模型不在价格目录里时运行金额写「金额无法估算」,不写 $0:真实运行里 token 记到了上百万,金额却是 $0,看着像没花钱。llm.end 发出时,用了 token、模型却不在价格目录里的标 unpriced(目录里标 0 价的本地模型不算);运行用量按 llm.end 数出 unpriced_calls,成功的运行也补上(状态里的用量分不出 0 是免费还是没价)。运行详情、画布运行面板、航迹的金额:一分都没估出来写「金额无法估算」,估出一部分写「≥ $x」,悬停说几次调用不在价格目录中。check-trace 补断言;流式用量测试和注释里的真实调用次数换成概括说法

This commit is contained in:
ThearchyHelios
2026-10-04 12:27:38 +08:00
parent 720f842b82
commit 46330dfd96
11 changed files with 151 additions and 20 deletions
+19 -1
View File
@@ -46,7 +46,7 @@ import type {
CatalogCardinality, CatalogMeasure, CatalogProfileNumberKey, CatalogSource, CatalogStatus, CatalogTableKind, NodeType, SnapshotReasonCode,
SqlCheckCode, SqlCheckLevel, ToolTrust,
} from '../types'
import { formatNumber } from './format'
import { formatCost, formatNumber } from './format'
export const TERMS = {
workflow: '工作流',
@@ -651,6 +651,24 @@ export const JUDGE_ON_UNSUPPORTED_LABEL: Record<string, string> = {
}
/** 设置页「证据裁判」一组(后端 engine/judge.py 的 JUDGE_DEFAULTS) */
/** 运行的金额。有调用的模型不在价格目录中时金额估不出来,不写「$0」(看着像没花钱) */
export const COST_TEXT = {
unpriced: '金额无法估算',
/** 悬停说明,n 是估不出金额的调用次数 */
unpricedTitle: (n: number) => `${formatNumber(n)} 次调用的模型不在价格目录中,金额无法估算,未计入`,
} as const
/**
* 运行级金额的写法。unpriced 是估不出金额的调用次数:一分都没估出来写「金额无法估算」,估出了一部分写「≥ $x」;
* 运行中(approx)只算已上报的调用,也写「≥」。没有金额返回 null,由调用方写占位
*/
export function runCostText(usd: number | null | undefined, unpriced: number, approx = false): string | null {
const known = typeof usd === 'number' && Number.isFinite(usd)
if (unpriced > 0 && !(known && usd > 0)) return COST_TEXT.unpriced
if (!known) return null
return `${(approx || unpriced > 0) && usd > 0 ? '≥ ' : ''}${formatCost(usd)}`
}
export const JUDGE_SETTING_TEXT = {
label: '证据裁判',
hint: '报告中的结论句(如「增长主要来自新客首单」)由另一个模型按证据逐句判断:正式运行由报告撰写节点当场裁判,探索运行在点击时逐句裁判。判断由模型给出,不是系统核对,界面上一律标注「非确定」。',
+5 -2
View File
@@ -10,7 +10,7 @@ import { type StatusCode } from '../../lib/status'
import { isExecuting, liveAt, project, type Projection, type RunPhase, type Trace } from '../../run/trace'
import { useRunClock } from '../../run/useRunClock'
import type { Approval, Run } from '../../types'
import { UNSAVED_HINT, isUnsaved, runName } from '../../lib/terms'
import { COST_TEXT, UNSAVED_HINT, isUnsaved, runCostText, runName } from '../../lib/terms'
import {
LONG_WAIT_MS, ageMs, cancelReason, runScope, runTiming, type RunTiming,
} from './model'
@@ -92,6 +92,9 @@ export function Telemetry({ run, trace, phase, code, streaming, pending, labelOf
const tokens = settled || !streaming ? tokensSettled ?? (liveTokens || undefined) : liveTokens
const cost = settled || !streaming ? (isNum(usage.cost_usd) ? usage.cost_usd : trace.costUsd || undefined) : trace.costUsd
const approx = streaming && !settled
// 金额估不出来的调用(模型不在价格目录中):有的话不写 $0
const unpriced = (settled || !streaming ? (isNum(usage.unpriced_calls) ? usage.unpriced_calls : undefined) : undefined)
?? trace.unpricedCalls
const running = Object.values(trace.nodes).filter(isExecuting)
const waitingId = trace.waitingNodeId ?? pending?.[0]?.node_id
@@ -156,7 +159,7 @@ export function Telemetry({ run, trace, phase, code, streaming, pending, labelOf
