fix: context overflow compaction and subagent announce improvements (#11664) (thanks @tyler6204)

* initial commit

* feat: implement deriveSessionTotalTokens function and update usage tests

* Added deriveSessionTotalTokens function to calculate total tokens based on usage and context tokens.
* Updated usage tests to include cases for derived session total tokens.
* Refactored session usage calculations in multiple files to utilize the new function for improved accuracy.

* fix: restore overflow truncation fallback + changelog/test hardening (#11551) (thanks @tyler6204)

src/agents/usage.test.ts

@@ -1,5 +1,5 @@
 import { describe, expect, it } from "vitest";
-import { hasNonzeroUsage, normalizeUsage } from "./usage.js";
+import { deriveSessionTotalTokens, hasNonzeroUsage, normalizeUsage } from "./usage.js";
 
 describe("normalizeUsage", () => {
   it("normalizes Anthropic-style snake_case usage", () => {
@@ -46,4 +46,32 @@ describe("normalizeUsage", () => {
     expect(hasNonzeroUsage({ input: 1 })).toBe(true);
     expect(hasNonzeroUsage({ total: 1 })).toBe(true);
   });
+
+  it("caps derived session total tokens to the context window", () => {
+    expect(
+      deriveSessionTotalTokens({
+        usage: {
+          input: 27,
+          cacheRead: 2_400_000,
+          cacheWrite: 0,
+          total: 2_402_300,
+        },
+        contextTokens: 200_000,
+      }),
+    ).toBe(200_000);
+  });
+
+  it("uses prompt tokens when within context window", () => {
+    expect(
+      deriveSessionTotalTokens({
+        usage: {
+          input: 1_200,
+          cacheRead: 300,
+          cacheWrite: 50,
+          total: 2_000,
+        },
+        contextTokens: 200_000,
+      }),
+    ).toBe(1_550);
+  });
 });