feat(ai_client): add native Ollama adapter; route localhost to it

When _llama_base_url is localhost/127.0.0.1, _send_llama now
calls _send_llama_native (the native /api/chat adapter)
instead of the OpenAI-compat path. The native adapter
supports Ollama's vendor-specific fields: think, images,
thinking.

Functions added (in src/ai_client.py, per the naming
convention HARD RULE on no new src/*.py files):

  ollama_chat(model, messages, *, think='low', images=None,
              tools=None, base_url=OLLAMA_DEFAULT_BASE_URL)
    -> dict[str, Any]

  _send_llama_native(md_content, user_message, base_dir,
                     file_items=None, discussion_history='',
                     stream=False, ...callbacks) -> str

  OLLAMA_DEFAULT_BASE_URL: str = 'http://localhost:11434'

Implementation notes:
- requests loaded via _require_warmed('requests') (local
  scope; preserves startup_speedup_20260606 invariant that
  heavy SDKs are warmed on _io_pool, not imported at module
  level)
- _send_llama dispatches based on 'localhost' in
  _llama_base_url (same check already used by
  _get_llama_cost_tracking at line 2500)
- Removed orphan def stub at the old _send_llama body (the
  dead 'def _build_llama_request' that was overwritten by
  the real one — a known session issue with stale set_file_slice
  edits)
- Native adapter appends the 'thinking' field to history so
  subsequent rounds preserve the reasoning chain

Tests:
- 7 new tests in tests/test_llama_ollama_native.py:
  * ollama_chat hits /api/chat (not /v1/chat/completions)
  * ollama_chat includes 'think' param in payload
  * ollama_chat includes 'images' in payload
  * _send_llama_native wraps ollama_chat
  * _send_llama_native preserves 'thinking' field
  * _send_llama routes localhost to native (no openai client)
  * _send_llama keeps openai path for non-local (no POST)
- Updated test_send_llama_ollama_backend in test_llama_provider.py
  to mock the native path (was: mocked openai-compat; now:
  mocked requests.post)
- 103/103 vendor+tool+provider+import-isolation tests pass
  (no regressions; +7 new tests this commit)
- 4 audit scripts pass

src/ai_client.py

@@ -2460,6 +2460,8 @@ def _send_llama(md_content: str, user_message: str, base_dir: str,
  qa_callback: Optional[Callable[[str], str]] = None,
  stream_callback: Optional[Callable[[str], None]] = None,
  patch_callback: Optional[Callable[[str, str], Optional[str]]] = None) -> str:
+ if "localhost" in _llama_base_url or "127.0.0.1" in _llama_base_url:
+  return _send_llama_native(md_content, user_message, base_dir, file_items, discussion_history, stream, pre_tool_callback, qa_callback, stream_callback, patch_callback)
  from src.openai_compatible import OpenAICompatibleRequest
  client = _ensure_llama_client()
  tools: list[dict[str, Any]] | None = _get_deepseek_tools() or None
@@ -2473,8 +2475,6 @@ def _send_llama(md_content: str, user_message: str, base_dir: str,
    _llama_history.append({"role": "user", "content": f"[DISCUSSION HISTORY]\n\n{discussion_history}\n\n---\n\n{user_message}"})
   else:
    _llama_history.append({"role": "user", "content": user_content})
- def _build_llama_request(_round_idx: int) -> OpenAICompatibleRequest:
-   _llama_history.append({"role": "user", "content": user_content})
  def _build_llama_request(_round_idx: int) -> OpenAICompatibleRequest:
   with _llama_history_lock:
    messages: list[dict[str, Any]] = [{"role": "system", "content": f"{_get_combined_system_prompt()}\n\n<context>\n{md_content}\n</context>"}]
@@ -2492,6 +2492,58 @@ def _send_llama(md_content: str, user_message: str, base_dir: str,
   history_lock=_llama_history_lock, history=_llama_history,
  )
 
