feat:Add endpoints and schemas to ElevenLabs OpenAPI (openapi.yaml)#169
Merged
feat:Add endpoints and schemas to ElevenLabs OpenAPI (openapi.yaml)#169
Conversation
WalkthroughAdds numerous REST endpoints and schema models to ElevenLabs OpenAPI for agent testing, conversations, knowledge base with RAG indexing, tools/agents management, MCP servers, batch calling/SIP, and various evaluation/metadata models. Changes are confined to schema and endpoint additions in src/libs/ElevenLabs/openapi.yaml. Changes
Sequence Diagram(s)sequenceDiagram
autonumber
participant Client
participant AgentTestingAPI as Agent Testing API
participant EvalEngine as Evaluation Engine
participant Store as Test Store
rect rgb(235, 245, 255)
note over Client,AgentTestingAPI: Create & manage tests (new)
Client->>AgentTestingAPI: POST /v1/convai/agent-testing/create
AgentTestingAPI->>Store: Persist Test Definition
Store-->>AgentTestingAPI: Test ID
AgentTestingAPI-->>Client: UnitTestRunResponseModel (id,status)
end
rect rgb(245, 235, 255)
note over Client,EvalEngine: Invocation & evaluation (new)
Client->>AgentTestingAPI: GET /v1/convai/test-invocations/{id}
AgentTestingAPI->>EvalEngine: Fetch Results/Evaluations
EvalEngine-->>AgentTestingAPI: Metrics, rationales
AgentTestingAPI-->>Client: Summary/Details
end
opt Update/Delete
Client->>AgentTestingAPI: PUT/DELETE /v1/convai/agent-testing/{test_id}
AgentTestingAPI->>Store: Update/Remove
Store-->>AgentTestingAPI: Ack
AgentTestingAPI-->>Client: 200/204
end
sequenceDiagram
autonumber
participant Client
participant KBAPI as Knowledge Base API
participant Indexer as RAG Indexer
participant Store as KB Store
Client->>KBAPI: POST /v1/convai/knowledge-base
KBAPI->>Store: Save Document
Store-->>KBAPI: Doc ID
KBAPI-->>Client: Document metadata
rect rgb(235, 255, 240)
note over Client,Indexer: RAG index operations (new)
Client->>KBAPI: POST /knowledge-base/{doc_id}/rag-index
KBAPI->>Indexer: Start Index Build
Indexer-->>KBAPI: Status (queued/running)
KBAPI-->>Client: Index status
Client->>KBAPI: GET /knowledge-base/{doc_id}/rag-index
KBAPI->>Indexer: Query Status
Indexer-->>KBAPI: Status/details
KBAPI-->>Client: Index info
end
sequenceDiagram
autonumber
participant Client
participant AgentsAPI as Agents API
participant Simulator as Conversation Simulator
Client->>AgentsAPI: POST /agents/{agent_id}/simulate-conversation
AgentsAPI->>Simulator: Run Simulation
Simulator-->>AgentsAPI: Transcript, metrics
AgentsAPI-->>Client: Simulation result
alt Stream
Client->>AgentsAPI: POST /agents/{agent_id}/simulate-conversation/stream
AgentsAPI-->>Client: Event stream (tokens/events)
end
Estimated code review effort🎯 4 (Complex) | ⏱️ ~60–90 minutes Poem
✨ Finishing Touches🧪 Generate unit tests
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. 🪧 TipsChatThere are 3 ways to chat with CodeRabbit:
SupportNeed help? Create a ticket on our support page for assistance with any issues or questions. CodeRabbit Commands (Invoked using PR/Issue comments)Type Other keywords and placeholders
CodeRabbit Configuration File (
|
![github-actions[bot]](https://avatars.githubusercontent.com/in/15368?s=60&v=4){kind=small}
coderabbitai
bot
changed the title
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 6
🧹 Nitpick comments (11)
src/libs/ElevenLabs/openapi.yaml (11)
6850-6882: Resubmit endpoint likely asynchronous; return 202 and drop empty bodyResubmission suggests an async re-queue. Prefer 202 Accepted with no response body for clarity.
- '200': - description: Successful Response - content: - application/json: - schema: { } + '202': + description: Accepted
10429-10439: AdhocAgentConfigOverrideForTestRequestModel: verify required fieldsBoth conversation_config and platform_settings are required. Is overriding platform settings always necessary for tests? If not, consider making it optional to reduce payload size.
- required: - - conversation_config - - platform_settings + required: + - conversation_config
10569-10583: Add constraints/examples to failure example textOptional, but adding minLength/maxLength and an example improves validation and SDK docs.
response: title: Response - type: string + type: string + minLength: 1 + maxLength: 2000 + example: "I cannot help with that request."
10662-10675: Mirror constraints on success exampleKeep symmetry with failure example.
response: title: Response - type: string + type: string + minLength: 1 + maxLength: 2000 + example: "Sure, here's how you can proceed..."
17079-17093: ExactParameterEvaluationStrategy only supports string; consider broader typesAgent tool parameters may be numeric/boolean. Support additional primitives.
- expected_value: - title: Expected Value - type: string - description: The exact string value that the parameter must match. + expected_value: + title: Expected Value + description: The exact value the parameter must match. + oneOf: + - type: string + - type: number + - type: integer + - type: boolean
18525-18541: created_at naming/time unit inconsistent with other modelsHere it's created_at (integer). Elsewhere you use created_at_unix_secs. Either rename for consistency (breaking) or document units.
created_at: title: Created At - type: integer + type: integer + description: Unix timestamp in seconds
19111-19125: Add basic constraints to LLMParameterEvaluationStrategy.descriptionPrevents unbounded payloads in requests.
description: title: Description type: string description: A description of the evaluation strategy to use for the test. + minLength: 1 + maxLength: 2000
22364-22376: ReferencedToolCommonModel: id should be non-emptyAdd minLength to prevent empty IDs.
id: title: Id type: string description: The ID of the tool + minLength: 1
22980-22988: SingleTestRunRequestModel: add example for test_idImproves SDK usability.
test_id: title: Test Id type: string description: ID of the test to run + example: "TeaqRRdTcIfIu2i7BYfT"
24326-24357: Statuses may need “running”/“canceled”; rationale structure is solidIf you plan to expose in-progress/canceled runs, add those statuses now to avoid breaking changes later. The rationale model looks good.
enum: - - pending - - passed - - failed + - pending + - running + - passed + - failed + - canceled
24872-24903: UnitTestRunResponseModel looks good; add example and clarify agent_responsesConsider noting that agent_responses may be omitted for failed early runs, and add an example object for SDKs.
UnitTestRunResponseModel: title: UnitTestRunResponseModel + example: + test_run_id: "run_abc123" + test_invocation_id: "inv_123" + agent_id: "21m00Tcm4TlvDq8ikWAM" + status: "passed" + test_id: "TeaqRRdTcIfIu2i7BYfT"
📜 Review details
Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro
💡 Knowledge Base configuration:
- MCP integration is disabled by default for public repositories
- Jira integration is disabled by default for public repositories
- Linear integration is disabled by default for public repositories
You can enable these sources in your CodeRabbit configuration.
