janpeter/Scrum4Me
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

feat(PBI-67/ST-1300): cost-attribution voor thinking-tokens + admin UI

Browse source 
T-792: token-stats + token-history rekenen actual_thinking_tokens nu
mee in de totale kosten (tegen input-rate, conform Anthropic billing).
COALESCE-veilig zodat oude rijen 0 bijdragen i.p.v. NaN. Nieuwe export
`getTokenStatsByKind` aggregeert tokens en kosten per ClaudeJob.kind
zodat we relatieve uitgaven van IDEA_GRILL/IDEA_MAKE_PLAN/PLAN_CHAT/
TASK_IMPLEMENTATION/SPRINT_IMPLEMENTATION kunnen zien.

T-793: admin/jobs Kosten-tabel toont:
  - Nieuwe kolom 'Thinking' (aantal verbruikte thinking-tokens)
  - Mismatch-marker (rood) als requested_model afwijkt van actuele
    model_id — duidt op een worker die de CLI-flag niet doorgaf.
    Tooltip toont aangevraagd model. Geen Sentry/log-noise.

Page-level cost-berekening volgt dezelfde formule (input_price ×
thinking_tokens). 563 tests groen.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
Janpeter Visser 2026-05-08 11:16:22 +02:00
parent 86472674f5
commit d0bebda3ac
4 changed files with 99 additions and 8 deletions
Download patch file Download diff file Expand all files Collapse all files

7
app/(app)/admin/jobs/page.tsx
View file

@ -21,6 +21,10 @@ export default async function AdminJobsPage() {
output_tokens: true,
cache_read_tokens: true,
cache_write_tokens: true,
actual_thinking_tokens: true,
requested_model: true,
requested_thinking_budget: true,
requested_permission_mode: true,
user: { select: { username: true } },
product: { select: { name: true } },
},
@ -36,7 +40,8 @@ export default async function AdminJobsPage() {
(job.input_tokens ?? 0) * Number(p.input_price_per_1m) / 1_000_000 +
(job.output_tokens ?? 0) * Number(p.output_price_per_1m) / 1_000_000 +
(job.cache_read_tokens ?? 0) * Number(p.cache_read_price_per_1m) / 1_000_000 +
(job.cache_write_tokens ?? 0) * Number(p.cache_write_price_per_1m) / 1_000_000
(job.cache_write_tokens ?? 0) * Number(p.cache_write_price_per_1m) / 1_000_000 +
(job.actual_thinking_tokens ?? 0) * Number(p.input_price_per_1m) / 1_000_000
return { ...job, cost_usd: cost }
})

20
components/admin/jobs-table.tsx
View file

@ -24,6 +24,10 @@ type Job = {
pr_url: string | null
error: string | null
model_id: string | null
actual_thinking_tokens: number | null
requested_model: string | null
requested_thinking_budget: number | null
requested_permission_mode: string | null
cost_usd: number | null
}
@ -131,13 +135,24 @@ function CostRow({ job }: { job: Job }) {
function handleCancel() { startTransition(() => cancelJobAction(job.id)) }
function handleDelete() { startTransition(() => deleteJobAction(job.id)) }
const costLabel = job.cost_usd != null ? `$${job.cost_usd.toFixed(4)}` : '—'
const thinkingLabel = job.actual_thinking_tokens != null ? job.actual_thinking_tokens.toLocaleString('nl-NL') : '—'
const modelMismatch = job.requested_model != null && job.model_id != null && job.requested_model !== job.model_id
const modelTitle = job.requested_model
? `Aangevraagd: ${job.requested_model}${modelMismatch ? ' (mismatch met actueel)' : ''}`
: undefined
return (
<TableRow>
<TableCell className="font-mono text-xs text-muted-foreground">{job.id.slice(0, 8)}</TableCell>
<TableCell className="text-sm">{job.user.username}</TableCell>
<TableCell className="text-sm">{job.product.name}</TableCell>
<TableCell className="text-xs">{KIND_LABEL[job.kind] ?? job.kind}</TableCell>
<TableCell className="text-xs text-muted-foreground">{job.model_id ?? '—'}</TableCell>
<TableCell
className={`text-xs ${modelMismatch ? 'text-priority-high font-medium' : 'text-muted-foreground'}`}
title={modelTitle}
>
{job.model_id ?? '—'}
</TableCell>
<TableCell className="text-xs font-mono text-muted-foreground">{thinkingLabel}</TableCell>
<TableCell className="text-xs font-mono">{costLabel}</TableCell>
<TableCell className="text-xs text-muted-foreground">
{new Date(job.created_at).toLocaleString('nl-NL', { dateStyle: 'short', timeStyle: 'short' })}
@ -164,6 +179,7 @@ function CostsTable({ jobs }: { jobs: Job[] }) {
<TableHead>Product</TableHead>
<TableHead>Type</TableHead>
<TableHead>Model</TableHead>
<TableHead>Thinking</TableHead>
<TableHead>Kosten (USD)</TableHead>
<TableHead>Aangemaakt</TableHead>
<TableHead className="text-right">Acties</TableHead>
@ -172,7 +188,7 @@ function CostsTable({ jobs }: { jobs: Job[] }) {
<TableBody>
{jobs.length === 0 && (
<TableRow>
<TableCell colSpan={8} className="text-center text-muted-foreground py-8">
<TableCell colSpan={9} className="text-center text-muted-foreground py-8">
Geen jobs gevonden
</TableCell>
</TableRow>