<Value data="tokens">
{tokens ? <>{approx && '≥ '}{formatTokens(tokens, { compact: true })}</> : NONE}
</Value>
<Sub>{isNum(cost) && cost > 0 ? `${approx ? '≥ ' : ''}${formatCost(cost)}` : isNum(cost) ? formatCost(cost) : ' '}</Sub>
<Sub title={unpriced ? COST_TEXT.unpricedTitle(unpriced) : undefined}>{runCostText(cost, unpriced, approx) ?? ' '}</Sub>
</Cell>
</div>
)
+4 -2
View File
@@ -11,7 +11,7 @@ import { explainRunError } from '../../lib/explain'
import {
NONE, formatCost, formatDateTime, formatNumber, formatOffset, formatSpan, formatTokens, shortId,
} from '../../lib/format'
import { runClassLabel, nodeTypeLabel } from '../../lib/terms'
import { COST_TEXT, runClassLabel, nodeTypeLabel, runCostText } from '../../lib/terms'
import { topology, type GraphLike } from '../../run/derive'
import {
isActivePhase, isSettled, liveAt, project, type NodeState, type Projection, type RunPhase, type Trace,
@@ -245,7 +245,9 @@ function Readout({
sub={tokens ? `输入 ${formatNumber(proj.tokensIn)} · 输出 ${formatNumber(proj.tokensOut)}` : undefined}>
{tokens == null ? NONE : formatTokens(tokens, { compact: true })}
</Metric>
<Metric label="成本" data="cost">{!metered || proj.costUsd == null ? NONE : formatCost(proj.costUsd)}</Metric>
<Metric label="成本" data="cost" title={trace.unpricedCalls ? COST_TEXT.unpricedTitle(trace.unpricedCalls) : undefined}>
{!metered || proj.costUsd == null ? NONE : runCostText(proj.costUsd, trace.unpricedCalls) ?? NONE}
</Metric>
</div>
<div className="runs-trace-cols">
+9 -4
View File
@@ -8,7 +8,7 @@ import { confirmDialog, Kbd, Spinner, StatusBadge, toast } from '../components/u
import { formatCost, formatDuration, formatLapse, formatOffset, formatSpan, formatTokens, NONE } from '../lib/format'
import { isTypingTarget, matchShortcut } from '../lib/keys'
import { statusMeta, STATUS, type StatusCode } from '../lib/status'
import { issuanceLabel, runClassLabel } from '../lib/terms'
import { COST_TEXT, issuanceLabel, runClassLabel, runCostText } from '../lib/terms'
import { lastStampOf, projectSettled, useDock, waitedMs } from '../canvas/RunTimeline'
import { structureSig, useStudio } from '../store/studio'
import type { RunEvent } from '../types'
@@ -91,6 +91,8 @@ export interface RunGlance {
series: [number, number][]
tokens: number | null
cost: number | null
/** 金额估不出来的调用次数(模型不在价格目录中);有的话金额不写 $0 */
unpriced: number
/** 这一段执行还剩多少时间;null = 不知道上限或眼下不在计时 */
remainingMs: number | null
limitMs: number | null
@@ -220,6 +222,7 @@ export function useRunGlance(active: boolean): RunGlance {
const replayTok = proj.tokensIn != null && proj.tokensOut != null ? proj.tokensIn + proj.tokensOut : null
const tokens = replayAt != null ? replayTok : backendTok ?? (seen ? usage.tokensIn + usage.tokensOut : null)
const cost = replayAt != null ? proj.costUsd ?? null : backendCost ?? (seen ? usage.costUsd : null)
const unpriced = (settledUsage ? num(runUsage.unpriced_calls) : null) ?? trace.unpricedCalls
// 时限按"这一段执行"计:等人工审批时执行已经结束,那段不算(和后端一致)
const drive = trace.drives[trace.drives.length - 1]
@@ -253,7 +256,7 @@ export function useRunGlance(active: boolean): RunGlance {
