* fix: report cache reads in streaming and correct cost calculation
Fix two bugs in how the OpenAI-to-Anthropic shim handles cached tokens:
1. codexShim: streaming message_delta missing cache_read_input_tokens
The codexStreamToAnthropic() function builds the final message_delta
usage object inline (not through makeUsage()), and only included
input_tokens and output_tokens. cache_read_input_tokens was always 0,
so /cost never showed cache reads for Responses API models (GPT-5+).
Also fix makeUsage() to read input_tokens_details.cached_tokens and
prompt_tokens_details.cached_tokens for the non-streaming path.
2. Both shims: cost double-counting from convention mismatch
OpenAI includes cached tokens in input_tokens/prompt_tokens (i.e.,
input_tokens = uncached + cached). Anthropic treats input_tokens as
uncached only. The cost formula was:
cost = input_tokens * inputRate + cache_read * cacheRate
This double-counts cached tokens. Fix by subtracting cached from
input during the conversion:
input_tokens = prompt_tokens - cached_tokens
In practice this was inflating reported costs by ~2x for sessions
with high cache hit rates (which is most sessions, since Copilot
auto-caches server-side).
Fixes #515
* fix: omit zero cache read/write fields from /cost output
Only show "cache read" and "cache write" in /cost per-model usage when
the value is > 0. Providers like GitHub Copilot never report
cache_creation_input_tokens (the server manages its own cache), so
showing "0 cache write" on every line is misleading — it implies caching
is not working when it actually is.
Before:
claude-haiku: 2.6k input, 151 output, 39.8k cache read, 0 cache write ($0.04)
After:
claude-haiku: 2.6k input, 151 output, 39.8k cache read ($0.04)
---------
Co-authored-by: Zartris <14197299+Zartris@users.noreply.github.com>
328 lines
11 KiB
TypeScript
328 lines
11 KiB
TypeScript
import type { BetaUsage as Usage } from '@anthropic-ai/sdk/resources/beta/messages/messages.mjs'
|
|
import chalk from 'chalk'
|
|
import {
|
|
addToTotalCostState,
|
|
addToTotalLinesChanged,
|
|
getCostCounter,
|
|
getModelUsage,
|
|
getSdkBetas,
|
|
getSessionId,
|
|
getTokenCounter,
|
|
getTotalAPIDuration,
|
|
getTotalAPIDurationWithoutRetries,
|
|
getTotalCacheCreationInputTokens,
|
|
getTotalCacheReadInputTokens,
|
|
getTotalCostUSD,
|
|
getTotalDuration,
|
|
getTotalInputTokens,
|
|
getTotalLinesAdded,
|
|
getTotalLinesRemoved,
|
|
getTotalOutputTokens,
|
|
getTotalToolDuration,
|
|
getTotalWebSearchRequests,
|
|
getUsageForModel,
|
|
hasUnknownModelCost,
|
|
resetCostState,
|
|
resetStateForTests,
|
|
setCostStateForRestore,
|
|
setHasUnknownModelCost,
|
|
} from './bootstrap/state.js'
|
|
import type { ModelUsage } from './entrypoints/agentSdkTypes.js'
|
|
import {
|
|
type AnalyticsMetadata_I_VERIFIED_THIS_IS_NOT_CODE_OR_FILEPATHS,
|
|
logEvent,
|
|
} from './services/analytics/index.js'
|
|
import { getAdvisorUsage } from './utils/advisor.js'
|
|
import {
|
|
getCurrentProjectConfig,
|
|
saveCurrentProjectConfig,
|
|
} from './utils/config.js'
|
|
import {
|
|
getContextWindowForModel,
|
|
getModelMaxOutputTokens,
|
|
} from './utils/context.js'
|
|
import { isFastModeEnabled } from './utils/fastMode.js'
|
|
import { formatDuration, formatNumber } from './utils/format.js'
|
|
import type { FpsMetrics } from './utils/fpsTracker.js'
|
|
import { getCanonicalName } from './utils/model/model.js'
|
|
import { calculateUSDCost } from './utils/modelCost.js'
|
|
export {
|
|
getTotalCostUSD as getTotalCost,
|
|
getTotalDuration,
|
|
getTotalAPIDuration,
|
|
getTotalAPIDurationWithoutRetries,
|
|
addToTotalLinesChanged,
|
|
getTotalLinesAdded,
|
|
getTotalLinesRemoved,
|
|
getTotalInputTokens,
|
|
getTotalOutputTokens,
|
|
getTotalCacheReadInputTokens,
|
|
getTotalCacheCreationInputTokens,
|
|
getTotalWebSearchRequests,
|
|
formatCost,
|
|
hasUnknownModelCost,
|
|
resetStateForTests,
|
|
resetCostState,
|
|
setHasUnknownModelCost,
|
|
getModelUsage,
|
|
getUsageForModel,
|
|
}
|
|
|
|
type StoredCostState = {
|
|
totalCostUSD: number
|
|
totalAPIDuration: number
|
|
totalAPIDurationWithoutRetries: number
|
|
totalToolDuration: number
|
|
totalLinesAdded: number
|
|
totalLinesRemoved: number
|
|
lastDuration: number | undefined
|
|
modelUsage: { [modelName: string]: ModelUsage } | undefined
|
|
}
|
|
|
|
/**
|
|
* Gets stored cost state from project config for a specific session.