⛔ Files ignored due to path filters (109)
src/libs/ElevenLabs/Generated/ElevenLabs..JsonSerializerContext.g.csis excluded by!**/generated/**src/libs/ElevenLabs/Generated/ElevenLabs.ElevenLabsClient.CreateConvaiAgentTestingCreate.g.csis excluded by!**/generated/**src/libs/ElevenLabs/Generated/ElevenLabs.ElevenLabsClient.CreateConvaiAgentTestingSummaries.g.csis excluded by!**/generated/**src/libs/ElevenLabs/Generated/ElevenLabs.ElevenLabsClient.CreateConvaiAgentsByAgentIdRunTests.g.csis excluded by!**/generated/**src/libs/ElevenLabs/Generated/ElevenLabs.ElevenLabsClient.CreateConvaiTestInvocationsByTestInvocationIdResubmit.g.csis excluded by!**/generated/**src/libs/ElevenLabs/Generated/ElevenLabs.ElevenLabsClient.DeleteConvaiAgentTestingByTestId.g.csis excluded by!**/generated/**src/libs/ElevenLabs/Generated/ElevenLabs.ElevenLabsClient.GetConvaiAgentTesting.g.csis excluded by!**/generated/**src/libs/ElevenLabs/Generated/ElevenLabs.ElevenLabsClient.GetConvaiAgentTestingByTestId.g.csis excluded by!**/generated/**src/libs/ElevenLabs/Generated/ElevenLabs.ElevenLabsClient.GetConvaiTestInvocationsByTestInvocationId.g.csis excluded by!**/generated/**src/libs/ElevenLabs/Generated/ElevenLabs.ElevenLabsClient.PutConvaiAgentTestingByTestId.g.csis excluded by!**/generated/**src/libs/ElevenLabs/Generated/ElevenLabs.IElevenLabsClient.CreateConvaiAgentTestingCreate.g.csis excluded by!**/generated/**src/libs/ElevenLabs/Generated/ElevenLabs.IElevenLabsClient.CreateConvaiAgentTestingSummaries.g.csis excluded by!**/generated/**src/libs/ElevenLabs/Generated/ElevenLabs.IElevenLabsClient.CreateConvaiAgentsByAgentIdRunTests.g.csis excluded by!**/generated/**src/libs/ElevenLabs/Generated/ElevenLabs.IElevenLabsClient.CreateConvaiTestInvocationsByTestInvocationIdResubmit.g.csis excluded by!**/generated/**src/libs/ElevenLabs/Generated/ElevenLabs.IElevenLabsClient.DeleteConvaiAgentTestingByTestId.g.csis excluded by!**/generated/**src/libs/ElevenLabs/Generated/ElevenLabs.IElevenLabsClient.GetConvaiAgentTesting.g.csis excluded by!**/generated/**src/libs/ElevenLabs/Generated/ElevenLabs.IElevenLabsClient.GetConvaiAgentTestingByTestId.g.csis excluded by!**/generated/**src/libs/ElevenLabs/Generated/ElevenLabs.IElevenLabsClient.GetConvaiTestInvocationsByTestInvocationId.g.csis excluded by!**/generated/**src/libs/ElevenLabs/Generated/ElevenLabs.IElevenLabsClient.GetDocs.g.csis excluded by!**/generated/**src/libs/ElevenLabs/Generated/ElevenLabs.IElevenLabsClient.PutConvaiAgentTestingByTestId.g.csis excluded by!**/generated/**src/libs/ElevenLabs/Generated/ElevenLabs.JsonConverters.AgentFailureResponseExampleType.g.csis excluded by!**/generated/**src/libs/ElevenLabs/Generated/ElevenLabs.JsonConverters.AgentFailureResponseExampleTypeNullable.g.csis excluded by!**/generated/**src/libs/ElevenLabs/Generated/ElevenLabs.JsonConverters.AgentSuccessfulResponseExampleType.g.csis excluded by!**/generated/**src/libs/ElevenLabs/Generated/ElevenLabs.JsonConverters.AgentSuccessfulResponseExampleTypeNullable.g.csis excluded by!**/generated/**src/libs/ElevenLabs/Generated/ElevenLabs.JsonConverters.Eval.g.csis excluded by!**/generated/**src/libs/ElevenLabs/Generated/ElevenLabs.JsonConverters.ExactParameterEvaluationStrategyType.g.csis excluded by!**/generated/**src/libs/ElevenLabs/Generated/ElevenLabs.JsonConverters.ExactParameterEvaluationStrategyTypeNullable.g.csis excluded by!**/generated/**src/libs/ElevenLabs/Generated/ElevenLabs.JsonConverters.LLMParameterEvaluationStrategyType.g.csis excluded by!**/generated/**src/libs/ElevenLabs/Generated/ElevenLabs.JsonConverters.LLMParameterEvaluationStrategyTypeNullable.g.csis excluded by!**/generated/**src/libs/ElevenLabs/Generated/ElevenLabs.JsonConverters.RegexParameterEvaluationStrategyType.g.csis excluded by!**/generated/**src/libs/ElevenLabs/Generated/ElevenLabs.JsonConverters.RegexParameterEvaluationStrategyTypeNullable.g.csis excluded by!**/generated/**src/libs/ElevenLabs/Generated/ElevenLabs.JsonConverters.TestRunStatus.g.csis excluded by!**/generated/**src/libs/ElevenLabs/Generated/ElevenLabs.JsonConverters.TestRunStatusNullable.g.csis excluded by!**/generated/**src/libs/ElevenLabs/Generated/ElevenLabs.JsonConverters.UnitTestToolCallParameterEvalDiscriminatorType.g.csis excluded by!**/generated/**src/libs/ElevenLabs/Generated/ElevenLabs.JsonConverters.UnitTestToolCallParameterEvalDiscriminatorTypeNullable.g.csis excluded by!**/generated/**src/libs/ElevenLabs/Generated/ElevenLabs.JsonSerializerContextTypes.g.csis excluded by!**/generated/**src/libs/ElevenLabs/Generated/ElevenLabs.Models.AdhocAgentConfigOverrideForTestRequestModel.Json.g.csis excluded by!**/generated/**src/libs/ElevenLabs/Generated/ElevenLabs.Models.AdhocAgentConfigOverrideForTestRequestModel.g.csis excluded by!**/generated/**src/libs/ElevenLabs/Generated/ElevenLabs.Models.AgentFailureResponseExample.Json.g.csis excluded by!**/generated/**src/libs/ElevenLabs/Generated/ElevenLabs.Models.AgentFailureResponseExample.g.csis excluded by!**/generated/**src/libs/ElevenLabs/Generated/ElevenLabs.Models.AgentFailureResponseExampleType.g.csis excluded by!**/generated/**src/libs/ElevenLabs/Generated/ElevenLabs.Models.AgentSuccessfulResponseExample.Json.g.csis excluded by!**/generated/**src/libs/ElevenLabs/Generated/ElevenLabs.Models.AgentSuccessfulResponseExample.g.csis excluded by!**/generated/**src/libs/ElevenLabs/Generated/ElevenLabs.Models.AgentSuccessfulResponseExampleType.g.csis excluded by!**/generated/**src/libs/ElevenLabs/Generated/ElevenLabs.Models.CreateUnitTestRequest.Json.g.csis excluded by!**/generated/**src/libs/ElevenLabs/Generated/ElevenLabs.Models.CreateUnitTestRequest.g.csis excluded by!**/generated/**src/libs/ElevenLabs/Generated/ElevenLabs.Models.CreateUnitTestRequestDynamicVariables.Json.g.csis excluded by!