+OLLAMA_DEFAULT_BASE_URL: str = "http://localhost:11434"
+
+def ollama_chat(
+ model: str,
+ messages: list[dict[str, Any]],
+ *,
+ think: str = "low",
+ images: list[str] | None = None,
+ tools: list[dict[str, Any]] | None = None,
+ base_url: str = OLLAMA_DEFAULT_BASE_URL,
+ ) -> dict[str, Any]:
+ requests = _require_warmed("requests")
+ payload: dict[str, Any] = {"model": model, "messages": messages, "stream": False}
+ if think:
+  payload["think"] = think
+ if images:
+  payload["images"] = images
+ if tools:
+  payload["tools"] = tools
+ resp = requests.post(f"{base_url}/api/chat", json=payload, timeout=120)
+ return resp.json()
+
+def _send_llama_native(md_content: str, user_message: str, base_dir: str,
+ file_items: list[dict[str, Any]] | None = None,
+ discussion_history: str = "",
+ stream: bool = False,
+ pre_tool_callback: Optional[Callable[[str, str, Optional[Callable[[str], str]]], Optional[str]]] = None,
+ qa_callback: Optional[Callable[[str], str]] = None,
+ stream_callback: Optional[Callable[[str], None]] = None,
+ patch_callback: Optional[Callable[[str, str], Optional[str]]] = None) -> str:
+ base_url = _llama_base_url.replace("/v1", "")
+ with _llama_history_lock:
+  if discussion_history and not _llama_history:
+   _llama_history.append({"role": "user", "content": f"[DISCUSSION HISTORY]\n\n{discussion_history}\n\n---\n\n{user_message}"})
+  else:
+   _llama_history.append({"role": "user", "content": user_message})
+  messages: list[dict[str, Any]] = [{"role": "system", "content": f"{_get_combined_system_prompt()}\n\n<context>\n{md_content}\n</context>"}]
+  messages.extend(_llama_history)
+  images: list[str] = []
+  if file_items:
+   for fi in file_items:
+    if fi.get("is_image") and fi.get("base64_data"):
+     images.append(fi["base64_data"])
+ response = ollama_chat(_model, messages, images=images, base_url=base_url)
+ text = response.get("message", {}).get("content", "")
+ thinking = response.get("message", {}).get("thinking", "")
+ with _llama_history_lock:
+  msg: dict[str, Any] = {"role": "assistant", "content": text or None}
+  if thinking:
+   msg["thinking"] = thinking
+  _llama_history.append(msg)
+ return (f"<thinking>\n{thinking}\n</thinking>\n" if thinking else "") + text
 def _list_llama_models() -> list[str]:
  from src.vendor_capabilities import list_models_for_vendor
  return list_models_for_vendor("llama")

