From a699de83ec6463b92e3cffbcb4bb2fff3a80e84b Mon Sep 17 00:00:00 2001
From: Nami4D <hello@nami4d.tech>
Date: Tue, 19 May 2026 11:23:40 +0900
Subject: [PATCH] fix(xai-oauth): strip service_tier and add safety-net
 sanitization for slash enums

xAI's /v1/responses endpoint rejects service_tier with HTTP 400
"Argument not supported: service_tier" when users activate /fast mode.

Also add a safety-net strip_slash_enum call in _preflight_codex_api_kwargs
to catch any tool schemas that might slip through the caller-level
sanitization. xAI's Responses API grammar compiler rejects enum values
containing forward slashes (e.g. HuggingFace model IDs like
"Qwen/Qwen3.5-0.8B") with the opaque "Invalid arguments passed to the
model" error.

Fixes the root cause of "Invalid arguments passed to the model" errors
reported by xAI OAuth (SuperGrok) users.
---
 agent/codex_responses_adapter.py | 20 ++++++++++++++++++++
 agent/transports/codex.py        | 11 +++++++++++
 2 files changed, 31 insertions(+)

diff --git a/agent/codex_responses_adapter.py b/agent/codex_responses_adapter.py
index e539656b7d1..230a6e613b1 100644
--- a/agent/codex_responses_adapter.py
+++ b/agent/codex_responses_adapter.py
@@ -913,6 +913,26 @@ def _preflight_codex_api_kwargs(
     elif "stream" in api_kwargs:
         raise ValueError("Codex Responses stream flag is only allowed in fallback streaming requests.")
 
+    # Safety-net sanitization for xAI Responses (#28490): defense-in-depth
+    # for the same slash-enum strip that ``chat_completion_helpers`` and
+    # ``auxiliary_client`` apply at request-build time.  If a future code
+    # path forgets to sanitize before calling us, this catches the bypass
+    # so xAI doesn't 400 with ``Invalid arguments passed to the model``
+    # (HuggingFace IDs like ``Qwen/Qwen3.5-0.8B`` from MCP tool schemas).
+    #
+    # Gated on the model name pattern because native Codex (OpenAI) DOES
+    # accept slash-containing enum values — stripping them there would
+    # silently degrade tool-schema constraints.  xAI is the only
+    # Responses-API surface that rejects the shape.
+    model_name_for_provider_check = str(api_kwargs.get("model") or "").lower()
+    is_xai_model = model_name_for_provider_check.startswith(("grok-", "x-ai/grok-"))
+    if is_xai_model and normalized.get("tools"):
+        try:
+            from tools.schema_sanitizer import strip_slash_enum
+            normalized["tools"], _ = strip_slash_enum(normalized["tools"])
+        except Exception:
+            pass  # Best-effort — the caller-level sanitization should have handled it
+
     unexpected = sorted(key for key in api_kwargs if key not in allowed_keys)
     if unexpected:
         raise ValueError(
diff --git a/agent/transports/codex.py b/agent/transports/codex.py
index f24f2304899..9a4a3a4b937 100644
--- a/agent/transports/codex.py
+++ b/agent/transports/codex.py
@@ -184,6 +184,17 @@ class ResponsesApiTransport(ProviderTransport):
         if request_overrides:
             kwargs.update(request_overrides)
 
+        # xAI Responses API rejects ``service_tier`` (HTTP 400 "Argument not
+        # supported: service_tier") — hit when ``/fast`` priority-processing
+        # mode lingers from a prior model in the same session, or when a
+        # user explicitly sets ``agent.service_tier`` in config.yaml.  The
+        # main-loop guard (``resolve_fast_mode_overrides`` only returns
+        # ``service_tier`` for OpenAI fast-eligible models) doesn't cover
+        # those leak paths, so strip defensively when targeting xAI.  See
+        # #28490 for the original report.
+        if is_xai_responses:
+            kwargs.pop("service_tier", None)
+
         # Forward per-request timeout to the SDK so OpenAI/Anthropic clients
         # honor it.  Without this, ``providers.<id>.request_timeout_seconds``
         # is silently dropped on the main agent Codex path while the