**/generated/**src/libs/ElevenLabs/Generated/ElevenLabs.Models.CreateUnitTestRequestDynamicVariables.g.csis excluded by!**/generated/**src/libs/ElevenLabs/Generated/ElevenLabs.Models.CreateUnitTestResponseModel.Json.g.csis excluded by!**/generated/**src/libs/ElevenLabs/Generated/ElevenLabs.Models.CreateUnitTestResponseModel.g.csis excluded by!**/generated/**src/libs/ElevenLabs/Generated/ElevenLabs.Models.DeleteChatResponseTestRouteResponse.Json.g.csis excluded by!**/generated/**src/libs/ElevenLabs/Generated/ElevenLabs.Models.DeleteChatResponseTestRouteResponse.g.csis excluded by!**/generated/**src/libs/ElevenLabs/Generated/ElevenLabs.Models.Eval.Json.g.csis excluded by!**/generated/**src/libs/ElevenLabs/Generated/ElevenLabs.Models.Eval.g.csis excluded by!**/generated/**src/libs/ElevenLabs/Generated/ElevenLabs.Models.ExactParameterEvaluationStrategy.Json.g.csis excluded by!**/generated/**src/libs/ElevenLabs/Generated/ElevenLabs.Models.ExactParameterEvaluationStrategy.g.csis excluded by!**/generated/**src/libs/ElevenLabs/Generated/ElevenLabs.Models.ExactParameterEvaluationStrategyType.g.csis excluded by!**/generated/**src/libs/ElevenLabs/Generated/ElevenLabs.Models.GetTestSuiteInvocationResponseModel.Json.g.csis excluded by!**/generated/**src/libs/ElevenLabs/Generated/ElevenLabs.Models.GetTestSuiteInvocationResponseModel.g.csis excluded by!**/generated/**src/libs/ElevenLabs/Generated/ElevenLabs.Models.GetTestsPageResponseModel.Json.g.csis excluded by!**/generated/**src/libs/ElevenLabs/Generated/ElevenLabs.Models.GetTestsPageResponseModel.g.csis excluded by!**/generated/**src/libs/ElevenLabs/Generated/ElevenLabs.Models.GetTestsSummariesByIdsResponseModel.Json.g.csis excluded by!**/generated/**src/libs/ElevenLabs/Generated/ElevenLabs.Models.GetTestsSummariesByIdsResponseModel.g.csis excluded by!**/generated/**src/libs/ElevenLabs/Generated/ElevenLabs.Models.GetTestsSummariesByIdsResponseModelTests.Json.g.csis excluded by!**/generated/**src/libs/ElevenLabs/Generated/ElevenLabs.Models.GetTestsSummariesByIdsResponseModelTests.g.csis excluded by!**/generated/**src/libs/ElevenLabs/Generated/ElevenLabs.Models.GetUnitTestResponseModel.Json.g.csis excluded by!**/generated/**src/libs/ElevenLabs/Generated/ElevenLabs.Models.GetUnitTestResponseModel.g.csis excluded by!**/generated/**src/libs/ElevenLabs/Generated/ElevenLabs.Models.GetUnitTestResponseModelDynamicVariables.Json.g.csis excluded by!**/generated/**src/libs/ElevenLabs/Generated/ElevenLabs.Models.GetUnitTestResponseModelDynamicVariables.g.csis excluded by!**/generated/**src/libs/ElevenLabs/Generated/ElevenLabs.Models.LLMParameterEvaluationStrategy.Json.g.csis excluded by!**/generated/**src/libs/ElevenLabs/Generated/ElevenLabs.Models.LLMParameterEvaluationStrategy.g.csis excluded by!**/generated/**src/libs/ElevenLabs/Generated/ElevenLabs.Models.LLMParameterEvaluationStrategyType.g.csis excluded by!**/generated/**src/libs/ElevenLabs/Generated/ElevenLabs.Models.ListTestsByIdsRequestModel.Json.g.csis excluded by!**/generated/**src/libs/ElevenLabs/Generated/ElevenLabs.Models.ListTestsByIdsRequestModel.g.csis excluded by!**/generated/**src/libs/ElevenLabs/Generated/ElevenLabs.Models.ReferencedToolCommonModel.Json.g.csis excluded by!**/generated/**src/libs/ElevenLabs/Generated/ElevenLabs.Models.ReferencedToolCommonModel.g.csis excluded by!**/generated/**src/libs/ElevenLabs/Generated/ElevenLabs.Models.RegexParameterEvaluationStrategy.Json.g.csis excluded by!**/generated/**src/libs/ElevenLabs/Generated/ElevenLabs.Models.RegexParameterEvaluationStrategy.g.csis excluded by!**/generated/**src/libs/ElevenLabs/Generated/ElevenLabs.Models.RegexParameterEvaluationStrategyType.g.csis excluded by!**/generated/**src/libs/ElevenLabs/Generated/ElevenLabs.Models.ResubmitTestsRequestModel.Json.g.csis excluded by!**/generated/**src/libs/ElevenLabs/Generated/ElevenLabs.Models.ResubmitTestsRequestModel.g.csis excluded by!**/generated/**src/libs/ElevenLabs/Generated/ElevenLabs.Models.ResubmitTestsRouteResponse.Json.g.csis excluded by!**/generated/**src/libs/ElevenLabs/Generated/ElevenLabs.Models.ResubmitTestsRouteResponse.g.csis excluded by!**/generated/**src/libs/ElevenLabs/Generated/ElevenLabs.Models.RunAgentTestsRequestModel.Json.g.csis excluded by!**/generated/**src/libs/ElevenLabs/Generated/ElevenLabs.Models.RunAgentTestsRequestModel.g.csis excluded by!**/generated/**src/libs/ElevenLabs/Generated/ElevenLabs.Models.SingleTestRunRequestModel.Json.g.csis excluded by!**/generated/**src/libs/ElevenLabs/Generated/ElevenLabs.Models.SingleTestRunRequestModel.g.csis excluded by!**/generated/**src/libs/ElevenLabs/Generated/ElevenLabs.Models.TestConditionRationaleCommonModel.Json.g.csis excluded by!**/generated/**src/libs/ElevenLabs/Generated/ElevenLabs.Models.TestConditionRationaleCommonModel.g.csis excluded by!**/generated/**src/libs/ElevenLabs/Generated/ElevenLabs.Models.TestConditionResultCommonModel.Json.g.csis excluded by!**/generated/**src/libs/ElevenLabs/Generated/ElevenLabs.Models.TestConditionResultCommonModel.g.csis excluded by!**/generated/**src/libs/ElevenLabs/Generated/ElevenLabs.Models.TestRunStatus.g.csis excluded by!**/generated/**src/libs/ElevenLabs/Generated/ElevenLabs.Models.UnitTestRunResponseModel.Json.g.csis excluded by!**/generated/**src/libs/ElevenLabs/Generated/ElevenLabs.Models.UnitTestRunResponseModel.g.csis excluded by!**/generated/**src/libs/ElevenLabs/Generated/ElevenLabs.Models.UnitTestSummaryResponseModel.Json.g.csis excluded by!**/generated/**src/libs/ElevenLabs/Generated/ElevenLabs.Models.UnitTestSummaryResponseModel.g.csis excluded by!**/generated/**src/libs/ElevenLabs/Generated/ElevenLabs.Models.UnitTestToolCallEvaluationModelInput.Json.g.csis excluded by!