feat: initial datalake and stats site (#28666)

2026-05-25 17:34:04 -05:00
parent 633b5d6208
commit 5b02ac4d33
68 changed files with 8967 additions and 42 deletions
@@ -0,0 +1,173 @@
+import { and, asc, eq } from "drizzle-orm"
+import { Effect, Layer } from "effect"
+import * as Context from "effect/Context"
+import { DatabaseError, DrizzleClient } from "../database"
+import { modelStat } from "../database/schema"
+import {
+  chunks,
+  collapseRows,
+  inserted,
+  rankBy,
+  statPeriodKey,
+  synthesizeAllTierRows,
+  toStatBaseRow,
+  UPSERT_CHUNK_SIZE,
+  type StatBaseAggregate,
+} from "./stat"
+
+export type ModelStatRow = typeof modelStat.$inferInsert
+export type ModelStatAggregate = StatBaseAggregate & { provider: string; model: string; provider_model: string }
+
+export type ModelStatMetric = {
+  periodStart: Date
+  periodEnd: Date
+  tier: string
+  provider: string
+  model: string
+  sessions: number
+  inputTokens: number
+  outputTokens: number
+  reasoningTokens: number
+  cacheReadTokens: number
+  totalTokens: number
+  inputCostMicrocents: number
+  outputCostMicrocents: number
+  totalCostMicrocents: number
+}
+
+export declare namespace ModelStatRepo {
+  export interface Service {
+    readonly listDaily: () => Effect.Effect<ModelStatMetric[], DatabaseError>
+    readonly upsert: (rows: ModelStatRow[]) => Effect.Effect<void, DatabaseError>
+  }
+}
+
+export class ModelStatRepo extends Context.Service<ModelStatRepo, ModelStatRepo.Service>()(
+  "@opencode/stats/ModelStatRepo",
+) {
+  static readonly layer: Layer.Layer<ModelStatRepo, never, DrizzleClient> = Layer.effect(
+    ModelStatRepo,
+    Effect.gen(function* () {
+      const db = yield* DrizzleClient
+
+      const listDaily = Effect.fn("ModelStatRepo.listDaily")(function* () {
+        return yield* Effect.tryPromise({
+          try: () =>
+            db
+              .select({
+                periodStart: modelStat.period_start,
+                periodEnd: modelStat.period_end,
+                tier: modelStat.tier,
+                provider: modelStat.provider,
+                model: modelStat.model,
+                sessions: modelStat.sessions,
+                inputTokens: modelStat.input_tokens,
+                outputTokens: modelStat.output_tokens,
+                reasoningTokens: modelStat.reasoning_tokens,
+                cacheReadTokens: modelStat.cache_read_tokens,
+                totalTokens: modelStat.total_tokens,
+                inputCostMicrocents: modelStat.input_cost_microcents,
+                outputCostMicrocents: modelStat.output_cost_microcents,
+                totalCostMicrocents: modelStat.total_cost_microcents,
+              })
+              .from(modelStat)
+              .where(and(eq(modelStat.grain, "day"), eq(modelStat.client, "all"), eq(modelStat.source, "all")))
+              .orderBy(asc(modelStat.period_start)),
+          catch: (cause) => DatabaseError.make({ cause }),
+        })
+      })
+
+      const upsert = Effect.fn("ModelStatRepo.upsert")(function* (rows: ModelStatRow[]) {
+        yield* Effect.forEach(
+          chunks(rows, UPSERT_CHUNK_SIZE),
+          (chunk) =>
+            Effect.tryPromise({
+              try: () =>
+                db
+                  .insert(modelStat)
+                  .values(chunk)
+                  .onDuplicateKeyUpdate({
+                    set: {
+                      period_end: inserted("period_end"),
+                      provider_model: inserted("provider_model"),
+                      sessions: inserted("sessions"),
+                      requests: inserted("requests"),
+                      input_tokens: inserted("input_tokens"),
+                      output_tokens: inserted("output_tokens"),
+                      reasoning_tokens: inserted("reasoning_tokens"),
+                      cache_read_tokens: inserted("cache_read_tokens"),
+                      total_tokens: inserted("total_tokens"),
+                      input_cost_microcents: inserted("input_cost_microcents"),
+                      output_cost_microcents: inserted("output_cost_microcents"),
+                      total_cost_microcents: inserted("total_cost_microcents"),
+                      avg_duration_ms: inserted("avg_duration_ms"),
+                      p50_duration_ms: inserted("p50_duration_ms"),
+                      p95_duration_ms: inserted("p95_duration_ms"),
+                      avg_ttfb_ms: inserted("avg_ttfb_ms"),
+                      p50_ttfb_ms: inserted("p50_ttfb_ms"),
+                      p95_ttfb_ms: inserted("p95_ttfb_ms"),
+                      avg_output_tps: inserted("avg_output_tps"),
+                      success_count: inserted("success_count"),
+                      error_count: inserted("error_count"),
+                      sample_count: inserted("sample_count"),
+                      rank_by_tokens: inserted("rank_by_tokens"),
+                      rank_by_requests: inserted("rank_by_requests"),
+                      rank_by_cost: inserted("rank_by_cost"),
+                    },
+                  }),
+              catch: (cause) => DatabaseError.make({ cause }),
+            }),
+          { discard: true },
+        )
+      })
+
+      return ModelStatRepo.of({ listDaily, upsert })
+    }),
+  )
+}
+
+export function rowsFromAggregates(aggregates: ModelStatAggregate[]) {
+  return rankRows([
+    ...synthesizeAllTierRows(
+      collapseRows(aggregates.filter((item) => item.grain === "week").map(toRow), dimensionKey),
+      dimensionKey,
+    ),
+    ...synthesizeAllTierRows(
+      collapseRows(aggregates.filter((item) => item.grain === "day").map(toRow), dimensionKey),
+      dimensionKey,
+    ),
+  ])
+}
+
+function toRow(data: ModelStatAggregate): ModelStatRow {
+  return {
+    ...toStatBaseRow(data),
+    provider: data.provider,
+    model: data.model,
+    provider_model: data.provider_model,
+  }
+}
+
+function rankRows(rows: ModelStatRow[]) {
+  return Object.values(
+    rows.reduce<Record<string, ModelStatRow[]>>((result, row) => {
+      const key = statPeriodKey(row)
+      result[key] = [...(result[key] ?? []), row]
+      return result
+    }, {}),
+  ).flatMap((group) => {
+    const tokenRanks = rankBy(group, (row) => row.total_tokens ?? 0)
+    const requestRanks = rankBy(group, (row) => row.requests ?? 0)
+    const costRanks = rankBy(group, (row) => row.total_cost_microcents ?? 0)
+    return group.map((row) => ({
+      ...row,
+      rank_by_tokens: tokenRanks.get(row) ?? null,
+      rank_by_requests: requestRanks.get(row) ?? null,
+      rank_by_cost: costRanks.get(row) ?? null,
+    }))
+  })
+}
+
+function dimensionKey(row: ModelStatRow) {
+  return [row.provider, row.model].join("\u0000")
+}