum: - extraction - type: string enum: - multi_step_reasoning taskType: type: string valid: type: boolean score: oneOf: - type: 'null' - type: number baselineVersion: oneOf: - type: 'null' - type: string failureModes: type: array items: oneOf: - type: string enum: - inefficient_path - type: string enum: - unnecessary_tool_call - type: string enum: - missed_tool_call - type: string enum: - looping_behavior - type: string enum: - non_parallel_execution - type: string enum: - premature_termination metrics: oneOf: - type: 'null' - type: object properties: actualSteps: type: number actualToolCalls: type: number actualDurationMs: type: number redundancyRatio: type: number redundancySteps: type: number sequenceSimilarity: type: number efficiency: type: number toolUsage: type: number redundancy: type: number latency: type: number parallelizationPenalty: type: number parallelizationScore: type: number requiredToolsMissing: type: array items: type: string forbiddenToolsUsed: type: array items: type: string extraToolsUsed: type: array items: type: string selectedBaselineVersion: oneOf: - type: 'null' - type: string baselineStepP50: type: number baselineStepP75: type: number baselineToolCallP50: type: number baselineToolCallP75: type: number baselineDurationP50: type: number baselineDurationP75: type: number idealExpectedSteps: type: number idealExpectedToolCalls: type: number additionalProperties: false required: - actualSteps - actualToolCalls - actualDurationMs - redundancyRatio - redundancySteps - sequenceSimilarity - efficiency - toolUsage - redundancy - latency - parallelizationPenalty - parallelizationScore - requiredToolsMissing - forbiddenToolsUsed - extraToolsUsed additionalProperties: false required: - schemaVersion - valid - score - failureModes - metrics additionalProperties: false required: - testCaseId - status - trajectory trajectoryMetrics: oneOf: - type: 'null' - type: object properties: testCaseId: type: number status: oneOf: - type: string enum: - failed - type: string enum: - passed trajectoryId: type: string behavior: oneOf: - type: string enum: - tool_use - type: string enum: - classification - type: string enum: - retrieval - type: string enum: - extraction - type: string enum: - multi_step_reasoning taskType: type: string score: oneOf: - type: 'null' - type: number baselineVersion: oneOf: - type: 'null' - type: string failureModes: type: array items: oneOf: - type: string enum: - inefficient_path - type: string enum: - unnecessary_tool_call - type: string enum: - missed_tool_call - type: string enum: - looping_behavior - type: string enum: - non_parallel_execution - type: string enum: - premature_termination metrics: oneOf: - type: 'null' - type: object properties: actualSteps: type: number actualToolCalls: type: number actualDurationMs: type: number redundancyRatio: type: number redundancySteps: type: number sequenceSimilarity: type: number efficiency: type: number toolUsage: type: number redundancy: type: number latency: type: number parallelizationPenalty: type: number parallelizationScore: type: number requiredToolsMissing: type: array items: type: string forbiddenToolsUsed: type: array items: type: string extraToolsUsed: type: array items: type: string selectedBaselineVersion: oneOf: - type: 'null' - type: string baselineStepP50: type: number baselineStepP75: type: number baselineToolCallP50: type: number baselineToolCallP75: type: number baselineDurationP50: type: number baselineDurationP75: type: number idealExpectedSteps: type: number idealExpectedToolCalls: type: number additionalProperties: false required: - actualSteps - actualToolCalls - actualDurationMs - redundancyRatio - redundancySteps - sequenceSimilarity - efficiency - toolUsage - redundancy - latency - parallelizationPenalty - parallelizationScore - requiredToolsMissing - forbiddenToolsUsed - extraToolsUsed additionalProperties: false required: - testCaseId - status - score - failureModes - metrics additionalProperties: false required: - testCaseId - testResultId - systemVerdict - caseName - input - expectedOutput - output - error - assertions - messages - toolCalls - trajectory - trajectoryMetrics reviews: type: array items: type: object properties: id: type: number batchId: type: number sampleId: type: number testCaseId: type: number