**/generated/**src/libs/ElevenLabs/Generated/ElevenLabs.Models.UnitTestToolCallEvaluationModelInput.g.csis excluded by!**/generated/**src/libs/ElevenLabs/Generated/ElevenLabs.Models.UnitTestToolCallEvaluationModelOutput.Json.g.csis excluded by!**/generated/**src/libs/ElevenLabs/Generated/ElevenLabs.Models.UnitTestToolCallEvaluationModelOutput.g.csis excluded by!**/generated/**src/libs/ElevenLabs/Generated/ElevenLabs.Models.UnitTestToolCallParameter.Json.g.csis excluded by!**/generated/**src/libs/ElevenLabs/Generated/ElevenLabs.Models.UnitTestToolCallParameter.g.csis excluded by!**/generated/**src/libs/ElevenLabs/Generated/ElevenLabs.Models.UnitTestToolCallParameterEvalDiscriminator.Json.g.csis excluded by!**/generated/**src/libs/ElevenLabs/Generated/ElevenLabs.Models.UnitTestToolCallParameterEvalDiscriminator.g.csis excluded by!**/generated/**src/libs/ElevenLabs/Generated/ElevenLabs.Models.UnitTestToolCallParameterEvalDiscriminatorType.g.csis excluded by!**/generated/**src/libs/ElevenLabs/Generated/ElevenLabs.Models.UpdateUnitTestRequest.Json.g.csis excluded by!**/generated/**src/libs/ElevenLabs/Generated/ElevenLabs.Models.UpdateUnitTestRequest.g.csis excluded by!**/generated/**src/libs/ElevenLabs/Generated/ElevenLabs.Models.UpdateUnitTestRequestDynamicVariables.Json.g.csis excluded by!**/generated/**src/libs/ElevenLabs/Generated/ElevenLabs.Models.UpdateUnitTestRequestDynamicVariables.g.csis excluded by!**/generated/**
📒 Files selected for processing (1)
src/libs/ElevenLabs/openapi.yaml(16 hunks)
🔇 Additional comments (2)
src/libs/ElevenLabs/openapi.yaml (2)
18543-18561: Pagination model looks goodtests + next_cursor + has_more matches the list endpoint’s query params.
22535-22555: ResubmitTestsRequestModel: consider 202 Accepted at endpoint and optional agent_config_overrideThe model is fine. Ensure the endpoint returns 202 (see earlier comment). Also, if agent_config_override is optional, clarify in docs that it overrides agent defaults only for resubmission.
Comment on lines
+6542
to
+6699
| /v1/convai/agent-testing/create: | ||
| post: | ||
| summary: Create Agent Response Test | ||
| description: Creates a new agent response test. | ||
| operationId: create_agent_response_test_route | ||
| parameters: | ||
| - name: xi-api-key | ||
| in: header | ||
| description: Your API key. This is required by most endpoints to access our API programatically. You can view your xi-api-key using the 'Profile' tab on the website. | ||
| schema: | ||
| title: Xi-Api-Key | ||
| type: string | ||
| description: Your API key. This is required by most endpoints to access our API programatically. You can view your xi-api-key using the 'Profile' tab on the website. | ||
| nullable: true | ||
| requestBody: | ||
| content: | ||
| application/json: | ||
| schema: | ||
| $ref: '#/components/schemas/CreateUnitTestRequest' | ||
| required: true | ||
| responses: | ||
| '200': | ||
| description: Successful Response | ||
| content: | ||
| application/json: | ||
| schema: | ||
| $ref: '#/components/schemas/CreateUnitTestResponseModel' | ||
| '422': | ||
| description: Validation Error | ||
| content: | ||
| application/json: | ||
| schema: | ||
| $ref: '#/components/schemas/HTTPValidationError' | ||
| '/v1/convai/agent-testing/{test_id}': | ||
| get: | ||
| summary: Get Agent Response Test By Id | ||
| description: Gets an agent response test by ID. | ||
| operationId: get_agent_response_test_route | ||
| parameters: | ||
| - name: test_id | ||
| in: path | ||
| description: The id of a chat response test. This is returned on test creation. | ||
| required: true | ||
| schema: | ||
| title: Test Id | ||
| type: string | ||
| description: The id of a chat response test. This is returned on test creation. | ||
| example: TeaqRRdTcIfIu2i7BYfT | ||
| - name: xi-api-key | ||
| in: header | ||
| description: Your API key. This is required by most endpoints to access our API programatically. You can view your xi-api-key using the 'Profile' tab on the website. | ||
| schema: | ||
| title: Xi-Api-Key | ||
| type: string | ||
| description: Your API key. This is required by most endpoints to access our API programatically. You can view your xi-api-key using the 'Profile' tab on the website. | ||
| nullable: true | ||
| responses: | ||
| '200': | ||
| description: Successful Response | ||
| content: | ||
| application/json: | ||
| schema: | ||
| $ref: '#/components/schemas/GetUnitTestResponseModel' | ||
| '422': | ||
| description: Validation Error | ||
| content: | ||
| application/json: | ||
| schema: | ||
| $ref: '#/components/schemas/HTTPValidationError' | ||
| put: | ||
| summary: Update Agent Response Test | ||
| description: Updates an agent response test by ID. | ||
| operationId: update_agent_response_test_route | ||
| parameters: | ||
| - name: test_id | ||
| in: path | ||
| description: The id of a chat response test. This is returned on test creation. | ||
| required: true | ||
| schema: | ||
| title: Test Id | ||
| type: string | ||
| description: The id of a chat response test. This is returned on test creation. | ||
| example: TeaqRRdTcIfIu2i7BYfT | ||
| - name: xi-api-key | ||
| in: header | ||
| description: Your API key. This is required by most endpoints to access our API programatically. You can view your xi-api-key using the 'Profile' tab on the website. | ||
| schema: | ||
| title: Xi-Api-Key | ||
| type: string | ||
| description: Your API key. This is required by most endpoints to access our API programatically. You can view your xi-api-key using the 'Profile' tab on the website. | ||
| nullable: true | ||
| requestBody: | ||
| content: | ||
| application/json: | ||
| schema: | ||
| $ref: '#/components/schemas/UpdateUnitTestRequest' | ||
| required: true | ||
| responses: | ||