12
lib/insights/token-history.ts
View file

@ -57,12 +57,13 @@ export async function getSprintTokenHistory(
sp.id AS sprint_id,
sp.code AS sprint_code,
sp.sprint_goal,
COALESCE(SUM(cj.input_tokens + cj.output_tokens + cj.cache_read_tokens + cj.cache_write_tokens), 0) AS total_tokens,
COALESCE(SUM(cj.input_tokens + cj.output_tokens + cj.cache_read_tokens + cj.cache_write_tokens + COALESCE(cj.actual_thinking_tokens, 0)), 0) AS total_tokens,
SUM(
cj.input_tokens * mp.input_price_per_1m / 1000000.0
+ cj.output_tokens * mp.output_price_per_1m / 1000000.0
+ cj.cache_read_tokens * mp.cache_read_price_per_1m / 1000000.0
+ cj.cache_write_tokens * mp.cache_write_price_per_1m / 1000000.0
+ COALESCE(cj.actual_thinking_tokens, 0) * mp.input_price_per_1m / 1000000.0
) FILTER (WHERE cj.input_tokens IS NOT NULL) AS total_cost,
COUNT(*) FILTER (WHERE cj.input_tokens IS NOT NULL) AS job_count
FROM claude_jobs cj
@ -82,12 +83,13 @@ export async function getSprintTokenHistory(
sp.id AS sprint_id,
sp.code AS sprint_code,
sp.sprint_goal,
COALESCE(SUM(cj.input_tokens + cj.output_tokens + cj.cache_read_tokens + cj.cache_write_tokens), 0) AS total_tokens,
COALESCE(SUM(cj.input_tokens + cj.output_tokens + cj.cache_read_tokens + cj.cache_write_tokens + COALESCE(cj.actual_thinking_tokens, 0)), 0) AS total_tokens,
SUM(
cj.input_tokens * mp.input_price_per_1m / 1000000.0
+ cj.output_tokens * mp.output_price_per_1m / 1000000.0
+ cj.cache_read_tokens * mp.cache_read_price_per_1m / 1000000.0
+ cj.cache_write_tokens * mp.cache_write_price_per_1m / 1000000.0
+ COALESCE(cj.actual_thinking_tokens, 0) * mp.input_price_per_1m / 1000000.0
) FILTER (WHERE cj.input_tokens IS NOT NULL) AS total_cost,
COUNT(*) FILTER (WHERE cj.input_tokens IS NOT NULL) AS job_count
FROM claude_jobs cj
@ -118,12 +120,13 @@ export async function getDayTokenData(userId: string, sprintId: string): Promise
const rows = await prisma.$queryRaw<RawDayRow[]>`
SELECT
DATE(cj.finished_at) AS day,
COALESCE(SUM(cj.input_tokens + cj.output_tokens + cj.cache_read_tokens + cj.cache_write_tokens), 0) AS total_tokens,
COALESCE(SUM(cj.input_tokens + cj.output_tokens + cj.cache_read_tokens + cj.cache_write_tokens + COALESCE(cj.actual_thinking_tokens, 0)), 0) AS total_tokens,
SUM(
cj.input_tokens * mp.input_price_per_1m / 1000000.0
+ cj.output_tokens * mp.output_price_per_1m / 1000000.0
+ cj.cache_read_tokens * mp.cache_read_price_per_1m / 1000000.0
+ cj.cache_write_tokens * mp.cache_write_price_per_1m / 1000000.0
+ COALESCE(cj.actual_thinking_tokens, 0) * mp.input_price_per_1m / 1000000.0
) FILTER (WHERE cj.input_tokens IS NOT NULL) AS total_cost
FROM claude_jobs cj
JOIN tasks t ON cj.task_id = t.id
@ -152,12 +155,13 @@ export async function getPbiTokenAggregates(userId: string, sprintId: string): P
p.id AS pbi_id,
p.code AS pbi_code,
p.title AS pbi_title,
COALESCE(SUM(cj.input_tokens + cj.output_tokens + cj.cache_read_tokens + cj.cache_write_tokens), 0) AS total_tokens,
COALESCE(SUM(cj.input_tokens + cj.output_tokens + cj.cache_read_tokens + cj.cache_write_tokens + COALESCE(cj.actual_thinking_tokens, 0)), 0) AS total_tokens,
SUM(
cj.input_tokens * mp.input_price_per_1m / 1000000.0
+ cj.output_tokens * mp.output_price_per_1m / 1000000.0
+ cj.cache_read_tokens * mp.cache_read_price_per_1m / 1000000.0
+ cj.cache_write_tokens * mp.cache_write_price_per_1m / 1000000.0
+ COALESCE(cj.actual_thinking_tokens, 0) * mp.input_price_per_1m / 1000000.0
) FILTER (WHERE cj.input_tokens IS NOT NULL) AS total_cost
FROM claude_jobs cj
JOIN tasks t ON cj.task_id = t.id

