vrr/opencode
2
0
Fork 0
mirror of https://github.com/anomalyco/opencode.git synced 2026-08-04 06:59:53 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 6

fix(ai): report OpenAI cache writes (#38735)

Browse source
This commit is contained in:
Kit Langton 2026-07-24 14:26:30 -04:00 • committed by GitHub
parent 423fad730c
commit b09a066fb5
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
5 changed files with 31 additions and 14 deletions
Download patch file Download diff file Expand all files Collapse all files

5
.changeset/bright-sols-write.md Normal file
View file

@ -0,0 +1,5 @@
---
"@opencode-ai/ai": patch
---
Report OpenAI prompt cache write tokens in normalized usage.

15
packages/ai/src/protocols/open-responses.ts
View file

@ -167,7 +167,12 @@ export type OpenResponsesBody = Schema.Schema.Type<typeof OpenResponsesBody>
const OpenResponsesUsage = Schema.Struct({
input_tokens: Schema.optional(Schema.Number),
input_tokens_details: optionalNull(Schema.Struct({ cached_tokens: Schema.optional(Schema.Number) })),
input_tokens_details: optionalNull(
Schema.Struct({
cached_tokens: Schema.optional(Schema.Number),
cache_write_tokens: Schema.optional(Schema.Number),
}),
),
output_tokens: Schema.optional(Schema.Number),
output_tokens_details: optionalNull(Schema.Struct({ reasoning_tokens: Schema.optional(Schema.Number) })),
total_tokens: Schema.optional(Schema.Number),
@ -540,19 +545,21 @@ export const fromRequest = Effect.fn("OpenResponses.fromRequest")(function* (
// Stream Parsing
// =============================================================================
// Responses APIs report `input_tokens` (inclusive total) with a
// `cached_tokens` subset, and `output_tokens` (inclusive total) with a
// `reasoning_tokens` subset. Pass the totals through and derive the
// cached-read and cache-write subsets, and `output_tokens` (inclusive total)
// with a `reasoning_tokens` subset. Pass the totals through and derive the
// non-cached breakdown.
const mapUsage = (usage: OpenResponsesUsage | null | undefined, providerMetadataKey: string) => {
if (!usage) return undefined
const cached = usage.input_tokens_details?.cached_tokens
const cacheWrite = usage.input_tokens_details?.cache_write_tokens
const reasoning = usage.output_tokens_details?.reasoning_tokens
const nonCached = ProviderShared.subtractTokens(usage.input_tokens, cached)
const nonCached = ProviderShared.subtractTokens(usage.input_tokens, ProviderShared.sumTokens(cached, cacheWrite))
return new Usage({
inputTokens: usage.input_tokens,
outputTokens: usage.output_tokens,
nonCachedInputTokens: nonCached,
cacheReadInputTokens: cached,
cacheWriteInputTokens: cacheWrite,
reasoningTokens: reasoning,
totalTokens: ProviderShared.totalTokens(usage.input_tokens, usage.output_tokens, usage.total_tokens),
providerMetadata: { [providerMetadataKey]: usage },

11
packages/ai/src/protocols/openai-chat.ts
View file

@ -131,6 +131,7 @@ const OpenAIChatUsage = Schema.Struct({
prompt_tokens_details: optionalNull(
Schema.Struct({
cached_tokens: Schema.optional(Schema.Number),
cache_write_tokens: Schema.optional(Schema.Number),
}),
),
completion_tokens_details: optionalNull(
@ -453,20 +454,22 @@ const mapFinishReason = (reason: string | null | undefined): FinishReason => {
}
// OpenAI Chat reports `prompt_tokens` (inclusive total) with a
// `cached_tokens` subset, and `completion_tokens` (inclusive total) with
// a `reasoning_tokens` subset. We pass the inclusive totals through and
// derive the non-cached breakdown so the `LLM.Usage` contract is
// cached-read and cache-write subsets, and `completion_tokens` (inclusive
// total) with a `reasoning_tokens` subset. We pass the inclusive totals
// through and derive the non-cached breakdown so the `LLM.Usage` contract is
// satisfied on both sides.
const mapUsage = (usage: OpenAIChatEvent["usage"]): Usage | undefined => {
if (!usage) return undefined
const cached = usage.prompt_tokens_details?.cached_tokens
const cacheWrite = usage.prompt_tokens_details?.cache_write_tokens
const reasoning = usage.completion_tokens_details?.reasoning_tokens
const nonCached = ProviderShared.subtractTokens(usage.prompt_tokens, cached)
const nonCached = ProviderShared.subtractTokens(usage.prompt_tokens, ProviderShared.sumTokens(cached, cacheWrite))
return new Usage({
inputTokens: usage.prompt_tokens,
outputTokens: usage.completion_tokens,
nonCachedInputTokens: nonCached,
cacheReadInputTokens: cached,
cacheWriteInputTokens: cacheWrite,
reasoningTokens: reasoning,
totalTokens: ProviderShared.totalTokens(usage.prompt_tokens, usage.completion_tokens, usage.total_tokens),
providerMetadata: { openai: usage },

7
packages/ai/test/provider/openai-chat.test.ts
View file

@ -550,7 +550,7 @@ describe("OpenAI Chat route", () => {
prompt_tokens: 5,
completion_tokens: 2,
total_tokens: 7,
prompt_tokens_details: { cached_tokens: 1 },
prompt_tokens_details: { cached_tokens: 1, cache_write_tokens: 2 },
completion_tokens_details: { reasoning_tokens: 0 },
}),
)
@ -558,8 +558,9 @@ describe("OpenAI Chat route", () => {
const usage = new Usage({
inputTokens: 5,
outputTokens: 2,
nonCachedInputTokens: 4,
nonCachedInputTokens: 2,
cacheReadInputTokens: 1,
cacheWriteInputTokens: 2,
reasoningTokens: 0,
totalTokens: 7,
providerMetadata: {
@ -567,7 +568,7 @@ describe("OpenAI Chat route", () => {
prompt_tokens: 5,
completion_tokens: 2,
total_tokens: 7,
prompt_tokens_details: { cached_tokens: 1 },
prompt_tokens_details: { cached_tokens: 1, cache_write_tokens: 2 },
completion_tokens_details: { reasoning_tokens: 0 },
},
},

7
packages/ai/test/provider/openai-responses.test.ts
View file

@ -832,7 +832,7 @@ describe("OpenAI Responses route", () => {
input_tokens: 5,
output_tokens: 2,
total_tokens: 7,
input_tokens_details: { cached_tokens: 1 },
input_tokens_details: { cached_tokens: 1, cache_write_tokens: 2 },
output_tokens_details: { reasoning_tokens: 0 },
},
},
@ -842,8 +842,9 @@ describe("OpenAI Responses route", () => {
const usage = new Usage({
inputTokens: 5,
outputTokens: 2,
nonCachedInputTokens: 4,
nonCachedInputTokens: 2,
cacheReadInputTokens: 1,
cacheWriteInputTokens: 2,
reasoningTokens: 0,
totalTokens: 7,
providerMetadata: {
@ -851,7 +852,7 @@ describe("OpenAI Responses route", () => {
input_tokens: 5,
output_tokens: 2,
total_tokens: 7,
input_tokens_details: { cached_tokens: 1 },
input_tokens_details: { cached_tokens: 1, cache_write_tokens: 2 },
output_tokens_details: { reasoning_tokens: 0 },
},
},