Memory/QMD: diversify mixed-source search results

CHANGELOG.md

@@ -63,6 +63,7 @@ Docs: https://docs.openclaw.ai
 - CLI/Pairing: default `pairing list` and `pairing approve` to the sole available pairing channel when omitted, so TUI-only setups can recover from `pairing required` without guessing channel arguments. (#21527) Thanks @losts1.
 - TUI/Pairing: show explicit pairing-required recovery guidance after gateway disconnects that return `pairing required`, including approval steps to unblock quickstart TUI hatching on fresh installs. (#21841) Thanks @nicolinux.
 - TUI/Input: suppress duplicate backspace events arriving in the same input burst window so SSH sessions no longer delete two characters per backspace press in the composer. (#19318) Thanks @eheimer.
+- Memory/QMD: diversify mixed-source search ranking when both session and memory collections are present so session transcript hits no longer crowd out durable memory-file matches in top results. (#19913) Thanks @alextempr.
 - Auth/Onboarding: align OAuth profile-id config mapping with stored credential IDs for OpenAI Codex and Chutes flows, preventing `provider:default` mismatches when OAuth returns email-scoped credentials. (#12692) thanks @mudrii.
 - Docker: pin base images to SHA256 digests in Docker builds to prevent mutable tag drift. (#7734) Thanks @coygeek.
 - Docker/Security: run E2E and install-sh test images as non-root by adding appuser directives. Thanks @thewilloftheshadow.

src/memory/qmd-manager.test.ts

@@ -933,6 +933,86 @@ describe("QmdMemoryManager", () => {
     await manager.close();
   });
 
+  it("diversifies mixed session and memory search results so memory hits are retained", async () => {
+    cfg = {
+      ...cfg,
+      memory: {
+        backend: "qmd",
+        qmd: {
+          includeDefaultMemory: false,
+          update: { interval: "0s", debounceMs: 60_000, onBoot: false },
+          sessions: { enabled: true },
+          paths: [{ path: workspaceDir, pattern: "**/*.md", name: "workspace" }],
+        },
+      },
+    } as OpenClawConfig;
+
+    spawnMock.mockImplementation((_cmd: string, args: string[]) => {
+      if (args[0] === "search" && args.includes("workspace-main")) {
+        const child = createMockChild({ autoClose: false });
+        emitAndClose(
+          child,
+          "stdout",
+          JSON.stringify([{ docid: "m1", score: 0.6, snippet: "@@ -1,1\nmemory fact" }]),
+        );
+        return child;
+      }
+      if (args[0] === "search" && args.includes("sessions-main")) {
+        const child = createMockChild({ autoClose: false });
+        emitAndClose(
+          child,
+          "stdout",
+          JSON.stringify([
+            { docid: "s1", score: 0.99, snippet: "@@ -1,1\nsession top 1" },
+            { docid: "s2", score: 0.95, snippet: "@@ -1,1\nsession top 2" },
+            { docid: "s3", score: 0.91, snippet: "@@ -1,1\nsession top 3" },
+            { docid: "s4", score: 0.88, snippet: "@@ -1,1\nsession top 4" },
+          ]),
+        );
+        return child;
+      }
+      return createMockChild();
+    });
+
+    const { manager } = await createManager();
+    const inner = manager as unknown as {
+      db: { prepare: (_query: string) => { all: (arg: unknown) => unknown }; close: () => void };
+    };
+    inner.db = {
+      prepare: (_query: string) => ({
+        all: (arg: unknown) => {
+          switch (arg) {
+            case "m1":
+              return [{ collection: "workspace-main", path: "memory/facts.md" }];
+            case "s1":
+            case "s2":
+            case "s3":
+            case "s4":
+              return [
+                {
+                  collection: "sessions-main",
+                  path: `${String(arg)}.md`,
+                },
+              ];
+            default:
+              return [];
+          }
+        },
+      }),
+      close: () => {},
+    };
+
+    const results = await manager.search("fact", {
+      maxResults: 4,
+      sessionKey: "agent:main:slack:dm:u123",
+    });
+
+    expect(results).toHaveLength(4);
+    expect(results.some((entry) => entry.source === "memory")).toBe(true);
+    expect(results.some((entry) => entry.source === "sessions")).toBe(true);
+    await manager.close();
+  });
+
   it("logs and continues when qmd embed times out", async () => {
     vi.useFakeTimers();
     cfg = {

src/memory/qmd-manager.ts

@@ -492,7 +492,7 @@ export class QmdMemoryManager implements MemorySearchManager {
         source: doc.source,
       });
     }
-    return this.clampResultsByInjectedChars(results.slice(0, limit));
+    return this.clampResultsByInjectedChars(this.diversifyResultsBySource(results, limit));
   }
 
   async sync(params?: {
@@ -1271,6 +1271,52 @@ export class QmdMemoryManager implements MemorySearchManager {
     return clamped;
   }
 
+  private diversifyResultsBySource(
+    results: MemorySearchResult[],
+    limit: number,
+  ): MemorySearchResult[] {
+    const target = Math.max(0, limit);
+    if (target <= 0) {
+      return [];
+    }
+    if (results.length <= 1) {
+      return results.slice(0, target);
+    }
+    const bySource = new Map<MemorySource, MemorySearchResult[]>();
+    for (const entry of results) {
+      const list = bySource.get(entry.source) ?? [];
+      list.push(entry);
+      bySource.set(entry.source, list);
+    }
+    const hasSessions = bySource.has("sessions");
+    const hasMemory = bySource.has("memory");
+    if (!hasSessions || !hasMemory) {
+      return results.slice(0, target);
+    }
+    const sourceOrder = Array.from(bySource.entries())
+      .toSorted((a, b) => (b[1][0]?.score ?? 0) - (a[1][0]?.score ?? 0))
+      .map(([source]) => source);
+    const diversified: MemorySearchResult[] = [];
+    while (diversified.length < target) {
+      let emitted = false;
+      for (const source of sourceOrder) {
+        const next = bySource.get(source)?.shift();
+        if (!next) {
+          continue;
+        }
+        diversified.push(next);
+        emitted = true;
+        if (diversified.length >= target) {
+          break;
+        }
+      }
+      if (!emitted) {
+        break;
+      }
+    }
+    return diversified;
+  }
+
   private shouldSkipUpdate(force?: boolean): boolean {
     if (force) {
       return false;