fix(memory): align QAT default docs/tests (#15429) (thanks @azade-c)

CHANGELOG.md

@@ -15,6 +15,7 @@ Docs: https://docs.openclaw.ai
 
 ### Fixes
 
+- Memory: switch default local embedding model to the QAT `embeddinggemma-300m-qat-Q8_0` variant for better quality at the same footprint. (#15429) Thanks @azade-c.
 - Agents/Compaction: centralize exec default resolution in the shared tool factory so per-agent `tools.exec` overrides (host/security/ask/node and related defaults) persist across compaction retries. (#15833) Thanks @napetrov.
 - Voice Call: route webhook runtime event handling through shared manager event logic so rejected inbound hangups are idempotent in production, with regression tests for duplicate reject events and provider-call-ID remapping parity. (#15892) Thanks @dcantu96.
 - CLI/Completion: route plugin-load logs to stderr and write generated completion scripts directly to stdout to avoid `source <(openclaw completion ...)` corruption. (#15481) Thanks @arosstale.

docs/concepts/memory.md

@@ -535,7 +535,7 @@ Notes:
 
 ### Local embedding auto-download
 
-- Default local embedding model: `hf:ggml-org/embeddinggemma-300M-GGUF/embeddinggemma-300M-Q8_0.gguf` (~0.6 GB).
+- Default local embedding model: `hf:ggml-org/embeddinggemma-300m-qat-q8_0-GGUF/embeddinggemma-300m-qat-Q8_0.gguf` (~0.6 GB).
 - When `memorySearch.provider = "local"`, `node-llama-cpp` resolves `modelPath`; if the GGUF is missing it **auto-downloads** to the cache (or `local.modelCacheDir` if set), then loads it. Downloads resume on retry.
 - Native build requirement: run `pnpm approve-builds`, pick `node-llama-cpp`, then `pnpm rebuild node-llama-cpp`.
 - Fallback: if local setup fails and `memorySearch.fallback = "openai"`, we automatically switch to remote embeddings (`openai/text-embedding-3-small` unless overridden) and record the reason.

src/memory/embeddings.test.ts

@@ -313,6 +313,7 @@ describe("local embedding normalization", () => {
 
   it("normalizes local embeddings to magnitude ~1.0", async () => {
     const unnormalizedVector = [2.35, 3.45, 0.63, 4.3, 1.2, 5.1, 2.8, 3.9];
+    const resolveModelFileMock = vi.fn(async () => "/fake/model.gguf");
 
     importNodeLlamaCppMock.mockResolvedValue({
       getLlama: async () => ({
@@ -324,7 +325,7 @@ describe("local embedding normalization", () => {
           }),
         }),
       }),
-      resolveModelFile: async () => "/fake/model.gguf",
+      resolveModelFile: resolveModelFileMock,
       LlamaLogLevel: { error: 0 },
     });
 
@@ -340,6 +341,10 @@ describe("local embedding normalization", () => {
     const magnitude = Math.sqrt(embedding.reduce((sum, x) => sum + x * x, 0));
 
     expect(magnitude).toBeCloseTo(1.0, 5);
+    expect(resolveModelFileMock).toHaveBeenCalledWith(
+      "hf:ggml-org/embeddinggemma-300m-qat-q8_0-GGUF/embeddinggemma-300m-qat-Q8_0.gguf",
+      undefined,
+    );
   });
 
   it("handles zero vector without division by zero", async () => {