| '200': | ||
| description: Successful Response | ||
| content: | ||
| application/json: | ||
| schema: | ||
| $ref: '#/components/schemas/GetUnitTestResponseModel' | ||
| '422': | ||
| description: Validation Error | ||
| content: | ||
| application/json: | ||
| schema: | ||
| $ref: '#/components/schemas/HTTPValidationError' | ||
| delete: | ||
| summary: Delete Agent Response Test | ||
| description: Deletes an agent response test by ID. | ||
| operationId: delete_chat_response_test_route | ||
| parameters: | ||
| - name: test_id | ||
| in: path | ||
| description: The id of a chat response test. This is returned on test creation. | ||
| required: true | ||
| schema: | ||
| title: Test Id | ||
| type: string | ||
| description: The id of a chat response test. This is returned on test creation. | ||
| example: TeaqRRdTcIfIu2i7BYfT | ||
| - name: xi-api-key | ||
| in: header | ||
| description: Your API key. This is required by most endpoints to access our API programatically. You can view your xi-api-key using the 'Profile' tab on the website. | ||
| schema: | ||
| title: Xi-Api-Key | ||
| type: string | ||
| description: Your API key. This is required by most endpoints to access our API programatically. You can view your xi-api-key using the 'Profile' tab on the website. | ||
| nullable: true | ||
| responses: | ||
| '200': | ||
| description: Successful Response | ||
| content: | ||
| application/json: | ||
| schema: { } | ||
| '422': | ||
| description: Validation Error | ||
| content: | ||
| application/json: | ||
| schema: | ||
| $ref: '#/components/schemas/HTTPValidationError' | ||
| /v1/convai/agent-testing/summaries: | ||
| post: | ||
| summary: Get Agent Response Test Summaries By Ids | ||
| description: Gets multiple agent response tests by their IDs. Returns a dictionary mapping test IDs to test summaries. | ||
| operationId: get_agent_response_tests_summaries_route | ||
| parameters: | ||
| - name: xi-api-key | ||
| in: header | ||
| description: Your API key. This is required by most endpoints to access our API programatically. You can view your xi-api-key using the 'Profile' tab on the website. | ||
| schema: | ||
| title: Xi-Api-Key | ||
| type: string | ||
| description: Your API key. This is required by most endpoints to access our API programatically. You can view your xi-api-key using the 'Profile' tab on the website. | ||
| nullable: true |
There was a problem hiding this comment.
💡 Verification agent
🧩 Analysis chain
Inconsistent operationIds and suboptimal status codes for create/delete; consider security reuse and tagging
- operationId naming mixes "agent" and "chat": list and delete use list_chat_response_tests_route/delete_chat_response_test_route while others use agent_*; unify for SDKs.
- Use 201 for create and 204 for delete (no body). Current 200 + empty schema is less idiomatic.
- Header parameter xi-api-key is copy-pasted per operation and marked nullable: true though described as required; prefer a reusable components/parameters or securitySchemes entry and mark it required consistently.
- Methods lack tags while nearby paths are tagged; add tags for grouping and codegen.
Apply targeted diffs:
- operationId: list_chat_response_tests_route
+ operationId: list_agent_response_tests_route- operationId: delete_chat_response_test_route
+ operationId: delete_agent_response_test_route- '200':
- description: Successful Response
+ '201':
+ description: Created- '200':
- description: Successful Response
- content:
- application/json:
- schema: { }
+ '204':
+ description: No ContentOptionally add tags and reuse the API key header:
post:
+ tags:
+ - conversational_ai
+ - agent_testingProposed shared header/ security (outside this hunk):
components:
securitySchemes:
XiApiKey:
type: apiKey
in: header
name: xi-api-key
security:
- XiApiKey: []Then remove per-endpoint xi-api-key parameters. Do you want me to generate a follow-up PR to consolidate these?
Run to spot remaining chat_* operationIds and missing tags:
🏁 Script executed:
#!/bin/bash
rg -n "operationId:\s*(get|list|delete|update|create)_chat_response_test" -n
rg -nP "(?s)^\s*/v1/convai/agent-testing.*?\n\s{2}(get|post|put|delete):\n(?!\s{4}tags:)" -nLength of output: 350
🏁 Script executed:
#!/bin/bash
# 1. Check occurrences of xi-api-key parameters (to verify if 'required' is missing)
echo "== xi-api-key parameter usage =="
rg -n "name:\s*xi-api-key" -n src/libs/ElevenLabs/openapi.yaml -C3 | head -n 20
# 2. Look for a shared XiApiKey security scheme in components
echo
echo "== XiApiKey security scheme =="
rg -n "XiApiKey" -n src/libs/ElevenLabs/openapi.yaml
# 3. Locate any securitySchemes definitions under components
echo
echo "== components.securitySchemes definitions =="
rg -nP "^\s*securitySchemes:" -n src/libs/ElevenLabs/openapi.yaml -C5
# 4. Inspect tags usage across the file to see existing grouping
echo
echo "== First tags occurrences =="
rg -n "tags:" -n src/libs/ElevenLabs/openapi.yaml | head -n 30Length of output: 2546
Consistent operationIds, RESTful status codes, and security reuse; add missing tags
• File: src/libs/ElevenLabs/openapi.yaml Lines 6542–6699
• Rename list_chat_response_tests_route → list_agent_response_tests_route and delete_chat_response_test_route → delete_agent_response_test_route for uniform agent_* naming.
• Change POST /v1/convai/agent-testing/create response from 200 → 201 (Created).
• Change DELETE /v1/convai/agent-testing/{test_id} response from 200 with empty body → 204 (No Content).
• Remove per-operation xi-api-key header parameters and rely on existing global components.securitySchemes.ApiKeyAuth + top-level security: block.
• Add tags under each operation (e.g. tags: [conversational_ai, agent_testing]) for grouping and codegen.
