Feat(ai-gateway): v2 telemetry

app/_data/ai-gateway/v2/otel-metrics.yaml

@@ -0,0 +1,332 @@
+metrics:
+  - name: gen_ai.client.operation.duration
+    min_version: ""
+    description: Total time Kong spends processing a Gen AI operation, such as an LLM request. Requires `enable_request_metrics` to populate the `error.type` attribute.
+    unit: "s"
+    type: Histogram
+    attributes:
+      - gen_ai.provider.name
+      - gen_ai.request.model
+      - gen_ai.response.model
+      - gen_ai.operation.name
+      - kong.workspace.name
+      - kong.auth.consumer.name
+      - kong.gen_ai.request.mode
+      - error.type
+  - name: gen_ai.server.request.duration
+    min_version: ""
+    description: Time the LLM provider spends processing the request. Requires `enable_latency_metrics` set to `true`. Requires `enable_request_metrics` to populate the `error.type` attribute.
+    unit: "s"
+    type: Histogram
+    attributes:
+      - gen_ai.provider.name
+      - gen_ai.request.model
+      - gen_ai.response.model
+      - gen_ai.operation.name
+      - kong.workspace.name
+      - kong.auth.consumer.name
+      - kong.gen_ai.request.mode
+      - error.type
+  - name: gen_ai.client.token.usage
+    min_version: ""
+    description: Number of tokens consumed by the Gen AI operation.
+    unit: "{token}"
+    type: Sum
+    attributes:
+      - gen_ai.provider.name
+      - gen_ai.request.model
+      - gen_ai.response.model
+      - gen_ai.token.type
+      - gen_ai.operation.name
+      - kong.workspace.name
+      - kong.auth.consumer.name
+      - kong.gen_ai.request.mode
+  - name: gen_ai.server.time_to_first_token
+    min_version: ""
+    description: Time from when the model server receives the request until the first output token is generated.
+    unit: "s"
+    type: Histogram
+    attributes:
+      - gen_ai.provider.name
+      - gen_ai.request.model
+      - gen_ai.response.model
+      - gen_ai.operation.name
+      - kong.workspace.name
+      - kong.auth.consumer.name
+      - kong.gen_ai.request.mode
+  - name: gen_ai.server.time_per_output_token
+    min_version: ""
+    description: Time between successive output tokens generated by the model server after the first token.
+    unit: "s"
+    type: Histogram
+    attributes:
+      - gen_ai.provider.name
+      - gen_ai.request.model
+      - gen_ai.response.model
+      - gen_ai.operation.name
+      - kong.workspace.name
+      - kong.auth.consumer.name
+      - kong.gen_ai.request.mode
+  - name: kong.gen_ai.llm.cost
+    min_version: ""
+    description: Cost of AI requests.
+    unit: "{cost}"
+    type: Sum
+    attributes:
+      - gen_ai.provider.name
+      - gen_ai.request.model
+      - gen_ai.response.model
+      - gen_ai.operation.name
+      - kong.gen_ai.cache.status
+      - kong.gen_ai.vector_db
+      - kong.gen_ai.embeddings.provider
+      - kong.gen_ai.embeddings.model
+      - kong.workspace.name
+      - kong.auth.consumer.name
+      - kong.gen_ai.request.mode
+  - name: kong.gen_ai.cache.fetch.latency
+    min_version: ""
+    description: Time to fetch a response from the semantic cache.
+    unit: "s"
+    type: Histogram
+    attributes:
+      - gen_ai.provider.name
+      - gen_ai.request.model
+      - gen_ai.response.model
+      - gen_ai.operation.name
+      - kong.gen_ai.cache.status
+      - kong.gen_ai.vector_db
+      - kong.gen_ai.embeddings.provider
+      - kong.gen_ai.embeddings.model
+      - kong.workspace.name
+      - kong.auth.consumer.name
+      - kong.gen_ai.request.mode
+  - name: kong.gen_ai.cache.embeddings.latency
+    min_version: ""
+    description: Time to generate embeddings during cache operations.
