scriptoriumadmin/strix
1
0
Fork 0
mirror of https://github.com/usestrix/strix.git synced 2026-08-28 05:25:00 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix(llm): Pass API key and base URL to memory compressor litellm calls

Browse source 
The memory compressor was calling litellm.completion() without passing
the api_key and api_base parameters, causing authentication errors when
LLM_API_KEY is set but provider-specific env vars (OPENAI_API_KEY, etc.)
are not. This matches the pattern used in dedupe.py.
This commit is contained in:
0xallam 2026-01-28 01:26:47 -08:00 • committed by Ahmed Allam
parent c5bd30e677
commit c2fbf81f1d
1 changed files with 13 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

14
strix/llm/memory_compressor.py
View file

@ -104,12 +104,24 @@ def _summarize_messages(
conversation = "\n".join(formatted)
prompt = SUMMARY_PROMPT_TEMPLATE.format(conversation=conversation)
api_key = Config.get("llm_api_key")
api_base = (
Config.get("llm_api_base")
or Config.get("openai_api_base")
or Config.get("litellm_base_url")
or Config.get("ollama_api_base")
)
try:
completion_args = {
completion_args: dict[str, Any] = {
"model": model,
"messages": [{"role": "user", "content": prompt}],
"timeout": timeout,
}
if api_key:
completion_args["api_key"] = api_key
if api_base:
completion_args["api_base"] = api_base
response = litellm.completion(**completion_args)
summary = response.choices[0].message.content or ""