Skip to content

Document LLM Observability LLM provider integration endpoints #4219

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
api-clients-generation-pipeline merged 1 commit into from
May 21, 2026
Merged

Document LLM Observability LLM provider integration endpoints #4219

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
870 changes: 870 additions & 0 deletions .generator/schemas/v2/openapi.yaml
View file
Open in desktop

Large diffs are not rendered by default.

54 changes: 54 additions & 0 deletions features/v2/llm_observability.feature
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -588,6 +588,40 @@ Feature: LLM Observability
When the request is sent
Then the response status is 200 OK

@generated @skip @team:DataDog/ml-observability
Scenario: List LLM integration accounts returns "Bad Request" response
Given operation "ListLLMObsIntegrationAccounts" enabled
And new "ListLLMObsIntegrationAccounts" request
And request contains "integration" parameter from "REPLACE.ME"
When the request is sent
Then the response status is 400 Bad Request

@generated @skip @team:DataDog/ml-observability
Scenario: List LLM integration accounts returns "OK" response
Given operation "ListLLMObsIntegrationAccounts" enabled
And new "ListLLMObsIntegrationAccounts" request
And request contains "integration" parameter from "REPLACE.ME"
When the request is sent
Then the response status is 200 OK

@generated @skip @team:DataDog/ml-observability
Scenario: List LLM integration models returns "Bad Request" response
Given operation "ListLLMObsIntegrationModels" enabled
And new "ListLLMObsIntegrationModels" request
And request contains "integration" parameter from "REPLACE.ME"
And request contains "account_id" parameter from "REPLACE.ME"
When the request is sent
Then the response status is 400 Bad Request

@generated @skip @team:DataDog/ml-observability
Scenario: List LLM integration models returns "OK" response
Given operation "ListLLMObsIntegrationModels" enabled
And new "ListLLMObsIntegrationModels" request
And request contains "integration" parameter from "REPLACE.ME"
And request contains "account_id" parameter from "REPLACE.ME"
When the request is sent
Then the response status is 200 OK

@generated @skip @team:DataDog/ml-observability
Scenario: List events for an LLM Observability experiment returns "Bad Request" response
Given operation "ListLLMObsExperimentEvents" enabled
Expand Down Expand Up @@ -639,6 +673,26 @@ Feature: LLM Observability
When the request is sent
Then the response status is 404 Not Found

@generated @skip @team:DataDog/ml-observability
Scenario: Run an LLM inference returns "Bad Request" response
Given operation "CreateLLMObsIntegrationInference" enabled
And new "CreateLLMObsIntegrationInference" request
And request contains "integration" parameter from "REPLACE.ME"
And request contains "account_id" parameter from "REPLACE.ME"
And body with value {"anthropic_metadata": {"effort": "medium", "thinking": {"budget_tokens": 1024, "type": "enabled"}}, "azure_openai_metadata": {"deployment_id": "my-gpt4-deployment", "model_version": "0613", "resource_name": "my-azure-resource"}, "bedrock_metadata": {"region": "us-east-1"}, "frequency_penalty": 0.0, "json_schema": "{\"type\":\"object\",\"properties\":{\"answer\":{\"type\":\"string\"}}}", "max_completion_tokens": 1024, "max_tokens": 1024, "messages": [{"content": "What is the capital of France?", "contents": [{"type": "text", "value": {"text": "Hello, how can I help you?", "tool_call": {"arguments": {"location": "San Francisco"}, "name": "get_weather", "tool_id": "call_abc123", "type": "function"}, "tool_call_result": {"name": "get_weather", "result": "The weather in San Francisco is 68\u00b0F and sunny.", "tool_id": "call_abc123", "type": "function"}}}], "id": "msg_001", "role": "user", "tool_calls": [{"arguments": {"location": "San Francisco"}, "name": "get_weather", "tool_id": "call_abc123", "type": "function"}], "tool_results": [{"name": "get_weather", "result": "The weather in San Francisco is 68\u00b0F and sunny.", "tool_id": "call_abc123", "type": "function"}]}], "model_id": "gpt-4o", "openai_metadata": {"reasoning_effort": "medium", "reasoning_summary": "auto"}, "presence_penalty": 0.0, "temperature": 0.7, "tools": [{"function": {"description": "Get the current weather for a location.", "name": "get_weather", "parameters": {"properties": {"location": {"type": "string"}}, "type": "object"}}, "type": "function"}], "top_k": 50, "top_p": 1.0, "vertex_ai_metadata": {"location": "us-central1", "project": "my-gcp-project", "project_ids": ["my-gcp-project"]}}
When the request is sent
Then the response status is 400 Bad Request

