Skip to content

LLM-25262 Account for cached input tokens separately #75

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
dtim merged 1 commit into from
Mar 18, 2026
Merged

LLM-25262 Account for cached input tokens separately #75

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
3 changes: 2 additions & 1 deletion src/CodexCommands.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -245,8 +245,9 @@ export class CodexCommands {
}
const total = this.formatTokenCount(usage.totalTokens);
const input = this.formatTokenCount(usage.inputTokens);
const cachedInput = this.formatTokenCount(usage.cachedInputTokens);
const output = this.formatTokenCount(usage.outputTokens);
return `${total} total (${input} input + ${output} output)`;
return `${total} total (${input} input + ${cachedInput} cached input, ${output} output)`;
}

private formatContextWindow(usage: TokenCount | null, contextWindow: number | null): string {
Expand Down
10 changes: 9 additions & 1 deletion src/TokenCount.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,6 +3,12 @@ import type {TokenUsageBreakdown} from "./app-server/v2";
/**
* Token usage information for a turn.
* This interface decouples our API from Codex's internal types.
*
* [totalTokens]: total number of tokens used (the sum of all other fields)
* [inputTokens]: number of non-cached input tokens
* [cachedInputTokens]: number of cached input tokens
* [outputTokens]: number of output tokens (including reasoning output tokens)
* [reasoningOutputTokens]: number of reasoning output tokens
*/
export interface TokenCount {
totalTokens: number;
Expand All @@ -15,11 +21,13 @@ export interface TokenCount {
/**
* Maps Codex's TokenUsageBreakdown to our TokenCount interface.
* This explicit mapping ensures compile-time errors if Codex changes their types.
* Note: Codex includes cached input tokens in the input token count, so they are subtracted here.
*/
export function toTokenCount(usage: TokenUsageBreakdown): TokenCount {

return {
totalTokens: usage.totalTokens,
inputTokens: usage.inputTokens,
inputTokens: usage.inputTokens - usage.cachedInputTokens,
cachedInputTokens: usage.cachedInputTokens,
outputTokens: usage.outputTokens,
reasoningOutputTokens: usage.reasoningOutputTokens,
Expand Down
4 changes: 2 additions & 2 deletions src/__tests__/CodexACPAgent/data/token-usage-end-turn.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,7 +4,7 @@
"quota": {
"token_count": {
"totalTokens": 2500,
"inputTokens": 2000,
"inputTokens": 1500,
"cachedInputTokens": 500,
"outputTokens": 450,
"reasoningOutputTokens": 50
Expand All @@ -14,7 +14,7 @@
"model": "model-id",
"token_count": {
"totalTokens": 2500,
"inputTokens": 2000,
"inputTokens": 1500,
"cachedInputTokens": 500,
"outputTokens": 450,
"reasoningOutputTokens": 50
Expand Down
4 changes: 2 additions & 2 deletions src/__tests__/CodexACPAgent/data/token-usage-multiple-updates.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,7 +4,7 @@
"quota": {
"token_count": {
"totalTokens": 1500,
"inputTokens": 1200,
"inputTokens": 700,
"cachedInputTokens": 500,
"outputTokens": 200,
"reasoningOutputTokens": 100
Expand All @@ -14,7 +14,7 @@
"model": "model-id",
"token_count": {
"totalTokens": 1500,
"inputTokens": 1200,
"inputTokens": 700,
"cachedInputTokens": 500,
"outputTokens": 200,
"reasoningOutputTokens": 100
Expand Down
Loading