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: Fix lifespan app handler not working

Browse source 
It was noticed that shutdown handlers for implementations are not
executed.

Investigation reveals that lifespan logic is not working. When server
starts, we see:

```
ASGI 'lifespan' protocol appears unsupported.
```

This is because uvicorn calls to app with a missing path on startup,
(perhaps to detect that the protocol is working?) and our
TracingMiddleware was not ready for that, resulting in an exception and
lifespan logic disabled.

Fixes #188

Signed-off-by: Ihar Hrachyshka <ihar.hrachyshka@gmail.com>
This commit is contained in:
Ihar Hrachyshka 2025-03-10 19:59:10 +00:00
parent e4acdf6d54
commit 056eb68fcc
1 changed files with 1 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

2
llama_stack/distribution/server/server.py
View file

@ -215,7 +215,7 @@ class TracingMiddleware:
self.app = app self.app = app
async def __call__(self, scope, receive, send): async def __call__(self, scope, receive, send):
path = scope["path"] path = scope.get("path", "")
await start_trace(path, {"__location__": "server"}) await start_trace(path, {"__location__": "server"})
try: try:
return await self.app(scope, receive, send) return await self.app(scope, receive, send)