|
|
* Returns the cost data if the session ID matches, or undefined otherwise.
|
|
* Use this to read costs BEFORE overwriting the config with saveCurrentSessionCosts().
|
|
*/
|
|
export function getStoredSessionCosts(
|
|
sessionId: string,
|
|
): StoredCostState | undefined {
|
|
const projectConfig = getCurrentProjectConfig()
|
|
|
|
// Only return costs if this is the same session that was last saved
|
|
if (projectConfig.lastSessionId !== sessionId) {
|
|
return undefined
|
|
}
|
|
|
|
// Build model usage with context windows
|
|
let modelUsage: { [modelName: string]: ModelUsage } | undefined
|
|
if (projectConfig.lastModelUsage) {
|
|
modelUsage = Object.fromEntries(
|
|
Object.entries(projectConfig.lastModelUsage).map(([model, usage]) => [
|
|
model,
|
|
{
|
|
...usage,
|
|
contextWindow: getContextWindowForModel(model, getSdkBetas()),
|
|
maxOutputTokens: getModelMaxOutputTokens(model).default,
|
|
},
|
|
]),
|
|
)
|
|
}
|
|
|
|
return {
|
|
totalCostUSD: projectConfig.lastCost ?? 0,
|
|
totalAPIDuration: projectConfig.lastAPIDuration ?? 0,
|
|
totalAPIDurationWithoutRetries:
|
|
projectConfig.lastAPIDurationWithoutRetries ?? 0,
|
|
totalToolDuration: projectConfig.lastToolDuration ?? 0,
|
|
totalLinesAdded: projectConfig.lastLinesAdded ?? 0,
|
|
totalLinesRemoved: projectConfig.lastLinesRemoved ?? 0,
|
|
lastDuration: projectConfig.lastDuration,
|
|
modelUsage,
|
|
}
|
|
}
|
|
|
|
/**
|
|
* Restores cost state from project config when resuming a session.
|
|
* Only restores if the session ID matches the last saved session.
|
|
* @returns true if cost state was restored, false otherwise
|
|
*/
|
|
export function restoreCostStateForSession(sessionId: string): boolean {
|
|
const data = getStoredSessionCosts(sessionId)
|
|
if (!data) {
|
|
return false
|
|
}
|
|
setCostStateForRestore(data)
|
|
return true
|
|
}
|
|
|
|
/**
|
|
* Saves the current session's costs to project config.
|
|
* Call this before switching sessions to avoid losing accumulated costs.