68
lib/insights/token-stats.ts
View file

@ -16,10 +16,18 @@ export interface TokenJobRow {
outputTokens: number | null
cacheReadTokens: number | null
cacheWriteTokens: number | null
thinkingTokens: number | null
costUsd: number | null
durationSeconds: number | null
}
export interface TokenStatsByKindRow {
kind: string
jobCount: number
totalTokens: number
totalCostUsd: number
}
export interface TokenStatsResult {
kpi: TokenKpi
jobs: TokenJobRow[]
@ -41,10 +49,18 @@ type RawJobRow = {
output_tokens: number | null
cache_read_tokens: number | null
cache_write_tokens: number | null
actual_thinking_tokens: number | null
cost_usd: number | null
duration_seconds: number | null
}
type RawByKindRow = {
kind: string
job_count: bigint
total_tokens: bigint
total_cost: number | null
}
const EMPTY_KPI: TokenKpi = { totalTokens: 0, totalCostUsd: 0, avgCostPerJob: 0, jobCount: 0 }
export async function getTokenStats(userId: string, sprintId: string): Promise<TokenStatsResult> {
@ -53,18 +69,20 @@ export async function getTokenStats(userId: string, sprintId: string): Promise<T
const [kpiRows, jobRows] = await Promise.all([
prisma.$queryRaw<RawKpiRow[]>`
SELECT
COALESCE(SUM(cj.input_tokens + cj.output_tokens + cj.cache_read_tokens + cj.cache_write_tokens), 0) AS total_tokens,
COALESCE(SUM(cj.input_tokens + cj.output_tokens + cj.cache_read_tokens + cj.cache_write_tokens + COALESCE(cj.actual_thinking_tokens, 0)), 0) AS total_tokens,
SUM(
cj.input_tokens * mp.input_price_per_1m / 1000000.0
+ cj.output_tokens * mp.output_price_per_1m / 1000000.0
+ cj.cache_read_tokens * mp.cache_read_price_per_1m / 1000000.0
+ cj.cache_write_tokens * mp.cache_write_price_per_1m / 1000000.0
+ COALESCE(cj.actual_thinking_tokens, 0) * mp.input_price_per_1m / 1000000.0
) FILTER (WHERE cj.input_tokens IS NOT NULL) AS total_cost,
AVG(
cj.input_tokens * mp.input_price_per_1m / 1000000.0
+ cj.output_tokens * mp.output_price_per_1m / 1000000.0
+ cj.cache_read_tokens * mp.cache_read_price_per_1m / 1000000.0
+ cj.cache_write_tokens * mp.cache_write_price_per_1m / 1000000.0
+ COALESCE(cj.actual_thinking_tokens, 0) * mp.input_price_per_1m / 1000000.0
) FILTER (WHERE cj.input_tokens IS NOT NULL) AS avg_cost,
COUNT(*) FILTER (WHERE cj.input_tokens IS NOT NULL) AS job_count
FROM claude_jobs cj
@ -85,11 +103,13 @@ export async function getTokenStats(userId: string, sprintId: string): Promise<T
cj.output_tokens,
cj.cache_read_tokens,
cj.cache_write_tokens,
cj.actual_thinking_tokens,
