Private
Public Access
0
0

refactor(ai_client): _send_llama_result() returns Result[str]

This commit is contained in:
2026-06-12 18:46:29 -04:00
parent 64d6ba2db5
commit 6665152950
+35 -32
View File
@@ -2471,45 +2471,48 @@ def _ensure_llama_client() -> Any:
_llama_client = openai.OpenAI(api_key=_llama_api_key, base_url=_llama_base_url)
return _llama_client
def _send_llama(md_content: str, user_message: str, base_dir: str,
def _send_llama_result(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:
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
with _llama_history_lock:
user_content = user_message
if file_items:
for fi in file_items:
if fi.get("is_image") and fi.get("base64_data"):
user_content = f"[IMAGE: {fi.get('path', 'attachment')}]\n{user_content}"
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_content})
def _build_llama_request(_round_idx: int) -> OpenAICompatibleRequest:
patch_callback: Optional[Callable[[str, str], Optional[str]]] = None) -> Result[str]:
from src.openai_compatible import OpenAICompatibleRequest, _classify_openai_compatible_error
try:
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)
client = _ensure_llama_client()
tools: list[dict[str, Any]] | None = _get_deepseek_tools() or None
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>"}]
messages.extend(_llama_history)
return OpenAICompatibleRequest(
messages=messages, model=_model, temperature=_temperature, top_p=_top_p,
max_tokens=_max_tokens, stream=stream, stream_callback=stream_callback,
tools=tools, tool_choice="auto" if tools else "auto",
)
caps = get_capabilities("llama", _model)
return run_with_tool_loop(
client, _build_llama_request, capabilities=caps,
pre_tool_callback=pre_tool_callback, qa_callback=qa_callback, stream_callback=stream_callback,
patch_callback=patch_callback, base_dir=base_dir, vendor_name="llama",
history_lock=_llama_history_lock, history=_llama_history,
)
user_content = user_message
if file_items:
for fi in file_items:
if fi.get("is_image") and fi.get("base64_data"):
user_content = f"[IMAGE: {fi.get('path', 'attachment')}]\n{user_content}"
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_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>"}]
messages.extend(_llama_history)
return OpenAICompatibleRequest(
messages=messages, model=_model, temperature=_temperature, top_p=_top_p,
max_tokens=_max_tokens, stream=stream, stream_callback=stream_callback,
tools=tools, tool_choice="auto" if tools else "auto",
)
caps = get_capabilities("llama", _model)
return Result(data=run_with_tool_loop(
client, _build_llama_request, capabilities=caps,
pre_tool_callback=pre_tool_callback, qa_callback=qa_callback, stream_callback=stream_callback,
patch_callback=patch_callback, base_dir=base_dir, vendor_name="llama",
history_lock=_llama_history_lock, history=_llama_history,
))
except Exception as exc:
return Result(data="", errors=[_classify_openai_compatible_error(exc, source="ai_client.llama")])
OLLAMA_DEFAULT_BASE_URL: str = "http://localhost:11434"