Proposed diffs:
--- a/src/libs/ElevenLabs/openapi.yaml
+++ b/src/libs/ElevenLabs/openapi.yaml
@@ -6545,8 +6545,12 @@
/v1/convai/agent-testing/create:
- post:
- operationId: create_agent_response_test_route
+ post:
+ tags:
+ - conversational_ai
+ - agent_testing
+ operationId: create_agent_response_test_route
summary: Create Agent Response Test
description: Creates a new agent response test.
requestBody:
@@ -6556,7 +6560,7 @@
responses:
- '200':
+ '201':
description: Created
content:
application/json:
@@ -6660,8 +6664,12 @@
'/v1/convai/agent-testing/{test_id}':
delete:
- operationId: delete_chat_response_test_route
+ tags:
+ - conversational_ai
+ - agent_testing
+ operationId: delete_agent_response_test_route
summary: Delete Agent Response Test
description: Deletes an agent response test by ID.
responses:
@@ -6671,10 +6679,7 @@
- '200':
- description: Successful Response
- content:
- application/json:
- schema: { }
+ '204':
+ description: No Content
'422':
description: Validation Error
content:
@@ -6720,7 +6725,11 @@
/v1/convai/agent-testing:
get:
- operationId: list_chat_response_tests_route
+ tags:
+ - conversational_ai
+ - agent_testing
+ operationId: list_agent_response_tests_route
summary: List Agent Response Tests
description: Retrieves a list of agent response tests.
responses:
@@ -6745,6 +6754,10 @@
/v1/convai/agent-testing/summaries:
post:
+ tags:
+ - conversational_ai
+ - agent_testing
operationId: get_agent_response_tests_summaries_route
summary: Get Agent Response Test Summaries By Ids
description: Gets multiple agent response tests by their IDs.
@@ -6545,17 +6558,4 @@
- parameters:
- - name: xi-api-key
- in: header
- description: Your API key…
- schema:
- type: string
- nullable: true
- …
- (remove this block from each operation under `/v1/convai/agent-testing/*`)These adjustments will:
- Ensure consistent SDK-friendly operation IDs
- Adopt idiomatic HTTP status codes
- Consolidate API-key handling via the existing
ApiKeyAuthscheme (no new definitions required) - Provide tags for grouping in generated clients
Let me know if you’d like me to prepare a follow-up PR with these refactors.
Committable suggestion skipped: line range outside the PR's diff.
Comment on lines
16146
to
+16154
| sid: | ||
| title: Sid | ||
| type: string | ||
| description: Twilio Account SID | ||
| token: | ||
| title: Token | ||
| description: Twilio Account SID | ||
| token: | ||
| title: Token | ||
| type: string | ||
| description: Twilio Auth Token | ||
| CreateUnitTestRequest: |
There was a problem hiding this comment.
Sensitive Twilio token should be writeOnly
Avoid echoing secrets in generated SDKs and UIs.
token:
title: Token
type: string
description: Twilio Auth Token
+ writeOnly: true📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
Suggested change
| sid: | |
| title: Sid | |
| type: string | |
| description: Twilio Account SID | |
| token: | |
| title: Token | |
| description: Twilio Account SID | |
| token: | |
| title: Token | |
| type: string | |
| description: Twilio Auth Token | |
| CreateUnitTestRequest: | |
| sid: | |
| title: Sid | |
| type: string | |
| description: Twilio Account SID | |
| token: | |
| title: Token | |
| type: string | |
| description: Twilio Auth Token | |
| writeOnly: true | |
| CreateUnitTestRequest: |
🤖 Prompt for AI Agents
In src/libs/ElevenLabs/openapi.yaml around lines 16146 to 16154, the Twilio
token property is currently exposed as a plain string; update the schema so the
token field is marked writeOnly: true (and optionally format: password) to
prevent it from being echoed in generated SDKs and UIs, and keep or adjust the
description to indicate it is sensitive and not returned in responses.
Comment on lines
+16155
to
+16207
| title: CreateUnitTestRequest | ||
| required: | ||
| - chat_history | ||
| - success_condition | ||
| - success_examples | ||
| - failure_examples | ||
| - name | ||
| type: object | ||
| properties: | ||
| chat_history: | ||
| title: Chat History | ||
| maxItems: 50 | ||
| minItems: 1 | ||
| type: array | ||
| items: | ||
| $ref: '#/components/schemas/ConversationHistoryTranscriptCommonModel-Input' | ||
| success_condition: | ||
| title: Success Condition | ||
| type: string | ||
| description: A prompt that evaluates whether the agent's response is successful. Should return True or False. | ||
| success_examples: | ||
| title: Success Examples | ||
| maxItems: 5 | ||
| minItems: 0 | ||
| type: array | ||
| items: | ||
| $ref: '#/components/schemas/AgentSuccessfulResponseExample' | ||
| description: Non-empty list of example responses that should be considered successful | ||
| failure_examples: | ||
| title: Failure Examples | ||
| maxItems: 5 | ||
| minItems: 0 | ||
| type: array | ||
| items: | ||
| $ref: '#/components/schemas/AgentFailureResponseExample' | ||
| description: Non-empty list of example responses that should be considered failures | ||
| tool_call_parameters: | ||
| $ref: '#/components/schemas/UnitTestToolCallEvaluationModel-Input' | ||
| dynamic_variables: | ||
| title: Dynamic Variables | ||
| type: object | ||
| additionalProperties: | ||
| anyOf: | ||
| - type: string | ||
| - type: number | ||
| - type: integer | ||
| - type: boolean | ||
| nullable: true | ||
| description: Dynamic variables to replace in the agent config during testing | ||
| name: | ||
| title: Name | ||
| type: string | ||
| CreateUnitTestResponseModel: |
There was a problem hiding this comment.
💡 Verification agent
❓ Verification inconclusive
success_examples/failure_examples contradict minItems 0 vs “Non-empty list”
Descriptions say non-empty but minItems is 0. Enforce minItems: 1 or relax the description.
success_examples:
title: Success Examples
maxItems: 5
- minItems: 0
+ minItems: 1
...
failure_examples:
title: Failure Examples
maxItems: 5
- minItems: 0
+ minItems: 1If zero is allowed, change descriptions to remove “Non-empty”.
Ensure consistency between array constraints and descriptions
The success_examples and failure_examples properties declare “Non-empty list…” in their descriptions but allow empty arrays via minItems: 0. Please update these to enforce minItems: 1 (or, if empty lists are intended, revise the descriptions to remove “Non-empty”).
