feat(core): update Copilot for token-based billing (#30181)

packages/opencode/src/session/llm.ts

@@ -280,6 +280,8 @@ const live: Layer.Layer<
       return {
         type: "ai-sdk" as const,
         result: streamText({
+          // Copilot returns the authoritative billed amount only in provider-specific response fields.
+          includeRawChunks: input.model.providerID.includes("github-copilot"),
           onError(error) {
             l.error("stream error", {
               error,

packages/opencode/src/session/llm/ai-sdk.ts

@@ -14,6 +14,7 @@ export function adapterState() {
     currentTextID: undefined as string | undefined,
     currentReasoningID: undefined as string | undefined,
     toolNames: {} as Record<string, string>,
+    copilotTotalNanoAiu: undefined as number | undefined,
   }
 }
 
@@ -26,6 +27,20 @@ function providerMetadata(value: unknown): ProviderMetadata | undefined {
   return Schema.is(ProviderMetadata)(value) ? value : undefined
 }
 
+// Temporary AI SDK bridge: Copilot billing survives only in raw provider chunks here.
+// Move this extraction into @opencode-ai/llm when Copilot is handled by the native runtime.
+function copilotTotalNanoAiu(value: unknown) {
+  if (!value || typeof value !== "object") return
+  const raw = value as Record<string, unknown>
+  const response =
+    raw.response && typeof raw.response === "object" ? (raw.response as Record<string, unknown>) : undefined
+  const usage = raw.copilot_usage ?? response?.copilot_usage
+  if (!usage || typeof usage !== "object") return
+  const total = (usage as Record<string, unknown>).total_nano_aiu
+  if (typeof total !== "number" || !Number.isFinite(total) || total < 0) return
+  return total
+}
+
 function usage(value: unknown) {
   if (!value || typeof value !== "object") return undefined
   const item = value as {
@@ -70,14 +85,28 @@ export function toLLMEvents(
       return Effect.succeed([LLMEvent.stepStart({ index: state.step })])
 
     case "finish-step":
-      return Effect.sync(() => [
-        LLMEvent.stepFinish({
-          index: state.step++,
-          reason: finishReason(event.finishReason),
-          usage: usage(event.usage),
-          providerMetadata: providerMetadata(event.providerMetadata),
-        }),
-      ])
+      return Effect.sync(() => {
+        const original = providerMetadata(event.providerMetadata)
+        const metadata =
+          state.copilotTotalNanoAiu === undefined
+            ? original
+            : {
+                ...original,
+                copilot: {
+                  ...original?.copilot,
+                  totalNanoAiu: state.copilotTotalNanoAiu,
+                },
+              }
+        state.copilotTotalNanoAiu = undefined
+        return [
+          LLMEvent.stepFinish({
+            index: state.step++,
+            reason: finishReason(event.finishReason),
+            usage: usage(event.usage),
+            providerMetadata: metadata,
+          }),
+        ]
+      })
 
     case "finish":
       return Effect.sync(() => {
@@ -238,11 +267,16 @@ export function toLLMEvents(
     case "abort":
     case "source":
     case "file":
-    case "raw":
     case "tool-output-denied":
     case "tool-approval-request":
       return Effect.succeed([])
 
+    case "raw":
+      return Effect.sync(() => {
+        state.copilotTotalNanoAiu = copilotTotalNanoAiu(event.rawValue) ?? state.copilotTotalNanoAiu
+        return []
+      })
+
     default: {
       const _exhaustive: never = event
       void _exhaustive

packages/opencode/src/session/session.ts

@@ -436,18 +436,22 @@ export const getUsage = (input: { model: Provider.Model; usage: Usage; metadata?
     (input.model.cost?.experimentalOver200K && contextTokens > 200_000
       ? input.model.cost.experimentalOver200K
       : input.model.cost)
+  const totalNanoAiu = input.metadata?.["copilot"]?.["totalNanoAiu"]
   return {
-    cost: safe(
-      new Decimal(0)
-        .add(new Decimal(tokens.input).mul(costInfo?.input ?? 0).div(1_000_000))
-        .add(new Decimal(tokens.output).mul(costInfo?.output ?? 0).div(1_000_000))
-        .add(new Decimal(tokens.cache.read).mul(costInfo?.cache?.read ?? 0).div(1_000_000))
-        .add(new Decimal(tokens.cache.write).mul(costInfo?.cache?.write ?? 0).div(1_000_000))
-        // TODO: update models.dev to have better pricing model, for now:
-        // charge reasoning tokens at the same rate as output tokens
-        .add(new Decimal(tokens.reasoning).mul(costInfo?.output ?? 0).div(1_000_000))
-        .toNumber(),
-    ),
+    cost:
+      typeof totalNanoAiu === "number" && Number.isFinite(totalNanoAiu) && totalNanoAiu >= 0
+        ? new Decimal(totalNanoAiu).div(100_000_000_000).toNumber()
+        : safe(
+            new Decimal(0)
+              .add(new Decimal(tokens.input).mul(costInfo?.input ?? 0).div(1_000_000))
+              .add(new Decimal(tokens.output).mul(costInfo?.output ?? 0).div(1_000_000))
+              .add(new Decimal(tokens.cache.read).mul(costInfo?.cache?.read ?? 0).div(1_000_000))
+              .add(new Decimal(tokens.cache.write).mul(costInfo?.cache?.write ?? 0).div(1_000_000))
+              // TODO: update models.dev to have better pricing model, for now:
+              // charge reasoning tokens at the same rate as output tokens
+              .add(new Decimal(tokens.reasoning).mul(costInfo?.output ?? 0).div(1_000_000))
+              .toNumber(),
+          ),
     tokens,
   }
 }