fix(ollama): preserve aborts with stream timeouts

CHANGELOG.md

@@ -16,6 +16,7 @@ Docs: https://docs.openclaw.ai
 
 ### Fixes
 
+- Ollama: compose caller abort signals with guarded-fetch timeouts for native `/api/chat` streams, so `/stop` and early cancellation still interrupt local Ollama requests that also carry provider timeout budgets. Refs #74133. Thanks @obviyus.
 - CLI/logs: fall back to the configured Gateway file log when implicit loopback Gateway connections close or time out before or during `logs.tail`, so `openclaw logs` still works while diagnosing local-model Gateway disconnects. Refs #74078. Thanks @sakalaboator.
 - MCP/plugins: stringify non-array plugin tool results with chat-content coercion instead of default object stringification, so MCP callers receive useful JSON/text content from plugin tools. Thanks @vincentkoc.
 - Active Memory/QMD: run QMD boot refresh through a one-shot subprocess path, preserve interactive file watching, and align watcher dependency/build ignores with QMD's scanner so gateway startup avoids arming long-lived QMD watchers. Thanks @codexGW.

extensions/ollama/src/stream-runtime.test.ts

@@ -23,6 +23,7 @@ type GuardedFetchCall = {
   url: string;
   init?: RequestInit;
   policy?: unknown;
+  signal?: AbortSignal;
   timeoutMs?: number;
   auditContext?: string;
 };
@@ -333,6 +334,29 @@ describe("createConfiguredOllamaCompatStreamWrapper", () => {
     );
   });
 
+  it("passes caller abort signals at guard level when a timeout is present", async () => {
+    await withMockNdjsonFetch(
+      [
+        '{"model":"m","created_at":"t","message":{"role":"assistant","content":"ok"},"done":false}',
+        '{"model":"m","created_at":"t","message":{"role":"assistant","content":""},"done":true,"prompt_eval_count":1,"eval_count":1}',
+      ],
+      async (fetchMock) => {
+        const signal = new AbortController().signal;
+        const stream = await createOllamaTestStream({
+          baseUrl: "http://ollama-host:11434",
+          options: { signal, timeoutMs: 123_456 },
+        });
+
+        await collectStreamEvents(stream);
+
+        const request = getGuardedFetchCall(fetchMock);
+        expect(request.timeoutMs).toBe(123_456);
+        expect(request.signal).toBe(signal);
+        expect(request.init?.signal).toBeUndefined();
+      },
+    );
+  });
+
   it("maps native Ollama max thinking to think=high on the wire", async () => {
     await withMockNdjsonFetch(
       [
@@ -1018,6 +1042,7 @@ async function createOllamaTestStream(params: {
     maxTokens?: number;
     temperature?: number;
     signal?: AbortSignal;
+    timeoutMs?: number;
     headers?: Record<string, string>;
   };
 }) {
@@ -1401,8 +1426,9 @@ describe("createOllamaStreamFn", () => {
         const request = getGuardedFetchCall(fetchMock);
         expect(request.url).toBe("http://ollama-host:11434/api/chat");
         expect(request.auditContext).toBe("ollama-stream.chat");
+        expect(request.signal).toBe(signal);
         const requestInit = request.init ?? {};
-        expect(requestInit.signal).toBe(signal);
+        expect(requestInit.signal).toBeUndefined();
         if (typeof requestInit.body !== "string") {
           throw new Error("Expected string request body");
         }

extensions/ollama/src/stream.ts

@@ -1000,9 +1000,9 @@ export function createOllamaStreamFn(
             method: "POST",
             headers,
             body: JSON.stringify(body),
-            signal: options?.signal,
           },
           policy: ssrfPolicy,
+          ...(options?.signal ? { signal: options.signal } : {}),
           timeoutMs: resolveOllamaRequestTimeoutMs(
             model,
             options as { requestTimeoutMs?: unknown; timeoutMs?: unknown } | undefined,