From ddae511ab1bdf404d3294045aebb1faabd630856 Mon Sep 17 00:00:00 2001
From: kshitijk4poor <82637225+kshitijk4poor@users.noreply.github.com>
Date: Mon, 3 Aug 2026 22:53:54 +0530
Subject: [PATCH] fix: thread extra_headers through the call_llm split
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The PR's concurrency wrapper splits call_llm into a semaphore-guarded
entry + _call_llm_impl; main added extra_headers to call_llm's
signature after the PR's base, so the split has to forward it too
(dropped silently otherwise — Azure Foundry and custom-endpoint
callers set it).
---
 agent/auxiliary_client.py | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/agent/auxiliary_client.py b/agent/auxiliary_client.py
index 5a33d25cc7..aacc2c2a39 100644
--- a/agent/auxiliary_client.py
+++ b/agent/auxiliary_client.py
@@ -8546,6 +8546,7 @@ def call_llm(
             timeout=timeout,
             extra_body=extra_body,
             reasoning_config=reasoning_config,
+            extra_headers=extra_headers,
             api_mode=api_mode,
             stream=stream,
             stream_options=stream_options,
@@ -8590,6 +8591,7 @@ def _call_llm_impl(
     timeout: float = None,
     extra_body: dict = None,
     reasoning_config: Optional[dict] = None,
+    extra_headers: Optional[Dict[str, str]] = None,
     api_mode: str = None,
     stream: bool = False,
     stream_options: dict = None,