From de2b464c3ffb91272076d143fc7bacc57bfe9630 Mon Sep 17 00:00:00 2001
From: Diego Rodrigues de Sa e Souza
 <8016841+diegosouzapw@users.noreply.github.com>
Date: Tue, 14 Jul 2026 21:19:16 -0300
Subject: [PATCH] fix: sanitize non-Latin1 chars in combo diagnostic headers
 (#6612) (#7190)

---
 ...mbo-diagnostics-header-bytestring-crash.md |  1 +
 open-sse/utils/error.ts                       | 28 +++++++++++---
 tests/unit/combo-diagnostics-trace.test.ts    | 38 +++++++++++++++++++
 3 files changed, 62 insertions(+), 5 deletions(-)
 create mode 100644 changelog.d/fixes/6612-combo-diagnostics-header-bytestring-crash.md

diff --git a/changelog.d/fixes/6612-combo-diagnostics-header-bytestring-crash.md b/changelog.d/fixes/6612-combo-diagnostics-header-bytestring-crash.md
new file mode 100644
index 0000000000..77f12ced1f
--- /dev/null
+++ b/changelog.d/fixes/6612-combo-diagnostics-header-bytestring-crash.md
@@ -0,0 +1 @@
+- fix(sse): sanitize non-Latin1 characters before embedding combo diagnostics in HTTP headers, preventing a ByteString crash on quality-check failure (#6612)
diff --git a/open-sse/utils/error.ts b/open-sse/utils/error.ts
index 88efa6c67d..be3de82dda 100644
--- a/open-sse/utils/error.ts
+++ b/open-sse/utils/error.ts
@@ -145,6 +145,22 @@ function clampDiagStr(v: unknown, max = 128): string {
   return typeof v === "string" ? v.slice(0, max).replace(/[\r\n]+/g, " ") : "";
 }
 
+/**
+ * HTTP header values must be Latin1/ByteString (undici throws a TypeError
+ * otherwise — see #6612). Replace any codepoint outside the Latin1 range
+ * (0-255) with "?" so header construction never throws. Only used for the
+ * literal header value; the JSON body keeps the original, unsanitized
+ * readable text via `sanitizeComboDiagnostics`.
+ */
+function toHeaderSafeAscii(v: string): string {
+  let out = "";
+  for (let i = 0; i < v.length; i++) {
+    const code = v.charCodeAt(i);
+    out += code > 255 ? "?" : v[i];
+  }
+  return out;
+}
+
 /**
  * Whitelist projection — guarantees only id/reason string primitives + integer
  * counts can escape, regardless of what the caller assembled. This is the secret
@@ -186,10 +202,12 @@ export function errorResponseWithComboDiagnostics(
   if (opts.code) body.error.code = opts.code;
   if (opts.type) body.error.type = opts.type;
   body.diagnostics = safe;
-  const excludedHeader = safe.excluded
-    .map((e) => `${e.provider}${e.model ? `/${e.model}` : ""}:${e.reason}`)
-    .join(",")
-    .slice(0, 900);
+  const excludedHeader = toHeaderSafeAscii(
+    safe.excluded
+      .map((e) => `${e.provider}${e.model ? `/${e.model}` : ""}:${e.reason}`)
+      .join(",")
+      .slice(0, 900)
+  );
   return new Response(JSON.stringify(body), {
     status: statusCode,
     headers: {
@@ -197,7 +215,7 @@ export function errorResponseWithComboDiagnostics(
       "x-omniroute-combo-pool-size": String(safe.poolSize),
       "x-omniroute-combo-attempted": String(safe.attempted),
       "x-omniroute-combo-excluded": excludedHeader,
-      "x-omniroute-combo-terminal-reason": safe.terminalReason.slice(0, 200),
+      "x-omniroute-combo-terminal-reason": toHeaderSafeAscii(safe.terminalReason.slice(0, 200)),
     },
   });
 }
diff --git a/tests/unit/combo-diagnostics-trace.test.ts b/tests/unit/combo-diagnostics-trace.test.ts
index be25e64c77..fe8bb546a4 100644
--- a/tests/unit/combo-diagnostics-trace.test.ts
+++ b/tests/unit/combo-diagnostics-trace.test.ts
@@ -79,3 +79,41 @@ test("combo diagnostics: secret containment — non-whitelisted fields never sur
   assert.ok(!serialized.includes("accessToken"), "no accessToken KEY survives");
   assert.ok(!serialized.includes("token"), "no token KEY survives");
 });
+
+test("combo diagnostics: terminalReason with a non-Latin1 char (em dash) must not crash Response construction (#6612)", () => {
+  const terminalReason = "reasoning consumed 5/5 tokens — no content output";
+  assert.doesNotThrow(() => {
+    const res = errorResponseWithComboDiagnostics(
+      502,
+      `Upstream response failed quality validation: ${terminalReason}`,
+      {
+        poolSize: 4,
+        attempted: 1,
+        excluded: [{ provider: "deepseek", model: "deepseek-v4-flash-free", reason: "quality — bad" }],
+        attemptOrder: [{ provider: "deepseek", model: "deepseek-v4-flash-free" }],
+        terminalReason,
+      }
+    );
+    assert.equal(res.status, 502);
+  });
+});
+
+test("combo diagnostics: JSON body keeps the original non-Latin1 text even though headers are ASCII-sanitized (#6612)", async () => {
+  const terminalReason = "reasoning consumed 5/5 tokens — no content output";
+  const res = errorResponseWithComboDiagnostics(
+    502,
+    `Upstream response failed quality validation: ${terminalReason}`,
+    {
+      poolSize: 1,
+      attempted: 1,
+      excluded: [],
+      attemptOrder: [{ provider: "deepseek", model: "deepseek-v4-flash-free" }],
+      terminalReason,
+    }
+  );
+  // Header value must be a valid Latin1 ByteString — em dash (U+2014) replaced.
+  assert.equal(res.headers.get("x-omniroute-combo-terminal-reason"), terminalReason.replace("—", "?"));
+  const body = await res.json();
+  // JSON body keeps the original, readable (unsanitized) em dash.
+  assert.equal(body.diagnostics.terminalReason, terminalReason);
+});