+    unit: "s"
+    type: Histogram
+    attributes:
+      - gen_ai.provider.name
+      - gen_ai.request.model
+      - gen_ai.response.model
+      - gen_ai.operation.name
+      - kong.gen_ai.cache.status
+      - kong.gen_ai.vector_db
+      - kong.gen_ai.embeddings.provider
+      - kong.gen_ai.embeddings.model
+      - kong.workspace.name
+      - kong.auth.consumer.name
+      - kong.gen_ai.request.mode
+  - name: kong.gen_ai.rag.fetch.latency
+    min_version: ""
+    description: Time to fetch data from a RAG source.
+    unit: "s"
+    type: Histogram
+    attributes:
+      - gen_ai.provider.name
+      - gen_ai.request.model
+      - gen_ai.response.model
+      - gen_ai.operation.name
+      - kong.gen_ai.cache.status
+      - kong.gen_ai.vector_db
+      - kong.gen_ai.embeddings.provider
+      - kong.gen_ai.embeddings.model
+      - kong.workspace.name
+      - kong.auth.consumer.name
+      - kong.gen_ai.request.mode
+  - name: kong.gen_ai.rag.embeddings.latency
+    min_version: ""
+    description: Time to generate embeddings for RAG operations.
+    unit: "s"
+    type: Histogram
+    attributes:
+      - gen_ai.provider.name
+      - gen_ai.request.model
+      - gen_ai.response.model
+      - gen_ai.operation.name
+      - kong.gen_ai.cache.status
+      - kong.gen_ai.vector_db
+      - kong.gen_ai.embeddings.provider
+      - kong.gen_ai.embeddings.model
+      - kong.workspace.name
+      - kong.auth.consumer.name
+      - kong.gen_ai.request.mode
+  - name: kong.gen_ai.aws.guardrails.latency
+    min_version: ""
+    description: Time for AWS Guardrails to process a request.
+    unit: "s"
+    type: Histogram
+    attributes:
+      - kong.gen_ai.aws.guardrails.id
+      - kong.gen_ai.aws.guardrails.version
+      - kong.gen_ai.aws.guardrails.mode
+      - kong.gen_ai.aws.guardrails.region
+      - kong.workspace.name
+      - kong.auth.consumer.name
+  - name: kong.gen_ai.mcp.response.size
+    min_version: ""
+    description: Size of the MCP response body in bytes.
+    unit: "By"
+    type: Histogram
+    attributes:
+      - kong.service.name
+      - kong.route.name
+      - kong.workspace.name
+      - mcp.method.name
+      - gen_ai.tool.name
+  - name: kong.gen_ai.mcp.request.error.count
+    min_version: ""
+    description: Number of MCP request errors.
+    unit: "{error}"
+    type: Sum
+    attributes:
+      - kong.service.name
+      - kong.route.name
+      - kong.workspace.name
+      - mcp.method.name
+      - gen_ai.tool.name
+      - error.type
+  - name: mcp.client.operation.duration
+    min_version: ""
+    description: Duration of the MCP request as observed by the sender. Only available when the MCP entity is in passthrough-listener mode. Requires `enable_latency_metrics` set to `true`.
+    unit: "s"
+    type: Histogram
+    attributes:
+      - kong.service.name
+      - kong.route.name
+      - kong.workspace.name
+      - mcp.method.name
+      - gen_ai.tool.name
+      - error.type
+      - gen_ai.operation.name
+  - name: mcp.server.operation.duration
+    min_version: ""
+    description: Duration of the MCP request as observed by the receiver.
+    unit: "s"
+    type: Histogram
+    attributes:
+      - kong.service.name
+      - kong.route.name
+      - kong.workspace.name
+      - mcp.method.name
+      - gen_ai.tool.name
+      - error.type
+      - gen_ai.operation.name
+  - name: kong.gen_ai.mcp.acl.allowed
+    min_version: ""
+    description: Number of MCP requests allowed by ACL rules.
+    unit: "{request}"
+    type: Sum
+    attributes:
+      - kong.service.name
+      - kong.route.name
+      - kong.workspace.name
+      - kong.gen_ai.mcp.primitive
+      - kong.gen_ai.mcp.primitive_name
+  - name: kong.gen_ai.mcp.acl.denied
+    min_version: ""
+    description: Number of MCP requests denied by ACL rules.
+    unit: "{request}"
+    type: Sum
+    attributes:
+      - kong.service.name
+      - kong.route.name
+      - kong.workspace.name
+      - kong.gen_ai.mcp.primitive
+      - kong.gen_ai.mcp.primitive_name
+  - name: kong.gen_ai.a2a.request.count
+    min_version: ""
+    description: Total number of A2A requests.
