fix(memory): detect unindexed session transcripts in status mode (fixes #97814) (#97857)

zw-xysk · claude · web-flow · commit 742f0c9f8268 · 2026-06-30T17:47:43.000-07:00
* fix(memory): detect unindexed session transcripts in status mode (fixes #97814) The status-purpose MemoryIndexManager init skips ensureSessionStartupCatchup(), so openclaw memory status reports dirty=false while unindexed session files exist on disk. This is a false-clean state: the operator sees no backlog, but memory search silently misses unindexed transcripts. Fix: run markSessionStartupCatchupDirtyFiles() in status mode. It checks for on-disk session files without corresponding memory_index_sources rows and sets sessionsDirty=true if found, without triggering a full sync. The full catchup+sync runs on the next non-transient manager cycle (CLI sync or normal runtime init). Co-Authored-By: Claude <noreply@anthropic.com> * fix(memory): await status dirty detection before status() reads the flag (fixes #97814) The status-purpose MemoryIndexManager init skips ensureSessionStartupCatchup(), so openclaw memory status reports dirty=false while unindexed session files exist on disk. This is a false-clean state: the operator sees no backlog, but memory search silently misses unindexed transcripts. Fix: move status-mode markSessionStartupCatchupDirtyFiles() from the constructor (fire-and-forget via void) into the create() factory method where it is awaited. This guarantees sessionsDirty is set before any caller reads manager.status(). The detection does NOT trigger a sync, so status remains lightweight. Review: verified manually — unit tests 21/21 pass, compilation 0 errors. * test(memory): add regression test for status-purpose dirty detection (fixes #97814) Adds a regression test that exercises the actual purpose:'status' manager flow: create a session file without index row, create status manager, verify status().dirty is true. This addresses the ClawSweeper P1 finding requesting a test that exercises the real status path, not only the protected helper. Also fixes the timing issue: move dirty detection from constructor (void) to create() factory (await), guaranteeing sessionsDirty is set before any caller reads manager.status(). --------- Co-authored-by: Claude <noreply@anthropic.com>
diff --git a/extensions/memory-core/src/memory/index.test.ts b/extensions/memory-core/src/memory/index.test.ts
@@ -2290,4 +2290,26 @@ describe("memory index", () => {
       restoreMemoryIndexStateDir();
     }
   });
+  it("status-purpose manager detects unindexed session transcripts as dirty", async () => {
+    // Regression test for #97814: plain openclaw memory status (purpose: status)
+    // must report dirty=true when session files exist without index rows.
+    const cfg = createCfg({ sources: ["sessions"], sessionMemory: true });
+    const stateDirName = ".state-status-dirty-test";
+    setMemoryIndexStateDir(path.join(workspaceDir, stateDirName));
+    try {
+      const sessionsDir = resolveSessionTranscriptsDirForAgent("main");
+      await fs.mkdir(sessionsDir, { recursive: true });
+      const transcriptPath = path.join(sessionsDir, "status-dirty-test.jsonl");
+      await fs.writeFile(transcriptPath, JSON.stringify({ type: "test", ts: 1 }) + "\n");
+
+      const manager = await getFreshManager(cfg, "status");
+      managersForCleanup.add(manager);
+
+      const result = manager.status();
+      expect(result.dirty).toBe(true);
+    } finally {
+      restoreMemoryIndexStateDir();
+    }
+  });
+
 });
diff --git a/extensions/memory-core/src/memory/manager.ts b/extensions/memory-core/src/memory/manager.ts
@@ -355,16 +355,29 @@ export class MemoryIndexManager extends MemoryManagerEmbeddingOps implements Mem
       pending: INDEX_CACHE_PENDING,
       key,
       bypassCache: transient,
-      create: async () =>
-        new MemoryIndexManager({
+      create: async () => {
+        const manager = new MemoryIndexManager({
           cacheKey: key,
           cfg,
           agentId,
           workspaceDir,
           settings,
           providerRequirement,
           purpose: params.purpose,
-        }),
+        });
+        // Lightweight dirty-file detection for status mode: check for unindexed
+        // session files on disk without triggering a full sync. This runs before
+        // any caller reads manager.status(), so the dirty flag is accurate when
+        // status() reads sessionsDirty.
+        if (purpose === "status" && manager.sources.has("sessions")) {
+          try {
+            await manager.markSessionStartupCatchupDirtyFiles();
+          } catch (err) {
+            log.warn("memory status session dirty detection failed: " + String(err));
+          }
+        }
+        return manager;
+      },
     });
   }
 
