Scott.Idem/Cortex-Inara
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix: apply host_type path correction in OpenAI orchestrator

Browse Source 
The AsyncOpenAI client always appends /chat/completions to base_url.
Open WebUI's endpoint is at /api/chat/completions, so for openwebui
host_type the base_url must include the /api prefix — same logic as
_local() in llm_client.py.

Also strip non-standard metadata fields (backend, host, etc.) from
session_messages before passing them to the API.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
Scott Idem
2026-04-08 23:16:33 -04:00
parent 869a596f4b
commit 27ca7c7efd
1 changed files with 15 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

19
cortex/openai_orchestrator.py
View File

@@ -62,24 +62,35 @@ async def run(
if not model_cfg: if not model_cfg:
raise RuntimeError("model_cfg is required for the OpenAI orchestrator") raise RuntimeError("model_cfg is required for the OpenAI orchestrator")
api_url = model_cfg.get("api_url", "") api_url = model_cfg.get("api_url", "")
api_key = model_cfg.get("api_key", "") or "none" api_key = model_cfg.get("api_key", "") or "none"
model_name = model_cfg.get("model_name", "") model_name = model_cfg.get("model_name", "")
host_type = model_cfg.get("host_type", "openwebui")
if not api_url or not model_name: if not api_url or not model_name:
raise RuntimeError( raise RuntimeError(
f"model_cfg missing api_url or model_name: {model_cfg.get('label', model_cfg)}" f"model_cfg missing api_url or model_name: {model_cfg.get('label', model_cfg)}"
) )
client = AsyncOpenAI(base_url=api_url, api_key=api_key) # Open WebUI's OpenAI-compatible endpoint lives at /api/chat/completions,
# so the SDK base_url needs the /api prefix; standard OpenAI-layout hosts don't.
base_url = api_url.rstrip("/")
if host_type == "openwebui":
base_url = base_url + "/api"
client = AsyncOpenAI(base_url=base_url, api_key=api_key)
# System prompt: persona context + brief tool instruction # System prompt: persona context + brief tool instruction
sys_content = (system_prompt or "") + _TOOL_INSTRUCTION sys_content = (system_prompt or "") + _TOOL_INSTRUCTION
# Build messages: [system, ...recent_session, current_task] # Build messages: [system, ...recent_session, current_task]
# Strip non-standard metadata fields (backend, host, etc.) before sending.
messages: list[dict] = [{"role": "system", "content": sys_content}] messages: list[dict] = [{"role": "system", "content": sys_content}]
if session_messages: if session_messages:
messages.extend(session_messages[-6:]) # last 3 turns for context messages.extend(
{"role": m["role"], "content": m["content"]}
for m in session_messages[-6:]
)
messages.append({"role": "user", "content": task}) messages.append({"role": "user", "content": task})
tool_call_log: list[dict] = [] tool_call_log: list[dict] = []