lmin/zmo-cli
1
0
Fork 0
Code Issues Pull Requests Actions 88 Packages Projects Releases Wiki Activity

refactor(llm): normalize Usage as inclusive total + non-overlapping breakdown (#26735)

Browse Source
This commit is contained in:
Kit Langton
2026-05-10 21:52:50 -04:00
committed by GitHub
parent 38e4540119
commit 2703eff2e2
12 changed files with 275 additions and 68 deletions
Download Patch File Download Diff File Expand all files Collapse all files
packages/llm/test/provider/anthropic-messages.test.ts
+11 -4
View File
@@ -1,6 +1,6 @@
import { describe, expect } from "bun:test"
import { Effect } from "effect"
import { CacheHint, LLM, LLMError } from "../../src"
import { CacheHint, LLM, LLMError, Usage } from "../../src"
import { LLMClient } from "../../src/route"
import * as AnthropicMessages from "../../src/protocols/anthropic-messages"
import { it } from "../lib/effect"
@@ -110,10 +110,11 @@ describe("Anthropic Messages route", () => {
expect(response.text).toBe("Hello!")
expect(response.reasoning).toBe("thinking")
expect(response.usage).toMatchObject({
inputTokens: 5,
inputTokens: 6,
outputTokens: 2,
nonCachedInputTokens: 5,
cacheReadInputTokens: 1,
totalTokens: 7,
totalTokens: 8,
})
expect(response.events.find((event) => event.type === "reasoning-end")).toMatchObject({
providerMetadata: { anthropic: { signature: "sig_1" } },
@@ -152,7 +153,13 @@ describe("Anthropic Messages route", () => {
{
type: "request-finish",
reason: "tool-calls",
usage: { inputTokens: 5, outputTokens: 1, totalTokens: 6, native: { input_tokens: 5, output_tokens: 1 } },
usage: new Usage({
inputTokens: 5,
outputTokens: 1,
nonCachedInputTokens: 5,
totalTokens: 6,
providerMetadata: { anthropic: { input_tokens: 5, output_tokens: 1 } },
}),
},
])
}),
packages/llm/test/provider/gemini.test.ts
+21 -16
View File
@@ -1,6 +1,6 @@
import { describe, expect } from "bun:test"
import { Effect } from "effect"
import { LLM, LLMError } from "../../src"
import { LLM, LLMError, Usage } from "../../src"
import { LLMClient } from "../../src/route"
import * as Gemini from "../../src/protocols/gemini"
import { it } from "../lib/effect"
@@ -198,9 +198,10 @@ describe("Gemini route", () => {
expect(response.reasoning).toBe("thinking")
expect(response.usage).toMatchObject({
inputTokens: 5,
outputTokens: 2,
reasoningTokens: 1,
outputTokens: 3,
nonCachedInputTokens: 4,
cacheReadInputTokens: 1,
reasoningTokens: 1,
totalTokens: 7,
})
expect(response.events).toEqual([
@@ -210,20 +211,23 @@ describe("Gemini route", () => {
{
type: "request-finish",
reason: "stop",
usage: {
usage: new Usage({
inputTokens: 5,
outputTokens: 2,
reasoningTokens: 1,
outputTokens: 3,
nonCachedInputTokens: 4,
cacheReadInputTokens: 1,
reasoningTokens: 1,
totalTokens: 7,
native: {
promptTokenCount: 5,
candidatesTokenCount: 2,
totalTokenCount: 7,
thoughtsTokenCount: 1,
cachedContentTokenCount: 1,
providerMetadata: {
google: {
promptTokenCount: 5,
candidatesTokenCount: 2,
totalTokenCount: 7,
thoughtsTokenCount: 1,
cachedContentTokenCount: 1,
},
},
},
}),
},
])
}),
@@ -257,12 +261,13 @@ describe("Gemini route", () => {
{
type: "request-finish",
reason: "tool-calls",
usage: {
usage: new Usage({
inputTokens: 5,
outputTokens: 1,
nonCachedInputTokens: 5,
totalTokens: 6,
native: { promptTokenCount: 5, candidatesTokenCount: 1 },
},
providerMetadata: { google: { promptTokenCount: 5, candidatesTokenCount: 1 } },
}),
},
])
}),
packages/llm/test/provider/openai-chat.test.ts
+13 -10
View File
@@ -1,7 +1,7 @@
import { describe, expect } from "bun:test"
import { Effect, Schema, Stream } from "effect"
import { HttpClientRequest } from "effect/unstable/http"
import { LLM, LLMError } from "../../src"
import { LLM, LLMError, Usage } from "../../src"
import * as Azure from "../../src/providers/azure"
import * as OpenAI from "../../src/providers/openai"
import * as OpenAIChat from "../../src/protocols/openai-chat"
@@ -230,20 +230,23 @@ describe("OpenAI Chat route", () => {
{
type: "request-finish",
reason: "stop",
usage: {
usage: new Usage({
inputTokens: 5,
outputTokens: 2,
