Skip to content

feat: emit OTel GenAI token and model attributes on LLM spans #125

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

Open
johndemic wants to merge 1 commit into
base: main
Choose a base branch
from
+65 −0
Open

feat: emit OTel GenAI token and model attributes on LLM spans #125

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
17 changes: 17 additions & 0 deletions src/handlers/message.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -27,6 +27,12 @@ import {
TOOL_NAME,
TOOL_PARAMETERS,
} from "@arizeai/openinference-semantic-conventions"
import {
ATTR_GEN_AI_REQUEST_MODEL,
ATTR_GEN_AI_RESPONSE_MODEL,
ATTR_GEN_AI_USAGE_INPUT_TOKENS,
ATTR_GEN_AI_USAGE_OUTPUT_TOKENS,
} from "@opentelemetry/semantic-conventions/incubating"
import {
agentAttrs,
errorSummary,
Expand All @@ -42,6 +48,11 @@ import type { HandlerContext } from "../types.ts"

const OPENINFERENCE_SPAN_KIND = SemanticConventions.OPENINFERENCE_SPAN_KIND
const LLM_FINISH_REASON = "llm.finish_reason"
// Spelled out rather than taken from semconv: the incubating constants emit
// `gen_ai.usage.cache_read.input_tokens`, while Anthropic's API and every GenAI
// consumer we target read the underscored form below.
const ATTR_GEN_AI_USAGE_CACHE_READ_INPUT_TOKENS = "gen_ai.usage.cache_read_input_tokens"
const ATTR_GEN_AI_USAGE_CACHE_CREATION_INPUT_TOKENS = "gen_ai.usage.cache_creation_input_tokens"

type SubtaskPart = {
type: "subtask"
Expand Down Expand Up @@ -130,6 +141,11 @@ export function handleMessageUpdated(e: EventMessageUpdated, ctx: HandlerContext
[LLM_TOKEN_COUNT_PROMPT_DETAILS_CACHE_READ]: assistant.tokens.cache.read,
[LLM_TOKEN_COUNT_PROMPT_DETAILS_CACHE_WRITE]: assistant.tokens.cache.write,
[LLM_TOKEN_COUNT_TOTAL]: totalTokens,
[ATTR_GEN_AI_RESPONSE_MODEL]: modelID,
[ATTR_GEN_AI_USAGE_INPUT_TOKENS]: assistant.tokens.input,
[ATTR_GEN_AI_USAGE_OUTPUT_TOKENS]: assistant.tokens.output,
[ATTR_GEN_AI_USAGE_CACHE_READ_INPUT_TOKENS]: assistant.tokens.cache.read,
[ATTR_GEN_AI_USAGE_CACHE_CREATION_INPUT_TOKENS]: assistant.tokens.cache.write,
[LLM_FINISH_REASON]: assistant.error ? "error" : (assistant.finish ?? "stop"),
[LLM_COST_TOTAL]: assistant.cost,
...(outputText
Expand Down Expand Up @@ -454,6 +470,7 @@ export function startMessageSpan(
[LLM_PROVIDER]: providerID,
"gen_ai.provider.name": genAiProviderName(providerID),
[LLM_MODEL_NAME]: modelID,
[ATTR_GEN_AI_REQUEST_MODEL]: modelID,
...(inputText
? {
[INPUT_VALUE]: inputText,
Expand Down
48 changes: 48 additions & 0 deletions tests/handlers/spans.test.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -370,6 +370,16 @@ describe("message (LLM) spans", () => {
expect(tracer.spans[0]!.attributes[LLM_MODEL_NAME]).toBe("claude-sonnet-4")
})

// Asserted as literal keys, not via the semconv constants the source imports:
// these strings are the wire format Gen AI consumers match on, so the test has
// to fail if a constant is renamed upstream.
test("startMessageSpan sets OTel GenAI model attribute", () => {
const { ctx, tracer } = makeCtx()
startMessageSpan("ses_1", "msg_1", "user_1", "claude-sonnet-4", "amazon-bedrock", 1000, ctx)
expect(tracer.spans[0]!.attributes["gen_ai.request.model"]).toBe("claude-sonnet-4")
expect(tracer.spans[0]!.attributes["gen_ai.provider.name"]).toBe("aws.bedrock")
})

test("startMessageSpan is a no-op when span already exists for sessionID:messageID", () => {
const { ctx, tracer } = makeCtx()
startMessageSpan("ses_1", "msg_1", "user_1", "claude", "anthropic", 1000, ctx)
Expand Down Expand Up @@ -434,6 +444,44 @@ describe("message (LLM) spans", () => {
expect(span.attributes["agent.type"]).toBe("subagent")
})

test("handleMessageUpdated sets OTel GenAI token attributes on span", () => {
const { ctx, tracer } = makeCtx()
startMessageSpan("ses_1", "msg_1", "user_1", "claude-3-5-sonnet", "anthropic", 1000, ctx)
handleMessageUpdated(
makeAssistantMessageUpdated({
id: "msg_1",
modelID: "claude-3-5-sonnet",
tokens: { input: 200, output: 80, reasoning: 10, cache: { read: 30, write: 5 } },
}),
ctx,
)
const span = tracer.spans[0]!
expect(span.attributes["gen_ai.response.model"]).toBe("claude-3-5-sonnet")
expect(span.attributes["gen_ai.usage.input_tokens"]).toBe(200)
expect(span.attributes["gen_ai.usage.output_tokens"]).toBe(80)
// Underscored, matching Anthropic's API and Gen AI consumers. The semconv
// constants spell these with a dot (gen_ai.usage.cache_read.input_tokens).
expect(span.attributes["gen_ai.usage.cache_read_input_tokens"]).toBe(30)
expect(span.attributes["gen_ai.usage.cache_creation_input_tokens"]).toBe(5)
})

test("GenAI token attributes do not displace the OpenInference ones", () => {
const { ctx, tracer } = makeCtx()
startMessageSpan("ses_1", "msg_1", "user_1", "claude-3-5-sonnet", "anthropic", 1000, ctx)
handleMessageUpdated(
makeAssistantMessageUpdated({
id: "msg_1",
tokens: { input: 200, output: 80, reasoning: 10, cache: { read: 30, write: 5 } },
}),
ctx,
)
const span = tracer.spans[0]!
expect(span.attributes[LLM_TOKEN_COUNT_PROMPT]).toBe(200)
expect(span.attributes["gen_ai.usage.input_tokens"]).toBe(200)
expect(span.attributes[LLM_TOKEN_COUNT_PROMPT_DETAILS_CACHE_WRITE]).toBe(5)
expect(span.attributes["gen_ai.usage.cache_creation_input_tokens"]).toBe(5)
})

test("handleMessageUpdated no-ops span handling when no span exists for messageID", () => {
const { ctx, tracer } = makeCtx()
const spansBefore = tracer.spans.length
Expand Down
Loading