File size: 10,706 Bytes
064bfd6 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 | 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, 0 cache read, 0 cache write'
}
// 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)) {
const usageString =
` ${formatNumber(usage.inputTokens)} input, ` +
`${formatNumber(usage.outputTokens)} output, ` +
`${formatNumber(usage.cacheReadInputTokens)} cache read, ` +
`${formatNumber(usage.cacheCreationInputTokens)} cache write` +
(usage.webSearchRequests > 0
? `, ${formatNumber(usage.webSearchRequests)} web search`
: '') +
` (${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
}
|