fix(thinking): add deepseek-v4 to thinking model patterns (#6000)

* fix(thinking): add deepseek-v4 to thinking model patterns

deepseek-v4-flash emits reasoning_content via the API but was not
recognized in _THINKING_MODEL_PATTERNS (only deepseek-r1 and
deepseek-reasoner were listed). Add the deepseek-v4 prefix so
the model is recognized as thinking-capable.

The between-round _thinkOpen leakage was separately fixed by
PR #5931 (perf(chat): batch live thinking rendering).

Related: #3998, #5931

* test(thinking): cover DeepSeek v4 detection

---------

Co-authored-by: Alexandre Teixeira <alexandremagteixeira@gmail.com>
Co-authored-by: Alexandre Teixeira <111787685+alteixeira20@users.noreply.github.com>

src/llm_core.py

@@ -1319,8 +1319,8 @@ _MISTRAL_REASONING_EFFORT = os.getenv("ODYSSEUS_MISTRAL_REASONING_EFFORT", "high
 
 # Models that support structured thinking — may output </think> without opening tag
 _THINKING_MODEL_PATTERNS = (
-    "qwen3", "qwq", "deepseek-r1", "deepseek-reasoner", "minimax",
-    "m2-reap", "gemma", "stepfun", "step-3", "step3",
+    "qwen3", "qwq", "deepseek-r1", "deepseek-reasoner", "deepseek-v4",
+    "minimax", "m2-reap", "gemma", "stepfun", "step-3", "step3",
     "magistral", "mistral-small", "mistral-medium",
 )
 

tests/test_llm_core_thinking_models.py

@@ -0,0 +1,27 @@
+"""Regression coverage for structured-thinking model detection."""
+
+import os
+
+os.environ.setdefault("DATABASE_URL", "sqlite:///:memory:")
+
+import pytest
+
+from src.llm_core import _supports_thinking
+
+
+@pytest.mark.parametrize(
+    "model",
+    [
+        "deepseek-v4",
+        "deepseek-v4-flash",
+        "DeepSeek-V4-Flash",
+        "deepseek/deepseek-v4-flash",
+    ],
+)
+def test_deepseek_v4_models_support_thinking(model):
+    assert _supports_thinking(model) is True
+
+
+@pytest.mark.parametrize("model", ["deepseek-v3", "deepseek-chat"])
+def test_other_deepseek_models_are_not_promoted_to_thinking(model):
+    assert _supports_thinking(model) is False