Locations to update:
- src/libs/ElevenLabs/openapi.yaml —
CreateUnitTestRequest.properties.success_examples - src/libs/ElevenLabs/openapi.yaml —
CreateUnitTestRequest.properties.failure_examples
Suggested diff:
success_examples:
title: Success Examples
maxItems: 5
- minItems: 0
+ minItems: 1
type: array
items:
$ref: '#/components/schemas/AgentSuccessfulResponseExample'
description: Non-empty list of example responses that should be considered successful
failure_examples:
title: Failure Examples
maxItems: 5
- minItems: 0
+ minItems: 1
type: array
items:
$ref: '#/components/schemas/AgentFailureResponseExample'
description: Non-empty list of example responses that should be considered failures📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
Suggested change
| title: CreateUnitTestRequest | |
| required: | |
| - chat_history | |
| - success_condition | |
| - success_examples | |
| - failure_examples | |
| - name | |
| type: object | |
| properties: | |
| chat_history: | |
| title: Chat History | |
| maxItems: 50 | |
| minItems: 1 | |
| type: array | |
| items: | |
| $ref: '#/components/schemas/ConversationHistoryTranscriptCommonModel-Input' | |
| success_condition: | |
| title: Success Condition | |
| type: string | |
| description: A prompt that evaluates whether the agent's response is successful. Should return True or False. | |
| success_examples: | |
| title: Success Examples | |
| maxItems: 5 | |
| minItems: 0 | |
| type: array | |
| items: | |
| $ref: '#/components/schemas/AgentSuccessfulResponseExample' | |
| description: Non-empty list of example responses that should be considered successful | |
| failure_examples: | |
| title: Failure Examples | |
| maxItems: 5 | |
| minItems: 0 | |
| type: array | |
| items: | |
| $ref: '#/components/schemas/AgentFailureResponseExample' | |
| description: Non-empty list of example responses that should be considered failures | |
| tool_call_parameters: | |
| $ref: '#/components/schemas/UnitTestToolCallEvaluationModel-Input' | |
| dynamic_variables: | |
| title: Dynamic Variables | |
| type: object | |
| additionalProperties: | |
| anyOf: | |
| - type: string | |
| - type: number | |
| - type: integer | |
| - type: boolean | |
| nullable: true | |
| description: Dynamic variables to replace in the agent config during testing | |
| name: | |
| title: Name | |
| type: string | |
| CreateUnitTestResponseModel: | |
| properties: | |
| chat_history: | |
| title: Chat History | |
| maxItems: 50 | |
| minItems: 1 | |
| type: array | |
| items: | |
| $ref: '#/components/schemas/ConversationHistoryTranscriptCommonModel-Input' | |
| success_condition: | |
| title: Success Condition | |
| type: string | |
| description: A prompt that evaluates whether the agent's response is successful. Should return True or False. | |
| success_examples: | |
| title: Success Examples | |
| maxItems: 5 | |
| minItems: 1 | |
| type: array | |
| items: | |
| $ref: '#/components/schemas/AgentSuccessfulResponseExample' | |
| description: Non-empty list of example responses that should be considered successful | |
| failure_examples: | |
| title: Failure Examples | |
| maxItems: 5 | |
| minItems: 1 | |
| type: array | |
| items: | |
| $ref: '#/components/schemas/AgentFailureResponseExample' | |
| description: Non-empty list of example responses that should be considered failures | |
| tool_call_parameters: | |
| $ref: '#/components/schemas/UnitTestToolCallEvaluationModel-Input' | |
| dynamic_variables: | |
| title: Dynamic Variables | |
| type: object | |
| additionalProperties: | |
| anyOf: | |
| - type: string | |
| - type: number | |
| - type: integer | |
| - type: boolean | |
| nullable: true | |
| description: Dynamic variables to replace in the agent config during testing | |
| name: | |
| title: Name | |
| type: string |
🤖 Prompt for AI Agents
In src/libs/ElevenLabs/openapi.yaml around lines 16155 to 16207, the
success_examples and failure_examples descriptions say “Non-empty list…” but
both use minItems: 0; update each schema to set minItems: 1 to enforce non-empty
arrays (leave the descriptions unchanged), and ensure the OpenAPI file remains
valid after the change.
Comment on lines
+18600
to
+18636
| title: GetUnitTestResponseModel | ||
| required: | ||
| - chat_history | ||
| - success_condition | ||
| - success_examples | ||
| - failure_examples | ||
| - id | ||
| - name | ||
| type: object | ||
| properties: | ||
| chat_history: | ||
| title: Chat History | ||
| maxItems: 50 | ||
| minItems: 1 | ||
| type: array | ||
| items: | ||
| $ref: '#/components/schemas/ConversationHistoryTranscriptCommonModel-Output' | ||
| success_condition: | ||
| title: Success Condition | ||
| type: string | ||
| description: A prompt that evaluates whether the agent's response is successful. Should return True or False. | ||
| success_examples: | ||
| title: Success Examples | ||
| maxItems: 5 | ||
| minItems: 0 | ||
| type: array | ||
| items: | ||
| $ref: '#/components/schemas/AgentSuccessfulResponseExample' | ||
| description: Non-empty list of example responses that should be considered successful | ||
| failure_examples: | ||
| title: Failure Examples | ||
| maxItems: 5 | ||
| minItems: 0 | ||
| type: array | ||
| items: | ||
| $ref: '#/components/schemas/AgentFailureResponseExample' | ||
| description: Non-empty list of example responses that should be considered failures |
There was a problem hiding this comment.
Same minItems inconsistency on the GET model
Descriptions say “Non-empty” but minItems is 0. Align with Create model.
success_examples:
title: Success Examples
maxItems: 5
- minItems: 0
+ minItems: 1
...
failure_examples:
title: Failure Examples
maxItems: 5
- minItems: 0
+ minItems: 1📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
Suggested change
| title: GetUnitTestResponseModel | |
| required: | |
| - chat_history | |
| - success_condition | |
| - success_examples | |
| - failure_examples | |
| - id | |
| - name | |
| type: object | |
| properties: | |
| chat_history: | |
| title: Chat History | |
| maxItems: 50 | |
| minItems: 1 | |
| type: array | |
| items: | |
| $ref: '#/components/schemas/ConversationHistoryTranscriptCommonModel-Output' | |
| success_condition: | |
| title: Success Condition | |
| type: string | |
| description: A prompt that evaluates whether the agent's response is successful. Should return True or False. | |
| success_examples: | |
| title: Success Examples | |
| maxItems: 5 | |
| minItems: 0 | |
| type: array | |
| items: | |
| $ref: '#/components/schemas/AgentSuccessfulResponseExample' | |
| description: Non-empty list of example responses that should be considered successful | |
| failure_examples: | |
| title: Failure Examples | |
| maxItems: 5 | |
| minItems: 0 | |
| type: array | |
| items: | |
| $ref: '#/components/schemas/AgentFailureResponseExample' | |
| description: Non-empty list of example responses that should be considered failures | |
| success_examples: | |
| title: Success Examples | |
| maxItems: 5 | |
| minItems: 1 | |
| type: array | |
| items: | |
| $ref: '#/components/schemas/AgentSuccessfulResponseExample' | |
| description: Non-empty list of example responses that should be considered successful | |
| failure_examples: | |
| title: Failure Examples | |
| maxItems: 5 | |
| minItems: 1 | |
| type: array | |
| items: | |
| $ref: '#/components/schemas/AgentFailureResponseExample' | |
| description: Non-empty list of example responses that should be considered failures |
🤖 Prompt for AI Agents
In src/libs/ElevenLabs/openapi.yaml around lines 18600 to 18636, the GET
response schema lists success_examples and failure_examples with descriptions
stating "Non-empty list" but sets minItems: 0; update both
success_examples.minItems and failure_examples.minItems to 1 to align with the
description and the Create model (leave maxItems: 5 and other properties
unchanged).
