feat(headroom): make the compression request timeout configurable

The 3000 ms timeout on /v1/compress was fixed, so busy or slow machines
timed out often and sent the LLM an inconsistently compressed body,
hurting prompt caching. Add a headroomTimeoutMs setting, thread it from
the chat handler down to compressWithHeadroom, expose it in the Token
Saver dashboard, and normalize invalid values back to the 3000 ms default.

open-sse/rtk/headroom.js

@@ -7,6 +7,12 @@ import {
 
 const DEFAULT_TIMEOUT_MS = 3000;
 
+function normalizeTimeout(value) {
+  return typeof value === "number" && Number.isFinite(value) && value > 0
+    ? value
+    : DEFAULT_TIMEOUT_MS;
+}
+
 function jsonBytes(value) {
   try {
     return new TextEncoder().encode(JSON.stringify(value) || "").length;
@@ -240,6 +246,7 @@ async function callCompress(url, messages, model, timeoutMs, compressUserMessage
 // /v1/compress only understands OpenAI shape, so Claude bodies are translated
 // to OpenAI, compressed, then translated back using 9Router's own translators.
 export async function compressWithHeadroom(body, { enabled, url, model, format, compressUserMessages, timeoutMs = DEFAULT_TIMEOUT_MS, diagnostics = null } = {}) {
+  timeoutMs = normalizeTimeout(timeoutMs);
   if (!enabled) {
     setDiagnostic(diagnostics, "disabled");
     return null;