diff --git a/apps/memos-local-plugin/core/llm/fetcher.ts b/apps/memos-local-plugin/core/llm/fetcher.ts
index 5e8b0317e..53eb55ec3 100644
--- a/apps/memos-local-plugin/core/llm/fetcher.ts
+++ b/apps/memos-local-plugin/core/llm/fetcher.ts
@@ -61,6 +61,7 @@ export async function httpPostJson<TResp>(opts: HttpPostOpts<unknown>): Promise<
           attempt,
           transient,
           durationMs: ms,
+          body: truncateLogBody(text),
         });
         if (transient && attempt <= opts.maxRetries) {
           opts.onRetry?.(attempt);
@@ -137,6 +138,7 @@ export async function httpPostStream(opts: {
   provider: LlmProviderName;
   log: LlmProviderLogger;
 }): Promise<Response> {
+  const start = Date.now();
   const signal = mergeSignals(opts.signal, AbortSignal.timeout(opts.timeoutMs));
   const resp = await fetch(opts.url, {
     method: "POST",
@@ -150,6 +152,12 @@ export async function httpPostStream(opts: {
   });
   if (!resp.ok) {
     const text = await safeText(resp);
+    opts.log.warn("http.non_ok", {
+      status: resp.status,
+      transient: resp.status >= 500 || resp.status === 429,
+      durationMs: Date.now() - start,
+      body: truncateLogBody(text),
+    });
     throw new MemosError(
       errCodeForStatus(resp.status),
       `HTTP ${resp.status} from ${opts.provider} (stream)`,
@@ -217,6 +225,10 @@ async function safeText(resp: Response): Promise<string | undefined> {
   }
 }
 
+function truncateLogBody(text: string | undefined): string | undefined {
+  return text?.slice(0, 512);
+}
+
 function isTransientError(err: unknown): boolean {
   if (!(err instanceof Error)) return false;
   const msg = err.message ?? "";
diff --git a/apps/memos-local-plugin/tests/unit/llm/fetcher.test.ts b/apps/memos-local-plugin/tests/unit/llm/fetcher.test.ts
index 3609aa2d8..a3941b7aa 100644
--- a/apps/memos-local-plugin/tests/unit/llm/fetcher.test.ts
+++ b/apps/memos-local-plugin/tests/unit/llm/fetcher.test.ts
@@ -101,6 +101,31 @@ describe("llm/fetcher", () => {
     }
   });
 
+  it("logs a truncated response body for non-ok JSON responses", async () => {
+    const warn = vi.fn();
+    const body = "x".repeat(600);
+    mockFetch([new Response(body, { status: 400 })]);
+
+    await expect(
+      httpPostJson({
+        url: "https://x",
+        body: {},
+        timeoutMs: 5_000,
+        maxRetries: 0,
+        provider: "openai_compatible",
+        log: { ...nullLog(), warn },
+      }),
+    ).rejects.toBeInstanceOf(MemosError);
+
+    expect(warn).toHaveBeenCalledWith(
+      "http.non_ok",
+      expect.objectContaining({
+        status: 400,
+        body: "x".repeat(512),
+      }),
+    );
+  });
+
   it("timeout → LLM_TIMEOUT", async () => {
     const timeout = new DOMException("The operation was aborted due to timeout", "TimeoutError");
     mockFetch([timeout]);
@@ -172,6 +197,29 @@ describe("llm/fetcher", () => {
     }
   });
 
+  it("logs response body for non-ok streaming responses", async () => {
+    const warn = vi.fn();
+    mockFetch([new Response("stream rejected", { status: 400 })]);
+
+    await expect(
+      httpPostStream({
+        url: "https://x",
+        body: {},
+        timeoutMs: 5_000,
+        provider: "openai_compatible",
+        log: { ...nullLog(), warn },
+      }),
+    ).rejects.toBeInstanceOf(MemosError);
+
+    expect(warn).toHaveBeenCalledWith(
+      "http.non_ok",
+      expect.objectContaining({
+        status: 400,
+        body: "stream rejected",
+      }),
+    );
+  });
+
   it("decodeSse splits events at blank lines and drops [DONE] sentinel handling to caller", async () => {
     const chunks = [
       "data: {\"a\":1}\n\n",