@generated @skip @team:DataDog/ml-observability
Scenario: Run an LLM inference returns "OK" response
Given operation "CreateLLMObsIntegrationInference" enabled
And new "CreateLLMObsIntegrationInference" request
And request contains "integration" parameter from "REPLACE.ME"
And request contains "account_id" parameter from "REPLACE.ME"
And body with value {"anthropic_metadata": {"effort": "medium", "thinking": {"budget_tokens": 1024, "type": "enabled"}}, "azure_openai_metadata": {"deployment_id": "my-gpt4-deployment", "model_version": "0613", "resource_name": "my-azure-resource"}, "bedrock_metadata": {"region": "us-east-1"}, "frequency_penalty": 0.0, "json_schema": "{\"type\":\"object\",\"properties\":{\"answer\":{\"type\":\"string\"}}}", "max_completion_tokens": 1024, "max_tokens": 1024, "messages": [{"content": "What is the capital of France?", "contents": [{"type": "text", "value": {"text": "Hello, how can I help you?", "tool_call": {"arguments": {"location": "San Francisco"}, "name": "get_weather", "tool_id": "call_abc123", "type": "function"}, "tool_call_result": {"name": "get_weather", "result": "The weather in San Francisco is 68\u00b0F and sunny.", "tool_id": "call_abc123", "type": "function"}}}], "id": "msg_001", "role": "user", "tool_calls": [{"arguments": {"location": "San Francisco"}, "name": "get_weather", "tool_id": "call_abc123", "type": "function"}], "tool_results": [{"name": "get_weather", "result": "The weather in San Francisco is 68\u00b0F and sunny.", "tool_id": "call_abc123", "type": "function"}]}], "model_id": "gpt-4o", "openai_metadata": {"reasoning_effort": "medium", "reasoning_summary": "auto"}, "presence_penalty": 0.0, "temperature": 0.7, "tools": [{"function": {"description": "Get the current weather for a location.", "name": "get_weather", "parameters": {"properties": {"location": {"type": "string"}}, "type": "object"}}, "type": "function"}], "top_k": 50, "top_p": 1.0, "vertex_ai_metadata": {"location": "us-central1", "project": "my-gcp-project", "project_ids": ["my-gcp-project"]}}
When the request is sent
Then the response status is 200 OK

@generated @skip @team:DataDog/ml-observability
Scenario: Search LLM Observability experimentation entities returns "Bad Request" response
Given operation "SearchLLMObsExperimentation" enabled
Expand Down
18 changes: 18 additions & 0 deletions features/v2/undo.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3797,6 +3797,24 @@
"type": "unsafe"
}
},
"ListLLMObsIntegrationAccounts": {
"tag": "LLM Observability",
"undo": {
"type": "safe"
}
},
"CreateLLMObsIntegrationInference": {
"tag": "LLM Observability",
"undo": {
"type": "safe"
}
},
"ListLLMObsIntegrationModels": {
"tag": "LLM Observability",
"undo": {
"type": "safe"
}
},
"ListLLMObsProjects": {
"tag": "LLM Observability",
"undo": {
Expand Down
33 changes: 33 additions & 0 deletions private/bdd_runner/src/support/scenarios_model_mapping.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2755,6 +2755,39 @@ export const ScenariosModelMappings: { [key: string]: OperationMapping } = {
},
operationResponseType: "{}",
},
"LLMObservabilityApi.V2.ListLLMObsIntegrationAccounts": {
integration: {
type: "LLMObsIntegrationName",
format: "",
},
operationResponseType: "Array<LLMObsIntegrationAccount>",
},
"LLMObservabilityApi.V2.CreateLLMObsIntegrationInference": {
integration: {
type: "LLMObsIntegrationName",
format: "",
},
accountId: {
type: "string",
format: "",
},
body: {
type: "LLMObsIntegrationInferenceRequest",
format: "",
},
operationResponseType: "LLMObsIntegrationInferenceResponse",
},
"LLMObservabilityApi.V2.ListLLMObsIntegrationModels": {
integration: {
type: "LLMObsIntegrationName",
format: "",
},
accountId: {
type: "string",
format: "",
},
operationResponseType: "Array<LLMObsIntegrationModel>",
},
"LLMObservabilityApi.V2.ListLLMObsProjects": {
filterId: {
type: "string",
Expand Down
Loading
Loading