CASE WHEN cj.input_tokens IS NOT NULL THEN
cj.input_tokens * mp.input_price_per_1m / 1000000.0
+ cj.output_tokens * mp.output_price_per_1m / 1000000.0
+ cj.cache_read_tokens * mp.cache_read_price_per_1m / 1000000.0
+ cj.cache_write_tokens * mp.cache_write_price_per_1m / 1000000.0
+ COALESCE(cj.actual_thinking_tokens, 0) * mp.input_price_per_1m / 1000000.0
END AS cost_usd,
EXTRACT(EPOCH FROM (cj.finished_at - cj.claimed_at)) AS duration_seconds
FROM claude_jobs cj
@ -122,8 +142,54 @@ export async function getTokenStats(userId: string, sprintId: string): Promise<T
outputTokens: r.output_tokens,
cacheReadTokens: r.cache_read_tokens,
cacheWriteTokens: r.cache_write_tokens,
thinkingTokens: r.actual_thinking_tokens,
costUsd: r.cost_usd != null ? Number(r.cost_usd) : null,
durationSeconds: r.duration_seconds != null ? Number(r.duration_seconds) : null,
})),
}
}
// PBI-67: per-kind aggregatie. Toont totaal tokens + kosten per ClaudeJob.kind
// binnen één sprint zodat we de relatieve uitgaven van IDEA_GRILL vs
// TASK_IMPLEMENTATION etc. kunnen zien. Voor jobs zonder sprint-koppeling
// (idea-jobs) blijven we filteren op user_id + sprint_id; idea-jobs zonder
// task vallen buiten deze view.
export async function getTokenStatsByKind(
userId: string,
sprintId: string,
): Promise<TokenStatsByKindRow[]> {
if (!sprintId) return []
const rows = await prisma.$queryRaw<RawByKindRow[]>`
SELECT
cj.kind::text AS kind,
COUNT(*) FILTER (WHERE cj.input_tokens IS NOT NULL) AS job_count,
COALESCE(SUM(
cj.input_tokens + cj.output_tokens + cj.cache_read_tokens + cj.cache_write_tokens
+ COALESCE(cj.actual_thinking_tokens, 0)
), 0) AS total_tokens,
SUM(
cj.input_tokens * mp.input_price_per_1m / 1000000.0
+ cj.output_tokens * mp.output_price_per_1m / 1000000.0
+ cj.cache_read_tokens * mp.cache_read_price_per_1m / 1000000.0
+ cj.cache_write_tokens * mp.cache_write_price_per_1m / 1000000.0
+ COALESCE(cj.actual_thinking_tokens, 0) * mp.input_price_per_1m / 1000000.0
) FILTER (WHERE cj.input_tokens IS NOT NULL) AS total_cost
FROM claude_jobs cj
JOIN tasks t ON cj.task_id = t.id
JOIN stories s ON t.story_id = s.id
LEFT JOIN model_prices mp ON mp.model_id = cj.model_id
WHERE cj.user_id = ${userId}
AND s.sprint_id = ${sprintId}
AND cj.status = 'DONE'
GROUP BY cj.kind
ORDER BY total_cost DESC NULLS LAST
`
return rows.map((r) => ({
kind: r.kind,
jobCount: Number(r.job_count),
totalTokens: Number(r.total_tokens),
totalCostUsd: Number(r.total_cost ?? 0),
}))
}