|
|
*/
|
|
export function saveCurrentSessionCosts(fpsMetrics?: FpsMetrics): void {
|
|
saveCurrentProjectConfig(current => ({
|
|
...current,
|
|
lastCost: getTotalCostUSD(),
|
|
lastAPIDuration: getTotalAPIDuration(),
|
|
lastAPIDurationWithoutRetries: getTotalAPIDurationWithoutRetries(),
|
|
lastToolDuration: getTotalToolDuration(),
|
|
lastDuration: getTotalDuration(),
|
|
lastLinesAdded: getTotalLinesAdded(),
|
|
lastLinesRemoved: getTotalLinesRemoved(),
|
|
lastTotalInputTokens: getTotalInputTokens(),
|
|
lastTotalOutputTokens: getTotalOutputTokens(),
|
|
lastTotalCacheCreationInputTokens: getTotalCacheCreationInputTokens(),
|
|
lastTotalCacheReadInputTokens: getTotalCacheReadInputTokens(),
|
|
lastTotalWebSearchRequests: getTotalWebSearchRequests(),
|
|
lastFpsAverage: fpsMetrics?.averageFps,
|
|
lastFpsLow1Pct: fpsMetrics?.low1PctFps,
|
|
lastModelUsage: Object.fromEntries(
|
|
Object.entries(getModelUsage()).map(([model, usage]) => [
|
|
model,
|
|
{
|
|
inputTokens: usage.inputTokens,
|
|
outputTokens: usage.outputTokens,
|
|
cacheReadInputTokens: usage.cacheReadInputTokens,
|
|
cacheCreationInputTokens: usage.cacheCreationInputTokens,
|
|
webSearchRequests: usage.webSearchRequests,
|
|
costUSD: usage.costUSD,
|
|
},
|
|
]),
|
|
),
|
|
lastSessionId: getSessionId(),
|
|
}))
|
|
}
|
|
|
|
function formatCost(cost: number, maxDecimalPlaces: number = 4): string {
|
|
return `$${cost > 0.5 ? round(cost, 100).toFixed(2) : cost.toFixed(maxDecimalPlaces)}`
|
|
}
|
|
|
|
function formatModelUsage(): string {
|
|
const modelUsageMap = getModelUsage()
|
|
if (Object.keys(modelUsageMap).length === 0) {
|
|
return 'Usage: 0 input, 0 output'
|
|
}
|
|
|
|
// Accumulate usage by short name
|
|
const usageByShortName: { [shortName: string]: ModelUsage } = {}
|
|
for (const [model, usage] of Object.entries(modelUsageMap)) {
|
|
const shortName = getCanonicalName(model)
|
|
if (!usageByShortName[shortName]) {
|
|
usageByShortName[shortName] = {
|
|
inputTokens: 0,
|
|
outputTokens: 0,
|
|
cacheReadInputTokens: 0,
|
|
cacheCreationInputTokens: 0,
|
|
webSearchRequests: 0,
|
|
costUSD: 0,
|
|
contextWindow: 0,
|
|
maxOutputTokens: 0,
|
|
}
|
|
}
|
|
const accumulated = usageByShortName[shortName]
|
|
accumulated.inputTokens += usage.inputTokens
|
|
accumulated.outputTokens += usage.outputTokens
|
|
accumulated.cacheReadInputTokens += usage.cacheReadInputTokens
|
|
accumulated.cacheCreationInputTokens += usage.cacheCreationInputTokens
|
|
accumulated.webSearchRequests += usage.webSearchRequests
|
|
accumulated.costUSD += usage.costUSD
|
|
}
|
|
|
|
let result = 'Usage by model:'
|
|
for (const [shortName, usage] of Object.entries(usageByShortName)) {
|
|
let usageString =
|
|
` ${formatNumber(usage.inputTokens)} input, ` +
|
|
`${formatNumber(usage.outputTokens)} output`
|
|
if (usage.cacheReadInputTokens > 0) {
|
|
usageString += `, ${formatNumber(usage.cacheReadInputTokens)} cache read`
|
|
}
|
|
if (usage.cacheCreationInputTokens > 0) {
|
|
usageString += `, ${formatNumber(usage.cacheCreationInputTokens)} cache write`
|
|
}
|
|
if (usage.webSearchRequests > 0) {
|
|
usageString += `, ${formatNumber(usage.webSearchRequests)} web search`
|
|
}
|
|
usageString += ` (${formatCost(usage.costUSD)})`
|
|
result += `\n` + `${shortName}:`.padStart(21) + usageString
