diff --git a/changelog.d/fixes/7907-chatcore-499-string-abort.md b/changelog.d/fixes/7907-chatcore-499-string-abort.md
new file mode 100644
index 0000000000..0d3ef1e90c
--- /dev/null
+++ b/changelog.d/fixes/7907-chatcore-499-string-abort.md
@@ -0,0 +1 @@
+- **Chat Core**: client aborts that reject the upstream fetch with a raw string reason (e.g. `request_signal_aborted`, `Client disconnected`) are now reported as `499 Request aborted` in the response, request logs, and usage records instead of `FAILED 502 / Bad Gateway`. Follow-up to #7908 for #7907.
diff --git a/open-sse/handlers/chatCore.ts b/open-sse/handlers/chatCore.ts
index 168c06c343..6375a310cb 100644
--- a/open-sse/handlers/chatCore.ts
+++ b/open-sse/handlers/chatCore.ts
@@ -319,6 +319,7 @@ import {
   stripMarkdownCodeFence,
 } from "../utils/aiSdkCompat.ts";
 import { generateRequestId } from "@/shared/utils/requestId";
+import { isLocalStreamLifecycleError } from "@/shared/utils/circuitBreaker";
 import { extractFacts } from "@/lib/memory/extraction";
 import { handleToolCallExecution } from "@/lib/skills/interception";
 import { OMNIROUTE_RESPONSE_HEADERS } from "@/shared/constants/headers";
@@ -3112,18 +3113,21 @@ export async function handleChatCore({
         errorCode: error.code,
       };
     }
-    const failureStatus =
-      error.name === "AbortError"
-        ? 499
-        : error.name === "TimeoutError" || error.name === "BodyTimeoutError"
-          ? HTTP_STATUS.GATEWAY_TIMEOUT
-          : error.status && typeof error.status === "number"
-            ? error.status
-            : HTTP_STATUS.BAD_GATEWAY;
-    const failureMessage =
-      error.name === "AbortError"
-        ? "Request aborted"
-        : formatProviderError(error, provider, model, failureStatus);
+    // abort(reason) can reject the upstream fetch with a raw string reason
+    // (e.g. "request_signal_aborted") that has no `name`/`status`; classify
+    // via isLocalStreamLifecycleError so those map to 499 instead of falling
+    // through to the 502 provider-failure default.
+    const isRequestAborted = isLocalStreamLifecycleError(error);
+    const failureStatus = isRequestAborted
+      ? 499
+      : error.name === "TimeoutError" || error.name === "BodyTimeoutError"
+        ? HTTP_STATUS.GATEWAY_TIMEOUT
+        : error.status && typeof error.status === "number"
+          ? error.status
+          : HTTP_STATUS.BAD_GATEWAY;
+    const failureMessage = isRequestAborted
+      ? "Request aborted"
+      : formatProviderError(error, provider, model, failureStatus);
     const upstreamErrorCode = getUpstreamErrorIdentifier(error);
     // Tag our own deadline timeouts (fetch-start TimeoutError / body BodyTimeoutError,
     // both surfaced as a 504) as "upstream_timeout" so the cooldown layer can tell a
@@ -3152,7 +3156,7 @@ export async function handleChatCore({
       claudeCacheMeta: claudePromptCacheLogMeta,
       cacheSource: "upstream",
     });
-    if (error.name === "AbortError") {
+    if (isRequestAborted) {
       streamController.handleError(error);
       return createErrorResult(499, "Request aborted");
     }
diff --git a/tests/unit/chatcore-translation-paths.test.ts b/tests/unit/chatcore-translation-paths.test.ts
index eb12a8c8f0..ed4310024e 100644
--- a/tests/unit/chatcore-translation-paths.test.ts
+++ b/tests/unit/chatcore-translation-paths.test.ts
@@ -2367,6 +2367,28 @@ test("chatCore maps upstream aborts to request-aborted errors", async () => {
   assert.equal(result.error, "Request aborted");
 });
 
+test("chatCore maps raw string abort reasons to 499, not 502 (#7907)", async () => {
+  // abort(reason) rejects the upstream fetch with the raw reason — often a
+  // bare string with no `name`/`status`. It must map to 499 like a named
+  // AbortError, not fall through to the 502 provider-failure default.
+  const { result } = await invokeChatCore({
+    provider: "openai",
+    model: "gpt-4o-mini",
+    body: {
+      model: "gpt-4o-mini",
+      stream: false,
+      messages: [{ role: "user", content: "abort me with a string reason" }],
+    },
+    responseFactory() {
+      throw "request_signal_aborted";
+    },
+  });
+
+  assert.equal(result.success, false);
+  assert.equal(result.status, 499);
+  assert.equal(result.error, "Request aborted");
+});
+
 test("chatCore returns streaming responses without waiting for upstream completion", async () => {
   const encoder = new TextEncoder();
   let closeUpstream: (() => void) | null = null;