headline: headlineOf(trace, phase, states, at, label, runError, replayAt == null ? cancelled : ''),
executing: phase === 'running' && cells.some((c) => c.state === 'running' && !trace.nodes[c.id]?.looping),
cells, done, visited, parallelNow: proj.parallelNow, series: trace.parallelSeries,
tokens, cost, remainingMs, limitMs, attention,
tokens, cost, unpriced, remainingMs, limitMs, attention,
failedNodeId: trace.failedNodeId, waitingNodeId: trace.waitingNodeId,
}
}
@@ -591,7 +594,7 @@ export function RunCapsule() {
<span className="sf-cap-nodes tnum hidden lg:inline" title="完成的节点 / 全部节点">{nodesText}</span>
<span className="sf-cap-sep hidden xl:block" />
<span className="sf-cap-usage tnum hidden xl:inline">
{tokens}{g.cost ? ` · ${formatCost(g.cost)}` : ''}
{tokens}{g.cost || g.unpriced ? ` · ${runCostText(g.cost, g.unpriced)}` : ''}
</span>
</>
)}
@@ -654,7 +657,9 @@ export function RunCapsule() {
<div className="sf-metric">
<div className="sf-metric-k">用量</div>
<div className="sf-metric-v tnum">{tokens}</div>
<div className="sf-metric-s tnum">{g.cost != null ? `≈ ${formatCost(g.cost)}` : NONE}</div>
<div className="sf-metric-s tnum" title={g.unpriced ? COST_TEXT.unpricedTitle(g.unpriced) : undefined}>
{g.unpriced ? runCostText(g.cost, g.unpriced) : g.cost != null ? `≈ ${formatCost(g.cost)}` : NONE}
</div>
</div>
<div className="sf-metric">
<div className="sf-metric-k">时限</div>
+5 -1
View File
@@ -96,6 +96,8 @@ export interface Trace {
tokensIn: number
tokensOut: number
costUsd: number
/** 金额估不出来的调用次数(llm.end 标了 unpriced:模型不在价格目录中)。这时 costUsd 的 0 不是「没花钱」 */
unpricedCalls: number
failedNodeId?: string
waitingNodeId?: string
issuance?: {
@@ -238,7 +240,7 @@ export const lastEventAt = (t: Trace): number => t.book.clock
export function emptyTrace(): Trace {
return {
phase: 'idle', waitMs: 0, nodes: {}, tokensIn: 0, tokensOut: 0, costUsd: 0,
phase: 'idle', waitMs: 0, nodes: {}, tokensIn: 0, tokensOut: 0, costUsd: 0, unpricedCalls: 0,
lastSeq: 0, parallelSeries: [], usageSeries: [], timed: true, drives: [], waits: [], phases: [],
lastReplay: false,
book: { clock: 0, awaiting: false, dispatchFrom: {}, exactDispatch: {}, asking: {} },
@@ -673,6 +675,7 @@ export function foldEvent(t: Trace, ev: RunEvent): Trace {
next.tokensIn += inTok
next.tokensOut += outTok
next.costUsd += cost
if (d.unpriced === true) next.unpricedCalls += 1
next.usageSeries = [...next.usageSeries, [at, next.tokensIn, next.tokensOut, next.costUsd]]
if (nodeId) {
const n = node(nodeId)
@@ -816,6 +819,7 @@ export function foldEvent(t: Trace, ev: RunEvent): Trace {
next.tokensIn = num(u.input_tokens) ?? next.tokensIn
next.tokensOut = num(u.output_tokens) ?? next.tokensOut
next.costUsd = num(u.cost_usd) ?? next.costUsd
next.unpricedCalls = num(u.unpriced_calls) ?? next.unpricedCalls
}
const timing = d.timing
if (timing && num(timing.wall_ms) != null) {
+2
View File
@@ -110,6 +110,8 @@ export interface RunUsage {
input_tokens?: number
output_tokens?: number
cost_usd?: number
/** 金额估不出来的调用次数(模型不在价格目录中),cost_usd 只是估得出的那部分。没有这种调用时不给 */
unpriced_calls?: number
[key: string]: any
}