|
|
}
|
|
return result
|
|
}
|
|
|
|
export function formatTotalCost(): string {
|
|
const costDisplay =
|
|
formatCost(getTotalCostUSD()) +
|
|
(hasUnknownModelCost()
|
|
? ' (costs may be inaccurate due to usage of unknown models)'
|
|
: '')
|
|
|
|
const modelUsageDisplay = formatModelUsage()
|
|
|
|
return chalk.dim(
|
|
`Total cost: ${costDisplay}\n` +
|
|
`Total duration (API): ${formatDuration(getTotalAPIDuration())}
|
|
Total duration (wall): ${formatDuration(getTotalDuration())}
|
|
Total code changes: ${getTotalLinesAdded()} ${getTotalLinesAdded() === 1 ? 'line' : 'lines'} added, ${getTotalLinesRemoved()} ${getTotalLinesRemoved() === 1 ? 'line' : 'lines'} removed
|
|
${modelUsageDisplay}`,
|
|
)
|
|
}
|
|
|
|
function round(number: number, precision: number): number {
|
|
return Math.round(number * precision) / precision
|
|
}
|
|
|
|
function addToTotalModelUsage(
|
|
cost: number,
|
|
usage: Usage,
|
|
model: string,
|
|
): ModelUsage {
|
|
const modelUsage = getUsageForModel(model) ?? {
|
|
inputTokens: 0,
|
|
outputTokens: 0,
|
|
cacheReadInputTokens: 0,
|
|
cacheCreationInputTokens: 0,
|
|
webSearchRequests: 0,
|
|
costUSD: 0,
|
|
contextWindow: 0,
|
|
maxOutputTokens: 0,
|
|
}
|
|
|
|
modelUsage.inputTokens += usage.input_tokens
|
|
modelUsage.outputTokens += usage.output_tokens
|
|
modelUsage.cacheReadInputTokens += usage.cache_read_input_tokens ?? 0
|
|
modelUsage.cacheCreationInputTokens += usage.cache_creation_input_tokens ?? 0
|
|
modelUsage.webSearchRequests +=
|
|
usage.server_tool_use?.web_search_requests ?? 0
|
|
modelUsage.costUSD += cost
|
|
modelUsage.contextWindow = getContextWindowForModel(model, getSdkBetas())
|
|
modelUsage.maxOutputTokens = getModelMaxOutputTokens(model).default
|
|
return modelUsage
|
|
}
|
|
|
|
export function addToTotalSessionCost(
|
|
cost: number,
|
|
usage: Usage,
|
|
model: string,
|
|
): number {
|
|
const modelUsage = addToTotalModelUsage(cost, usage, model)
|
|
addToTotalCostState(cost, modelUsage, model)
|
|
|
|
const attrs =
|
|
isFastModeEnabled() && usage.speed === 'fast'
|
|
? { model, speed: 'fast' }
|
|
: { model }
|
|
|
|
getCostCounter()?.add(cost, attrs)
|
|
getTokenCounter()?.add(usage.input_tokens, { ...attrs, type: 'input' })
|
|
getTokenCounter()?.add(usage.output_tokens, { ...attrs, type: 'output' })
|
|
getTokenCounter()?.add(usage.cache_read_input_tokens ?? 0, {
|
|
...attrs,
|
|
type: 'cacheRead',
|
|
})
|
|
getTokenCounter()?.add(usage.cache_creation_input_tokens ?? 0, {
|
|
...attrs,
|
|
type: 'cacheCreation',
|
|
})
|
|
|
|
let totalCost = cost
|
|
for (const advisorUsage of getAdvisorUsage(usage)) {
|
|
const advisorCost = calculateUSDCost(advisorUsage.model, advisorUsage)
|
|
logEvent('tengu_advisor_tool_token_usage', {
|
|
advisor_model:
|
|
advisorUsage.model as AnalyticsMetadata_I_VERIFIED_THIS_IS_NOT_CODE_OR_FILEPATHS,
|
|
input_tokens: advisorUsage.input_tokens,
|
|
output_tokens: advisorUsage.output_tokens,
|
|
cache_read_input_tokens: advisorUsage.cache_read_input_tokens ?? 0,
|
|
cache_creation_input_tokens:
|
|
advisorUsage.cache_creation_input_tokens ?? 0,
|
|
cost_usd_micros: Math.round(advisorCost * 1_000_000),
|
|
})
|
|
totalCost += addToTotalSessionCost(
|
|
advisorCost,
|
|
advisorUsage,
|
|
advisorUsage.model,
|
|
)
|
|
}
|
|
return totalCost
|
|
}
|