fix: avoid logging stale anthropic usage (#1501) (thanks @parubets)

src/agents/anthropic-payload-log.test.ts

@@ -76,6 +76,43 @@ describe("createAnthropicPayloadLogger", () => {
     expect(event.usage).toEqual({ input: 12 });
   });
 
+  it("skips usage when no new assistant message was added", () => {
+    const lines: string[] = [];
+    const logger = createAnthropicPayloadLogger({
+      cfg: {
+        diagnostics: {
+          anthropicPayloadLog: {
+            enabled: true,
+          },
+        },
+      },
+      env: {},
+      modelApi: "anthropic-messages",
+      writer: {
+        filePath: "memory",
+        write: (line) => lines.push(line),
+      },
+    });
+
+    logger?.recordUsage(
+      [
+        {
+          role: "assistant",
+          usage: {
+            input: 1,
+          },
+        } as unknown as {
+          role: string;
+          usage: { input: number };
+        },
+      ],
+      undefined,
+      1,
+    );
+
+    expect(lines.length).toBe(0);
+  });
+
   it("records request payloads and forwards onPayload", async () => {
     const lines: string[] = [];
     let forwarded: unknown;

src/agents/anthropic-payload-log.ts

@@ -110,8 +110,12 @@ function isAnthropicModel(model: Model<Api> | undefined | null): boolean {
   return (model as { api?: unknown })?.api === "anthropic-messages";
 }
 
-function findLastAssistantUsage(messages: AgentMessage[]): Record<string, unknown> | null {
+function findLastAssistantUsage(
+  messages: AgentMessage[],
+  minIndex = 0,
+): Record<string, unknown> | null {
   for (let i = messages.length - 1; i >= 0; i -= 1) {
+    if (i < minIndex) break;
     const msg = messages[i] as { role?: unknown; usage?: unknown };
     if (msg?.role === "assistant" && msg.usage && typeof msg.usage === "object") {
       return msg.usage as Record<string, unknown>;
@@ -124,7 +128,7 @@ export type AnthropicPayloadLogger = {
   enabled: true;
   filePath: string;
   wrapStreamFn: (streamFn: StreamFn) => StreamFn;
-  recordUsage: (messages: AgentMessage[], error?: unknown) => void;
+  recordUsage: (messages: AgentMessage[], error?: unknown, baselineMessageCount?: number) => void;
 };
 
 export function createAnthropicPayloadLogger(params: {
@@ -184,8 +188,12 @@ export function createAnthropicPayloadLogger(params: {
     return wrapped;
   };
 
-  const recordUsage: AnthropicPayloadLogger["recordUsage"] = (messages, error) => {
+  const recordUsage: AnthropicPayloadLogger["recordUsage"] = (
-    const usage = findLastAssistantUsage(messages);
+    messages,
+    error,
+    baselineMessageCount,
+  ) => {
+    const usage = findLastAssistantUsage(messages, baselineMessageCount ?? 0);
     if (!usage) {
       if (error) {
         record({

src/agents/pi-embedded-runner/run/attempt.ts

@@ -643,6 +643,7 @@ export async function runEmbeddedAttempt(
 
       let messagesSnapshot: AgentMessage[] = [];
       let sessionIdUsed = activeSession.sessionId;
+      let promptStartMessageCount = activeSession.messages.length;
       const onAbort = () => {
         const reason = params.abortSignal ? getAbortReason(params.abortSignal) : undefined;
         const timeout = reason ? isTimeoutError(reason) : false;
@@ -714,6 +715,8 @@ export async function runEmbeddedAttempt(
           );
         }
 
+        promptStartMessageCount = activeSession.messages.length;
+
         try {
           // Detect and load images referenced in the prompt for vision-capable models.
           // This eliminates the need for an explicit "view" tool call by injecting
@@ -789,7 +792,7 @@ export async function runEmbeddedAttempt(
           messages: messagesSnapshot,
           note: promptError ? "prompt error" : undefined,
         });
-        anthropicPayloadLogger?.recordUsage(messagesSnapshot, promptError);
+        anthropicPayloadLogger?.recordUsage(messagesSnapshot, promptError, promptStartMessageCount);
 
         // Run agent_end hooks to allow plugins to analyze the conversation
         // This is fire-and-forget, so we don't await