fix(memoryFlush): guard transcript-size forced flush against repeated runs (#32358)

The `forceFlushTranscriptBytes` path (introduced in d729ab21) bypasses the
`memoryFlushCompactionCount` guard that prevents repeated flushes within the
same compaction cycle. Once the session transcript exceeds 2 MB, memory flush
fires on every single message — even when token count is well under the
compaction threshold.

Extract `hasAlreadyFlushedForCurrentCompaction()` from the inline guard in
`shouldRunMemoryFlush` and apply it to both the token-based and the
transcript-size trigger paths.

Fixes #32317

Signed-off-by: HCL <chenglunhu@gmail.com>

src/auto-reply/reply/agent-runner-memory.ts

@@ -31,6 +31,7 @@ import {
   resolveModelFallbackOptions,
 } from "./agent-runner-utils.js";
 import {
+  hasAlreadyFlushedForCurrentCompaction,
   resolveMemoryFlushContextWindowTokens,
   resolveMemoryFlushPromptForRun,
   resolveMemoryFlushSettings,
@@ -437,7 +438,9 @@ export async function runMemoryFlushIfNeeded(params: {
         reserveTokensFloor: memoryFlushSettings.reserveTokensFloor,
         softThresholdTokens: memoryFlushSettings.softThresholdTokens,
       })) ||
-    shouldForceFlushByTranscriptSize;
+    (shouldForceFlushByTranscriptSize &&
+      entry != null &&
+      !hasAlreadyFlushedForCurrentCompaction(entry));
 
   if (!shouldFlushMemory) {
     return entry ?? params.sessionEntry;

src/auto-reply/reply/memory-flush.ts

@@ -161,11 +161,22 @@ export function shouldRunMemoryFlush(params: {
     return false;
   }
 
-  const compactionCount = params.entry.compactionCount ?? 0;
-  const lastFlushAt = params.entry.memoryFlushCompactionCount;
-  if (typeof lastFlushAt === "number" && lastFlushAt === compactionCount) {
+  if (hasAlreadyFlushedForCurrentCompaction(params.entry)) {
     return false;
   }
 
   return true;
 }
+
+/**
+ * Returns true when a memory flush has already been performed for the current
+ * compaction cycle. This prevents repeated flush runs within the same cycle —
+ * important for both the token-based and transcript-size–based trigger paths.
+ */
+export function hasAlreadyFlushedForCurrentCompaction(
+  entry: Pick<SessionEntry, "compactionCount" | "memoryFlushCompactionCount">,
+): boolean {
+  const compactionCount = entry.compactionCount ?? 0;
+  const lastFlushAt = entry.memoryFlushCompactionCount;
+  return typeof lastFlushAt === "number" && lastFlushAt === compactionCount;
+}

src/auto-reply/reply/reply-state.test.ts

@@ -17,6 +17,7 @@ import {
 import {
   DEFAULT_MEMORY_FLUSH_FORCE_TRANSCRIPT_BYTES,
   DEFAULT_MEMORY_FLUSH_SOFT_TOKENS,
+  hasAlreadyFlushedForCurrentCompaction,
   resolveMemoryFlushContextWindowTokens,
   resolveMemoryFlushSettings,
   shouldRunMemoryFlush,
@@ -350,6 +351,42 @@ describe("shouldRunMemoryFlush", () => {
   });
 });
 
+describe("hasAlreadyFlushedForCurrentCompaction", () => {
+  it("returns true when memoryFlushCompactionCount matches compactionCount", () => {
+    expect(
+      hasAlreadyFlushedForCurrentCompaction({
+        compactionCount: 3,
+        memoryFlushCompactionCount: 3,
+      }),
+    ).toBe(true);
+  });
+
+  it("returns false when memoryFlushCompactionCount differs", () => {
+    expect(
+      hasAlreadyFlushedForCurrentCompaction({
+        compactionCount: 3,
+        memoryFlushCompactionCount: 2,
+      }),
+    ).toBe(false);
+  });
+
+  it("returns false when memoryFlushCompactionCount is undefined", () => {
+    expect(
+      hasAlreadyFlushedForCurrentCompaction({
+        compactionCount: 1,
+      }),
+    ).toBe(false);
+  });
+
+  it("treats missing compactionCount as 0", () => {
+    expect(
+      hasAlreadyFlushedForCurrentCompaction({
+        memoryFlushCompactionCount: 0,
+      }),
+    ).toBe(true);
+  });
+});
+
 describe("resolveMemoryFlushContextWindowTokens", () => {
   it("falls back to agent config or default tokens", () => {
     expect(resolveMemoryFlushContextWindowTokens({ agentCfgContextTokens: 42_000 })).toBe(42_000);