fix(agent): add qwen and deepseek to TOOL_USE_ENFORCEMENT_MODELS

When `agent.tool_use_enforcement` is `"auto"` (the default), the
runtime checks the active model name against `TOOL_USE_ENFORCEMENT_MODELS`
in `agent/prompt_builder.py` and only injects `TOOL_USE_ENFORCEMENT_GUIDANCE`
if a substring matches. Qwen and DeepSeek hit the same chatty/hallucinatory
failure mode as GPT, Codex, Grok, and GLM (describing intended actions
instead of calling tools, ignoring memory, silently stopping mid-execution),
but neither substring was in the tuple — so the enforcement prompt was
never injected for users on those families, even with `auto` left at
its default.

Add `"qwen"` and `"deepseek"` to the tuple, matching the established
additive pattern (#5595 added grok, #24715 added glm, #27797 widened
grok to xai-oauth). Add four regression-guard tests that fail before
the production change and pass after: two unit assertions in
`test_prompt_builder.py` mirroring the existing grok/gpt checks, and
two integration tests in `test_run_agent.py` confirming that a
qwen/deepseek model under `tool_use_enforcement="auto"` now gets the
guidance string in its system prompt.

The "robust" alternative from the issue (default-true for all models)
is intentionally not taken: it would silently flip behavior for users
who currently rely on `auto` leaving Claude / non-listed families
unsteered, and the maintainer's prior merged work in this area is
uniformly additive.

Fixes #28079

agent/prompt_builder.py

@@ -268,7 +268,7 @@ TOOL_USE_ENFORCEMENT_GUIDANCE = (
 
 # Model name substrings that trigger tool-use enforcement guidance.
 # Add new patterns here when a model family needs explicit steering.
-TOOL_USE_ENFORCEMENT_MODELS = ("gpt", "codex", "gemini", "gemma", "grok", "glm")
+TOOL_USE_ENFORCEMENT_MODELS = ("gpt", "codex", "gemini", "gemma", "grok", "glm", "qwen", "deepseek")
 
 # OpenAI GPT/Codex-specific execution guidance.  Addresses known failure modes
 # where GPT models abandon work on partial results, skip prerequisite lookups,

tests/agent/test_prompt_builder.py

@@ -1144,6 +1144,12 @@ class TestToolUseEnforcementGuidance:
     def test_enforcement_models_includes_grok(self):
         assert "grok" in TOOL_USE_ENFORCEMENT_MODELS
 
+    def test_enforcement_models_includes_qwen(self):
+        assert "qwen" in TOOL_USE_ENFORCEMENT_MODELS
+
+    def test_enforcement_models_includes_deepseek(self):
+        assert "deepseek" in TOOL_USE_ENFORCEMENT_MODELS
+
     def test_enforcement_models_is_tuple(self):
         assert isinstance(TOOL_USE_ENFORCEMENT_MODELS, tuple)
 

tests/run_agent/test_run_agent.py

@@ -1103,6 +1103,20 @@ class TestToolUseEnforcementConfig:
         prompt = agent._build_system_prompt()
         assert TOOL_USE_ENFORCEMENT_GUIDANCE in prompt
 
+    def test_auto_injects_for_qwen(self):
+        """Qwen models default to chatty/hallucinatory tool use without enforcement."""
+        from agent.prompt_builder import TOOL_USE_ENFORCEMENT_GUIDANCE
+        agent = self._make_agent(model="qwen/qwen3.6-plus", tool_use_enforcement="auto")
+        prompt = agent._build_system_prompt()
+        assert TOOL_USE_ENFORCEMENT_GUIDANCE in prompt
+
+    def test_auto_injects_for_deepseek(self):
+        """DeepSeek models default to chatty/hallucinatory tool use without enforcement."""
+        from agent.prompt_builder import TOOL_USE_ENFORCEMENT_GUIDANCE
+        agent = self._make_agent(model="deepseek/deepseek-r1", 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