phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-08-11 20:40:40 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix: Enable lifespan=on for uvicorn

Browse source 
Default behavior is "auto", meaning it will try lifespan, but if
something goes wrong, it will silently swallow the issue and won't use
the lifespan handler at all.

This default behavior resulted in silently breaking shutdown handlers
for providers. With this patch, server will fail to start next time
something gets borked in the middleware layer, which is good.

Related: #188

Signed-off-by: Ihar Hrachyshka <ihar.hrachyshka@gmail.com>
This commit is contained in:
Ihar Hrachyshka 2025-03-10 20:03:14 +00:00
parent 056eb68fcc
commit ca571025f5
1 changed files with 1 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

1
llama_stack/distribution/server/server.py
View file

@ -418,6 +418,7 @@ def main():
"app": app, "app": app,
"host": listen_host, "host": listen_host,
"port": port, "port": port,
"lifespan": "on",
} }
if ssl_config: if ssl_config:
uvicorn_config.update(ssl_config) uvicorn_config.update(ssl_config)