tests/test_llama_ollama_native.py

@@ -0,0 +1,128 @@
+"""Red tests for native Ollama adapter (_send_llama_native + ollama_chat).
+
+When _llama_base_url points at localhost/127.0.0.1 (Ollama default), _send_llama
+should route to a native adapter that POSTs to /api/chat (NOT the OpenAI-compat
+/v1/chat/completions endpoint). The native adapter supports Ollama's vendor-
+specific fields: think, images, thinking.
+
+This file is t4_2 (red phase) of qwen_llama_grok_followup_20260611 Phase 4.
+"""
+from unittest.mock import MagicMock, patch
+import pytest
+from src import ai_client
+
+@pytest.fixture(autouse=True)
+def _reset_llama_state():
+ if hasattr(ai_client, '_llama_client'):
+  ai_client._llama_client = None
+ if hasattr(ai_client, '_llama_history'):
+  ai_client._llama_history = []
+ if hasattr(ai_client, '_llama_base_url'):
+  ai_client._llama_base_url = "http://localhost:11434/v1"
+ if hasattr(ai_client, '_llama_api_key'):
+  ai_client._llama_api_key = "ollama"
+ yield
+
+def _mock_requests_with(post_response: MagicMock):
+ """Return a context manager that patches _require_warmed('requests') with a mock whose .post returns the given response."""
+ mock_requests = MagicMock()
+ mock_requests.post.return_value = post_response
+ return patch("src.ai_client._require_warmed", return_value=mock_requests)
+
+def test_ollama_chat_posts_to_native_api_chat_endpoint() -> None:
+ """ollama_chat hits /api/chat (not /v1/chat/completions) and returns parsed JSON."""
+ mock_response = MagicMock()
+ mock_response.json.return_value = {
+  "message": {"role": "assistant", "content": "ok"},
+  "done": True,
+ }
+ with _mock_requests_with(mock_response) as warm:
+  result = ai_client.ollama_chat(model="llama3.2:3b", messages=[{"role": "user", "content": "hi"}])
+  assert result["message"]["content"] == "ok"
+  post = warm.return_value.post
+  called_url = post.call_args.args[0]
+  assert called_url == "http://localhost:11434/api/chat"
+  payload = post.call_args.kwargs["json"]
+  assert payload["model"] == "llama3.2:3b"
+  assert payload["stream"] is False
+  assert payload["messages"] == [{"role": "user", "content": "hi"}]
+
+def test_ollama_chat_includes_think_param_when_set() -> None:
+ """Ollama native adapter should set the 'think' field in the payload."""
+ mock_response = MagicMock()
+ mock_response.json.return_value = {"message": {"content": "ok"}, "done": True}
+ with _mock_requests_with(mock_response) as warm:
+  ai_client.ollama_chat(model="qwen3:8b", messages=[{"role": "user", "content": "x"}], think="high")
+  payload = warm.return_value.post.call_args.kwargs["json"]
+  assert payload["think"] == "high"
+
+def test_ollama_chat_includes_images_when_provided() -> None:
+ """Ollama native adapter should include images in the payload (base64 strings)."""
+ mock_response = MagicMock()
+ mock_response.json.return_value = {"message": {"content": "i see a cat"}, "done": True}
+ with _mock_requests_with(mock_response) as warm:
+  ai_client.ollama_chat(
+   model="llama3.2-vision:11b",
+   messages=[{"role": "user", "content": "describe this"}],
+   images=["iVBOR..."],
+  )
+  payload = warm.return_value.post.call_args.kwargs["json"]
+  assert payload["images"] == ["iVBOR..."]
+
+def test_send_llama_native_calls_ollama_chat_when_localhost() -> None:
+ """_send_llama_native wraps ollama_chat and returns the message content."""
+ ai_client.set_provider("llama", "llama-3.2-3b-preview")
+ ai_client._llama_base_url = "http://localhost:11434/v1"
+ mock_response = MagicMock()
+ mock_response.json.return_value = {
+  "message": {"role": "assistant", "content": "hi from native ollama"},
+  "done": True,
+ }
+ with _mock_requests_with(mock_response):
+  result = ai_client._send_llama_native("system", "user", ".", None, "", False, None, None, None)
+  assert "hi from native ollama" in result
+
+def test_send_llama_native_preserves_thinking_field() -> None:
+ """Ollama's 'thinking' field should be captured and rendered in the output."""
+ ai_client.set_provider("llama", "qwen3:8b")
+ ai_client._llama_base_url = "http://localhost:11434/v1"
+ mock_response = MagicMock()
+ mock_response.json.return_value = {
+  "message": {"role": "assistant", "content": "answer", "thinking": "I thought about it"},
+  "done": True,
+ }
+ with _mock_requests_with(mock_response):
+  result = ai_client._send_llama_native("system", "user", ".", None, "", False, None, None, None)
+  assert "I thought about it" in result
+  assert "answer" in result
+
+def test_send_llama_routes_to_native_when_localhost() -> None:
+ """The dispatcher in _send_llama must route localhost/127.0.0.1 to _send_llama_native."""
+ ai_client.set_provider("llama", "llama-3.2-3b-preview")
+ ai_client._llama_base_url = "http://localhost:11434/v1"
+ mock_response = MagicMock()
+ mock_response.json.return_value = {
+  "message": {"role": "assistant", "content": "via native"},
+  "done": True,
+ }
+ with _mock_requests_with(mock_response), \
+      patch("src.ai_client._ensure_llama_client") as ensure:
+  result = ai_client._send_llama("system", "user", ".", None, "", False, None, None, None)
+  assert "via native" in result
+  assert not ensure.called, "_send_llama should NOT instantiate the openai client for native backend"
+
+def test_send_llama_keeps_openai_path_for_non_local() -> None:
+ """_send_llama must NOT route to native for non-localhost URLs (custom server, OpenRouter)."""
+ ai_client.set_provider("llama", "llama-3.1-70b-versatile")
+ ai_client._llama_base_url = "https://openrouter.ai/api/v1"
+ mock_client = MagicMock()
+ mock_client.chat.completions.create.return_value = MagicMock(
+  choices=[MagicMock(message=MagicMock(content="via openrouter", tool_calls=[]))],
+  usage=MagicMock(prompt_tokens=5, completion_tokens=3),
+ )
+ with patch("src.ai_client._ensure_llama_client", return_value=mock_client) as ensure, \
+      _mock_requests_with(MagicMock(json=MagicMock(return_value={}))) as warm:
+  result = ai_client._send_llama("system", "user", ".", None, "", False, None, None, None)
+  assert "via openrouter" in result
+  assert ensure.called
+  assert not warm.return_value.post.called, "non-local backend must NOT hit Ollama's /api/chat"

tests/test_llama_provider.py

@@ -17,14 +17,18 @@ def _reset_llama_state():
 def test_send_llama_ollama_backend(monkeypatch: pytest.MonkeyPatch) -> None:
  ai_client._llama_base_url = "http://localhost:11434/v1"
  ai_client.set_provider("llama", "llama-3.2-3b-preview")
- mock_client = MagicMock()
+ mock_response = MagicMock()
- mock_client.chat.completions.create.return_value = MagicMock(
+ mock_response.json.return_value = {
-  choices=[MagicMock(message=MagicMock(content="hi from ollama", tool_calls=[]))],
+  "message": {"role": "assistant", "content": "hi from ollama"},
-  usage=MagicMock(prompt_tokens=5, completion_tokens=3),
+  "done": True,
- )
+ }
- with patch("src.ai_client._ensure_llama_client", return_value=mock_client):
+ mock_requests = MagicMock()
+ mock_requests.post.return_value = mock_response
+ with patch("src.ai_client._require_warmed", return_value=mock_requests):
   result = ai_client._send_llama("system", "user", ".", None, "", False, None, None, None)
-  assert result == "hi from ollama"
+  assert "hi from ollama" in result
+  called_url = mock_requests.post.call_args.args[0]
+  assert called_url == "http://localhost:11434/api/chat"
 
 def test_send_llama_openrouter_backend(monkeypatch: pytest.MonkeyPatch) -> None:
  ai_client._llama_base_url = "https://openrouter.ai/api/v1"