Comment on lines
+19555
to
+19568
| title: ListTestsByIdsRequestModel | ||
| required: | ||
| - test_ids | ||
| type: object | ||
| properties: | ||
| test_ids: | ||
| title: Test Ids | ||
| type: array | ||
| items: | ||
| type: string | ||
| description: List of test IDs to fetch. No duplicates allowed. | ||
| example: | ||
| - test_id_1 | ||
| - test_id_2 |
There was a problem hiding this comment.
🛠️ Refactor suggestion
Enforce uniqueness of test_ids
The description says “No duplicates allowed” but schema doesn’t enforce it. Add uniqueItems: true.
test_ids:
title: Test Ids
type: array
+ uniqueItems: true
items:
type: string📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
Suggested change
| title: ListTestsByIdsRequestModel | |
| required: | |
| - test_ids | |
| type: object | |
| properties: | |
| test_ids: | |
| title: Test Ids | |
| type: array | |
| items: | |
| type: string | |
| description: List of test IDs to fetch. No duplicates allowed. | |
| example: | |
| - test_id_1 | |
| - test_id_2 | |
| title: ListTestsByIdsRequestModel | |
| required: | |
| - test_ids | |
| type: object | |
| properties: | |
| test_ids: | |
| title: Test Ids | |
| type: array | |
| uniqueItems: true | |
| items: | |
| type: string | |
| description: List of test IDs to fetch. No duplicates allowed. | |
| example: | |
| - test_id_1 | |
| - test_id_2 |
🤖 Prompt for AI Agents
In src/libs/ElevenLabs/openapi.yaml around lines 19555 to 19568 the
ListTestsByIdsRequestModel declares test_ids with description "No duplicates
allowed" but does not enforce it; add uniqueItems: true under the test_ids array
property (alongside type: array and items) to enforce uniqueness in the schema.
Comment on lines
+24989
to
25041
| title: UpdateUnitTestRequest | ||
| required: | ||
| - chat_history | ||
| - success_condition | ||
| - success_examples | ||
| - failure_examples | ||
| - name | ||
| type: object | ||
| properties: | ||
| chat_history: | ||
| title: Chat History | ||
| maxItems: 50 | ||
| minItems: 1 | ||
| type: array | ||
| items: | ||
| $ref: '#/components/schemas/ConversationHistoryTranscriptCommonModel-Input' | ||
| success_condition: | ||
| title: Success Condition | ||
| type: string | ||
| description: A prompt that evaluates whether the agent's response is successful. Should return True or False. | ||
| success_examples: | ||
| title: Success Examples | ||
| maxItems: 5 | ||
| minItems: 0 | ||
| type: array | ||
| items: | ||
| $ref: '#/components/schemas/AgentSuccessfulResponseExample' | ||
| description: Non-empty list of example responses that should be considered successful | ||
| failure_examples: | ||
| title: Failure Examples | ||
| maxItems: 5 | ||
| minItems: 0 | ||
| type: array | ||
| items: | ||
| $ref: '#/components/schemas/AgentFailureResponseExample' | ||
| description: Non-empty list of example responses that should be considered failures | ||
| tool_call_parameters: | ||
| $ref: '#/components/schemas/UnitTestToolCallEvaluationModel-Input' | ||
| dynamic_variables: | ||
| title: Dynamic Variables | ||
| type: object | ||
| additionalProperties: | ||
| anyOf: | ||
| - type: string | ||
| - type: number | ||
| - type: integer | ||
| - type: boolean | ||
| nullable: true | ||
| description: Dynamic variables to replace in the agent config during testing | ||
| name: | ||
| title: Name | ||
| type: string | ||
| UpdateWorkspaceMemberResponseModel: |
There was a problem hiding this comment.
UpdateUnitTestRequest: same minItems inconsistency; align with Create
Mirror the fixes suggested for Create model.
success_examples:
title: Success Examples
maxItems: 5
- minItems: 0
+ minItems: 1
...
failure_examples:
title: Failure Examples
maxItems: 5
- minItems: 0
+ minItems: 1📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
Suggested change
| title: UpdateUnitTestRequest | |
| required: | |
| - chat_history | |
| - success_condition | |
| - success_examples | |
| - failure_examples | |
| - name | |
| type: object | |
| properties: | |
| chat_history: | |
| title: Chat History | |
| maxItems: 50 | |
| minItems: 1 | |
| type: array | |
| items: | |
| $ref: '#/components/schemas/ConversationHistoryTranscriptCommonModel-Input' | |
| success_condition: | |
| title: Success Condition | |
| type: string | |
| description: A prompt that evaluates whether the agent's response is successful. Should return True or False. | |
| success_examples: | |
| title: Success Examples | |
| maxItems: 5 | |
| minItems: 0 | |
| type: array | |
| items: | |
| $ref: '#/components/schemas/AgentSuccessfulResponseExample' | |
| description: Non-empty list of example responses that should be considered successful | |
| failure_examples: | |
| title: Failure Examples | |
| maxItems: 5 | |
| minItems: 0 | |
| type: array | |
| items: | |
| $ref: '#/components/schemas/AgentFailureResponseExample' | |
| description: Non-empty list of example responses that should be considered failures | |
| tool_call_parameters: | |
| $ref: '#/components/schemas/UnitTestToolCallEvaluationModel-Input' | |
| dynamic_variables: | |
| title: Dynamic Variables | |
| type: object | |
| additionalProperties: | |
| anyOf: | |
| - type: string | |
| - type: number | |
| - type: integer | |
| - type: boolean | |
| nullable: true | |
| description: Dynamic variables to replace in the agent config during testing | |
| name: | |
| title: Name | |
| type: string | |
| UpdateWorkspaceMemberResponseModel: | |
| success_examples: | |
| title: Success Examples | |
| maxItems: 5 | |
| minItems: 1 | |
| type: array | |
| items: | |
| $ref: '#/components/schemas/AgentSuccessfulResponseExample' | |
| description: Non-empty list of example responses that should be considered successful | |
| failure_examples: | |
| title: Failure Examples | |
| maxItems: 5 | |
| minItems: 1 | |
| type: array | |
| items: | |
| $ref: '#/components/schemas/AgentFailureResponseExample' | |
| description: Non-empty list of example responses that should be considered failures |
🤖 Prompt for AI Agents
In src/libs/ElevenLabs/openapi.yaml around lines 24989 to 25041, the
UpdateUnitTestRequest schema has minItems: 0 for success_examples and
failure_examples while their descriptions state they should be non-empty; mirror
the Create model fix by changing those minItems to 1 (making them required to be
non-empty) and ensure the schema and description are consistent.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary by CodeRabbit