+    unit: "{request}"
+    type: Sum
+    attributes:
+      - kong.service.name
+      - kong.route.name
+      - kong.workspace.name
+      - kong.gen_ai.a2a.method
+      - kong.gen_ai.a2a.binding
+  - name: kong.gen_ai.a2a.request.duration
+    min_version: ""
+    description: Duration of an A2A request in seconds.
+    unit: "s"
+    type: Histogram
+    attributes:
+      - kong.service.name
+      - kong.route.name
+      - kong.workspace.name
+      - kong.gen_ai.a2a.method
+      - kong.gen_ai.a2a.binding
+  - name: kong.gen_ai.a2a.response.size
+    min_version: ""
+    description: Size of the A2A response body in bytes.
+    unit: "By"
+    type: Histogram
+    attributes:
+      - kong.service.name
+      - kong.route.name
+      - kong.workspace.name
+      - kong.gen_ai.a2a.method
+      - kong.gen_ai.a2a.binding
+  - name: kong.gen_ai.a2a.ttfb
+    min_version: ""
+    description: Time to first byte for A2A streaming responses in seconds.
+    unit: "s"
+    type: Histogram
+    attributes:
+      - kong.service.name
+      - kong.route.name
+      - kong.workspace.name
+      - kong.gen_ai.a2a.method
+      - kong.gen_ai.a2a.binding
+  - name: kong.gen_ai.a2a.request.error.count
+    min_version: ""
+    description: Number of A2A request errors.
+    unit: "{error}"
+    type: Sum
+    attributes:
+      - kong.service.name
+      - kong.route.name
+      - kong.workspace.name
+      - kong.gen_ai.a2a.method
+      - kong.gen_ai.a2a.binding
+      - kong.gen_ai.a2a.error.type
+  - name: kong.gen_ai.a2a.task.state.count
+    min_version: ""
+    description: Number of A2A task state transitions.
+    unit: "{state}"
+    type: Sum
+    attributes:
+      - kong.service.name
+      - kong.route.name
+      - kong.workspace.name
+      - kong.gen_ai.a2a.task.state
+
+attributes:
+  kong.service.name: Name of the Gateway Service.
+  kong.route.name: Name of the Route.
+  kong.auth.consumer.name: Name of the authenticated Consumer.
+  kong.workspace.name: Name of the Workspace.
+  error.type: Type of error that occurred.
+  gen_ai.provider.name: Name of the Gen AI provider.
+  gen_ai.request.model: Model name targeted by the request.
+  gen_ai.response.model: Model name reported by the provider in the response.
+  gen_ai.operation.name: "Operation requested, such as `chat` or `embeddings`."
+  gen_ai.token.type: "Token category: `input`, `output`, or `total`."
+  kong.gen_ai.request.mode: "Request mode: `oneshot`, `stream`, or `realtime`."
+  kong.gen_ai.cache.status: "Cache status: `hit` or empty if not cached."
+  kong.gen_ai.vector_db: "Vector database used for caching, such as `redis`."
+  kong.gen_ai.embeddings.provider: Embeddings provider used for caching.
+  kong.gen_ai.embeddings.model: Embeddings model used for caching.
+  kong.gen_ai.aws.guardrails.id: ID of the AWS Guardrails configuration.
+  kong.gen_ai.aws.guardrails.version: Version of the AWS Guardrails configuration.
+  kong.gen_ai.aws.guardrails.mode: Mode of the AWS Guardrails evaluation.
+  kong.gen_ai.aws.guardrails.region: AWS region of the Guardrails service.
+  mcp.method.name: "MCP method name, such as `tools/call`."
+  gen_ai.tool.name: Name of the MCP tool invoked.
+  kong.gen_ai.mcp.primitive: "MCP primitive type, such as `tool`."
+  kong.gen_ai.mcp.primitive_name: Name of the MCP primitive.
+  kong.gen_ai.a2a.method: A2A method name.
+  kong.gen_ai.a2a.binding: A2A binding type.
+  kong.gen_ai.a2a.error.type: Type of the A2A error.
+  kong.gen_ai.a2a.task.state: "Task state, such as `completed`, `failed`, or `in_progress`."