reasoningTokens: 0,
nonCachedInputTokens: 4,
cacheReadInputTokens: 1,
reasoningTokens: 0,
totalTokens: 7,
native: {
prompt_tokens: 5,
completion_tokens: 2,
total_tokens: 7,
prompt_tokens_details: { cached_tokens: 1 },
completion_tokens_details: { reasoning_tokens: 0 },
providerMetadata: {
openai: {
prompt_tokens: 5,
completion_tokens: 2,
total_tokens: 7,
prompt_tokens_details: { cached_tokens: 1 },
completion_tokens_details: { reasoning_tokens: 0 },
},
},
},
}),
},
])
}),
packages/llm/test/provider/openai-responses.test.ts
+20 -11
View File
@@ -1,7 +1,7 @@
import { describe, expect } from "bun:test"
import { ConfigProvider, Effect, Layer, Stream } from "effect"
import { Headers, HttpClientRequest } from "effect/unstable/http"
import { LLM, LLMError } from "../../src"
import { LLM, LLMError, Usage } from "../../src"
import { Auth, LLMClient, RequestExecutor, WebSocketExecutor } from "../../src/route"
import * as Azure from "../../src/providers/azure"
import * as OpenAI from "../../src/providers/openai"
@@ -342,20 +342,23 @@ describe("OpenAI Responses route", () => {
type: "request-finish",
reason: "stop",
providerMetadata: { openai: { responseId: "resp_1", serviceTier: "default" } },
usage: {
usage: new Usage({
inputTokens: 5,
outputTokens: 2,
reasoningTokens: 0,
nonCachedInputTokens: 4,
cacheReadInputTokens: 1,
reasoningTokens: 0,
totalTokens: 7,
native: {
input_tokens: 5,
output_tokens: 2,
total_tokens: 7,
input_tokens_details: { cached_tokens: 1 },
output_tokens_details: { reasoning_tokens: 0 },
providerMetadata: {
openai: {
input_tokens: 5,
output_tokens: 2,
total_tokens: 7,
input_tokens_details: { cached_tokens: 1 },
output_tokens_details: { reasoning_tokens: 0 },
},
},
},
}),
},
])
}),
@@ -411,7 +414,13 @@ describe("OpenAI Responses route", () => {
{
type: "request-finish",
reason: "tool-calls",
usage: { inputTokens: 5, outputTokens: 1, totalTokens: 6, native: { input_tokens: 5, output_tokens: 1 } },
usage: new Usage({
inputTokens: 5,
outputTokens: 1,
nonCachedInputTokens: 5,
totalTokens: 6,
providerMetadata: { openai: { input_tokens: 5, output_tokens: 1 } },
}),
},
])
}),
packages/llm/test/schema.test.ts
+29 -1
View File
@@ -1,6 +1,7 @@
import { describe, expect, test } from "bun:test"
import { Schema } from "effect"
import { ContentPart, LLMEvent, LLMRequest, ModelID, ModelLimits, ModelRef, ProviderID } from "../src/schema"
import { ContentPart, LLMEvent, LLMRequest, ModelID, ModelLimits, ModelRef, ProviderID, Usage } from "../src/schema"
import { ProviderShared } from "../src/protocols/shared"
const model = new ModelRef({
id: ModelID.make("fake-model"),
@@ -48,3 +49,30 @@ describe("llm schema", () => {
expect(ContentPart.guards.media({ type: "text", text: "hi" })).toBe(false)
})
})
describe("LLM.Usage", () => {
test("subtractTokens clamps non-sensical breakdowns to zero", () => {
// Defense against a provider reporting cached_tokens > prompt_tokens or
// reasoning_tokens > completion_tokens — the negative would otherwise
// round-trip through the pipeline and crash strict downstream schemas.
expect(ProviderShared.subtractTokens(5, 3)).toBe(2)
expect(ProviderShared.subtractTokens(5, 10)).toBe(0)
expect(ProviderShared.subtractTokens(5, undefined)).toBe(5)
expect(ProviderShared.subtractTokens(undefined, 3)).toBeUndefined()
expect(ProviderShared.subtractTokens(undefined, undefined)).toBeUndefined()
})
test("sumTokens returns undefined only when every input is undefined", () => {
expect(ProviderShared.sumTokens(1, 2, 3)).toBe(6)
expect(ProviderShared.sumTokens(1, undefined, 3)).toBe(4)
expect(ProviderShared.sumTokens(undefined, undefined, undefined)).toBeUndefined()
expect(ProviderShared.sumTokens()).toBeUndefined()
})
test("visibleOutputTokens clamps reasoning > output to zero", () => {
expect(new Usage({ outputTokens: 10, reasoningTokens: 4 }).visibleOutputTokens).toBe(6)
expect(new Usage({ outputTokens: 10 }).visibleOutputTokens).toBe(10)
expect(new Usage({ outputTokens: 4, reasoningTokens: 10 }).visibleOutputTokens).toBe(0)
expect(new Usage({}).visibleOutputTokens).toBe(0)
})
})