From c201b72f346a75fd121ce1661566697b508d4d32 Mon Sep 17 00:00:00 2001
From: Krowd <krowd3v@users.noreply.github.com>
Date: Fri, 17 Jul 2026 07:56:37 -0700
Subject: [PATCH] fix(auxiliary): sync runtime after fallback restoration

---
 agent/auxiliary_client.py        | 14 +++++++------
 agent/turn_context.py            | 21 ++++++++++----------
 tests/agent/test_turn_context.py | 34 ++++++++++++++++++++++++++++++++
 3 files changed, 53 insertions(+), 16 deletions(-)

diff --git a/agent/auxiliary_client.py b/agent/auxiliary_client.py
index 642dd37021b..fd86ee2d77d 100644
--- a/agent/auxiliary_client.py
+++ b/agent/auxiliary_client.py
@@ -4690,12 +4690,14 @@ def resolve_provider_client(
     # Normalise aliases
     provider = _normalize_aux_provider(provider)
 
-    # Universal model-resolution fallback chain.  Callers (notably title
-    # generation, vision, session search, and other auxiliary tasks) can
-    # reach this function without an explicit model — the user picked their
-    # main provider, didn't bother configuring a per-task ``auxiliary.<task>.model``,
-    # and just expects "use my main model for side tasks too."  Resolve in
-    # this order, stopping at the first non-empty answer:
+    # Universal model-resolution fallback for concrete providers. ``auto`` is
+    # intentionally excluded: `_resolve_auto(main_runtime=...)` returns the
+    # model paired with the provider it actually selected. Pre-filling an auto
+    # call from `_read_main_model()` can leak a stale process-global runtime
+    # into a different provider (for example Claude model slug on Codex OAuth)
+    # and override that correctly resolved model.
+    #
+    # Concrete provider resolution order:
     #
     #   1. ``model`` argument (caller knew what they wanted)
     #   2. Provider's catalog default — cheap/fast model the provider
diff --git a/agent/turn_context.py b/agent/turn_context.py
index 4e390fe4228..ade5d12763d 100644
--- a/agent/turn_context.py
+++ b/agent/turn_context.py
@@ -151,7 +151,17 @@ def build_turn_context(
     # null; rebuilding from scratch" warning and a needless first-turn prefix
     # cache miss. (Issue #45499.)
 
-    # Tell auxiliary_client what the live main provider/model are for this turn.
+    # Tag log records on this thread with the session ID for ``hermes logs``.
+    set_session_context(agent.session_id)
+
+    # Bind the skill write-origin ContextVar for this thread.
+    set_current_write_origin(getattr(agent, "_memory_write_origin", "assistant_tool"))
+
+    # Restore the primary runtime if the previous turn activated fallback.
+    agent._restore_primary_runtime()
+
+    # Tell auxiliary_client what the live main provider/model are for this turn
+    # after primary restoration has settled the runtime.
     try:
         from agent.auxiliary_client import set_runtime_main
         set_runtime_main(
@@ -165,15 +175,6 @@ def build_turn_context(
     except Exception:
         pass
 
-    # Tag log records on this thread with the session ID for ``hermes logs``.
-    set_session_context(agent.session_id)
-
-    # Bind the skill write-origin ContextVar for this thread.
-    set_current_write_origin(getattr(agent, "_memory_write_origin", "assistant_tool"))
-
-    # Restore the primary runtime if the previous turn activated fallback.
-    agent._restore_primary_runtime()
-
     # Between-turns MCP refresh: an MCP server that finished connecting since
     # the previous turn (slow HTTP/OAuth servers routinely take 2-6s on a cold
     # connect, missing the bounded startup wait) lands in THIS turn's tool
diff --git a/tests/agent/test_turn_context.py b/tests/agent/test_turn_context.py
index e0642c5f11b..1021c9cbdaf 100644
--- a/tests/agent/test_turn_context.py
+++ b/tests/agent/test_turn_context.py
@@ -259,6 +259,40 @@ def test_pending_cli_message_uses_clean_override_for_api_local_note():
     assert agent._pending_cli_user_message is None
 
 
+def test_runtime_main_sync_happens_after_restore():
+    agent = _FakeAgent()
+    agent.model = "stale-fallback-model"
+    agent.provider = "openai-codex"
+    agent.base_url = "https://chatgpt.com/backend-api/codex"
+    agent.api_key = "fallback-key"
+    agent.api_mode = "codex_responses"
+
+    def restore_primary():
+        agent.model = "primary-model"
+        agent.provider = "anthropic"
+        agent.base_url = "https://api.anthropic.com"
+        agent.api_key = "primary-key"
+        agent.api_mode = "anthropic_messages"
+
+    agent._restore_primary_runtime = restore_primary
+    calls = []
+    with patch(
+        "agent.auxiliary_client.set_runtime_main",
+        side_effect=lambda *args, **kwargs: calls.append((args, kwargs)),
+    ):
+        _build(agent)
+
+    assert calls == [(
+        ("anthropic", "primary-model"),
+        {
+            "base_url": "https://api.anthropic.com",
+            "api_key": "primary-key",
+            "api_mode": "anthropic_messages",
+            "auth_mode": "",
+        },
+    )]
+
+
 def test_memory_nudge_fires_at_interval():
     agent = _FakeAgent()
     agent._memory_nudge_interval = 1