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;