feat(grok): apply OpenAI execution guidance to xAI Grok / xai-oauth models (#27797)

Grok models hit the same failure modes that OPENAI_MODEL_EXECUTION_GUIDANCE
addresses for GPT/Codex: claiming completion without tool calls
('to be honest, I didn't create the file yet'), suggesting workarounds
instead of using existing tools (proposing a folder-based memory system
when the memory tool exists), replying with plans instead of executing.

TOOL_USE_ENFORCEMENT_GUIDANCE was already injected for any model whose
name contains 'grok' (TOOL_USE_ENFORCEMENT_MODELS). This extends the
follow-on family-specific block — OPENAI_MODEL_EXECUTION_GUIDANCE
(tool_persistence / mandatory_tool_use / act_dont_ask / prerequisite_checks
/ verification / missing_context) — to grok-named models too.

The OPENAI_ prefix is retained for backwards compat with imports/tests;
docstring + inline comment now note that the body is family-agnostic and
the prefix reflects origin, not exclusivity.

Tests cover the OpenRouter slug (x-ai/grok-4.3) and the xai-oauth bare
name (grok-4.3), plus a negative control on claude.

E2E verified against a real AIAgent build of the system prompt for both
xai-oauth and openrouter grok models.

agent/prompt_builder.py

@@ -274,6 +274,10 @@ TOOL_USE_ENFORCEMENT_MODELS = ("gpt", "codex", "gemini", "gemma", "grok", "glm")
 # where GPT models abandon work on partial results, skip prerequisite lookups,
 # hallucinate instead of using tools, and declare "done" without verification.
 # Inspired by patterns from OpenAI's GPT-5.4 prompting guide & OpenClaw PR #38953.
+# Also applied to xAI Grok — same failure modes in practice (claims completion
+# without tool calls, suggests workarounds instead of using existing tools,
+# replies with plans/suggestions instead of executing). The body is
+# family-agnostic; the OPENAI_ prefix reflects origin, not exclusivity.
 OPENAI_MODEL_EXECUTION_GUIDANCE = (
     "# Execution discipline\n"
     "<tool_persistence>\n"

agent/system_prompt.py

@@ -156,7 +156,10 @@ def build_system_prompt_parts(agent: Any, system_message: Optional[str] = None)
                 stable_parts.append(GOOGLE_MODEL_OPERATIONAL_GUIDANCE)
             # OpenAI GPT/Codex execution discipline (tool persistence,
             # prerequisite checks, verification, anti-hallucination).
-            if "gpt" in _model_lower or "codex" in _model_lower:
+            # Also applied to xAI Grok — same failure modes (claims completion
+            # without tool calls, suggests workarounds instead of using
+            # existing tools, replies with plans instead of executing).
+            if "gpt" in _model_lower or "codex" in _model_lower or "grok" in _model_lower:
                 stable_parts.append(OPENAI_MODEL_EXECUTION_GUIDANCE)
 
     has_skills_tools = any(name in agent.valid_tool_names for name in ['skills_list', 'skill_view', 'skill_manage'])

tests/run_agent/test_run_agent.py

@@ -1074,6 +1074,40 @@ class TestToolUseEnforcementConfig:
         prompt = agent._build_system_prompt()
         assert TOOL_USE_ENFORCEMENT_GUIDANCE not in prompt
 
+    def test_auto_injects_for_grok(self):
+        """xAI Grok / xai-oauth models hit the same enforcement path as GPT."""
+        from agent.prompt_builder import TOOL_USE_ENFORCEMENT_GUIDANCE
+        agent = self._make_agent(model="x-ai/grok-4.3", tool_use_enforcement="auto")
+        prompt = agent._build_system_prompt()
+        assert TOOL_USE_ENFORCEMENT_GUIDANCE in prompt
+
+    def test_auto_injects_execution_guidance_for_grok(self):
+        """Grok also gets OPENAI_MODEL_EXECUTION_GUIDANCE (verification,
+        mandatory_tool_use, act_dont_ask). Same failure modes as GPT in
+        practice — claims completion without tool calls, suggests workarounds
+        instead of using existing tools.
+        """
+        from agent.prompt_builder import OPENAI_MODEL_EXECUTION_GUIDANCE
+        agent = self._make_agent(model="x-ai/grok-4.3", tool_use_enforcement="auto")
+        prompt = agent._build_system_prompt()
+        assert OPENAI_MODEL_EXECUTION_GUIDANCE in prompt
+
+    def test_auto_injects_execution_guidance_for_xai_oauth_model(self):
+        """xai-oauth bare model names (no slash) also match the grok pattern."""
+        from agent.prompt_builder import OPENAI_MODEL_EXECUTION_GUIDANCE
+        agent = self._make_agent(model="grok-4.3", tool_use_enforcement="auto")
+        prompt = agent._build_system_prompt()
+        assert OPENAI_MODEL_EXECUTION_GUIDANCE in prompt
+
+    def test_auto_does_not_inject_execution_guidance_for_claude(self):
+        """Sanity: execution guidance stays off for non-targeted families."""
+        from agent.prompt_builder import OPENAI_MODEL_EXECUTION_GUIDANCE
+        agent = self._make_agent(
+            model="anthropic/claude-sonnet-4", tool_use_enforcement="auto"
+        )
+        prompt = agent._build_system_prompt()
+        assert OPENAI_MODEL_EXECUTION_GUIDANCE not in prompt
+
     def test_true_forces_for_all_models(self):
         from agent.prompt_builder import TOOL_USE_ENFORCEMENT_GUIDANCE
         agent = self._make_agent(model="anthropic/claude-sonnet-4", tool_use_enforcement=True)