reviewerId: type: string systemVerdict: oneOf: - type: string enum: - pass - type: string enum: - fail reviewVerdict: oneOf: - type: string enum: - pass - type: string enum: - fail - type: string enum: - uncertain agreedWithSystem: oneOf: - type: 'null' - type: boolean enum: - false - type: boolean enum: - true rating: oneOf: - type: 'null' - type: number feedback: oneOf: - type: 'null' - type: string labels: oneOf: - type: 'null' - type: object additionalProperties: $ref: '#/components/schemas/JsonValue' createdAt: type: string additionalProperties: false required: - id - batchId - sampleId - testCaseId - reviewerId - systemVerdict - reviewVerdict - agreedWithSystem - rating - feedback - labels - createdAt latestReview: oneOf: - type: 'null' - type: object properties: id: type: number batchId: type: number sampleId: type: number testCaseId: type: number reviewerId: type: string systemVerdict: oneOf: - type: string enum: - pass - type: string enum: - fail reviewVerdict: oneOf: - type: string enum: - pass - type: string enum: - fail - type: string enum: - uncertain agreedWithSystem: oneOf: - type: 'null' - type: boolean enum: - false - type: boolean enum: - true rating: oneOf: - type: 'null' - type: number feedback: oneOf: - type: 'null' - type: string labels: oneOf: - type: 'null' - type: object additionalProperties: $ref: '#/components/schemas/JsonValue' createdAt: type: string additionalProperties: false required: - id - batchId - sampleId - testCaseId - reviewerId - systemVerdict - reviewVerdict - agreedWithSystem - rating - feedback - labels - createdAt additionalProperties: false required: - sampleId - testCaseId - testResultId - snapshot - reviews - latestReview stats: type: object properties: totalSamples: type: number reviewedSamples: type: number totalReviews: type: number comparableReviews: type: number agreementRate: oneOf: - type: 'null' - type: number disagreementRate: oneOf: - type: 'null' - type: number uncertainRate: oneOf: - type: 'null' - type: number verdictDistribution: type: object properties: pass: type: number fail: type: number uncertain: type: number additionalProperties: false required: - pass - fail - uncertain additionalProperties: false required: - totalSamples - reviewedSamples - totalReviews - comparableReviews - agreementRate - disagreementRate - uncertainRate - verdictDistribution history: type: array items: type: object properties: batchId: type: number createdAt: type: string totalReviews: type: number comparableReviews: type: number disagreementRate: oneOf: - type: 'null' - type: number additionalProperties: false required: - batchId - createdAt - totalReviews - comparableReviews - disagreementRate additionalProperties: false required: - batch - items - stats - history JsonValue: oneOf: - type: 'null' - type: boolean - type: number - type: string - type: array items: $ref: '#/components/schemas/JsonValue' - type: object additionalProperties: $ref: '#/components/schemas/JsonValue' ApiError: type: object properties: error: type: object properties: code: type: string enum: - UNAUTHORIZED - FORBIDDEN - NOT_FOUND - VALIDATION_ERROR - RATE_LIMITED - CONFLICT - INTERNAL_ERROR - SERVICE_UNAVAILABLE - QUOTA_EXCEEDED - NO_ORG_MEMBERSHIP - CROSS_ORG_REFERENCE - INCOMPLETE - MALFORMED message: type: string details: {} requestId: type: string format: uuid required: - code - message required: - error responses: ValidationError: description: Validation error content: application/json: schema: $ref: '#/components/schemas/ApiError' Unauthorized: description: Unauthorized content: application/json: schema: $ref: '#/components/schemas/ApiError' Forbidden: description: Forbidden content: application/json: schema: $ref: '#/components/schemas/ApiError' NotFound: description: Resource not found content: application/json: schema: $ref: '#/components/schemas/ApiError' Conflict: description: Conflict content: application/json: schema: $ref: '#/components/schemas/ApiError' RateLimited: description: Rate limit exceeded content: application/json: schema: $ref: '#/components/schemas/ApiError' InternalError: description: Internal server error content: application/json: schema: $ref: '#/components/schemas/ApiError' securitySchemes: bearerAuth: type: http scheme: bearer bearerFormat: API Key or Session Token ````