mirror of
https://github.com/katanemo/plano.git
synced 2026-06-23 15:38:07 +02:00
fix(llm_gateway): buffer non-streaming response body until end_of_stream
Wait for the full upstream body before JSON parsing to avoid truncated responses on chunked replies. Retry currency_exchange demo tests on flake. Co-authored-by: Musa <musa@spherrrical.dev>
This commit is contained in:
parent
e5f0cee39e
commit
420431b30c
2 changed files with 8 additions and 1 deletions
|
|
@ -19,7 +19,8 @@ run_hurl_with_retries() {
|
|||
local max_attempts=1
|
||||
local attempt=1
|
||||
|
||||
if [ "$demo_name" = "llm_routing/preference_based_routing" ]; then
|
||||
if [ "$demo_name" = "llm_routing/preference_based_routing" ] \
|
||||
|| [ "$demo_name" = "advanced/currency_exchange" ]; then
|
||||
max_attempts=3
|
||||
fi
|
||||
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue